ABCDEFGJKNO
1
NameRelevanceGoogle Scholar ProfileGoogle Scholar Citation CountGoogle Scholar Role/InstitutionGoogle Scholar CollaboratorsGoogle Scholar Search LinkGoogle Result 1 TitleGoogle Result 1 SnippetGoogle Result 1 TitleGoogle Result 2 Snippet
2
Thomas Serre100https://scholar.google.com/citations?user=kZlPW4wAAAAJ&hl=en&num=2&oi=ao13290Brown University and ANR-3IA Artificial and Natural Intelligence Toulouse InstituteTOMASO POGGIO, Huei-han Jhuang, Maximilian Riesenhuber, Lior Wolf, Hilde Kuehne, Estibaliz Garrote, Bernd Heisele, Drew Linsley, Stanley Bileschi, Gabriel Kreiman, Cheston Tan, Sven Eberhardt, David Alex Mély, Massimiliano Pontil, Ali Bilgin Arslan, PhD, Aude Oliva, Charles Cadieu, Ulf Knoblich, Sharat Chikkerur, Samuel Prenticehttps://scholar.google.com/scholar?q=author%3A%22Thomas+Serre%22&hl=en&num=2HMDB: a large video database for human motion recognitionWith nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video. While much effort has been devoted to the collection and annotation of large scalable static image datasets containing …Robust object recognition with cortex-like mechanismsWe introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature …
3
Antonio Torralba100https://scholar.google.com/citations?user=8cxDHS4AAAAJ&hl=en&num=2&oi=ao80260Professor of Computer Science, MITAude Oliva, William T. Freeman, Bolei Zhou, Aditya Khosla, Sanja Fidler, Jianxiong Xiao, Carl Vondrick, Joshua B. Tenenbaum, Kevin Murphy, Krista Ehinger, Àgata Lapedriza, Fredo Durand, Rob Fergus, Hamed Pirsiavash, David Bau, Hang Zhao, Bryan Russell, Jun-Yan Zhu, Jiajun Wu, Ruslan Salakhutdinovhttps://scholar.google.com/scholar?q=author%3A%22Antonio+Torralba%22&hl=en&num=2Modeling the shape of the scene: A holistic representation of the spatial envelopeIn this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. The procedure is based on a very low dimensional representation of the scene, that we term the …Learning deep features for discriminative localizationIn this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on image-level labels. While this technique was …
4
Andrew Zisserman71https://scholar.google.com/citations?user=UZ5wscMAAAAJ&hl=en&num=2&oi=ao263620University of OxfordKaren Simonyan, Andrea Vedaldi, Josef Sivic, Luc Van Gool, Andrew Fitzgibbon, Philip Torr, Andrew Blake, David Forsyth, Joon Son Chung, Relja Arandjelović / Реља Аранђелов..., Omkar M Parkhi, Cordelia Schmid, Timor Kadir, Pietro Perona, Chris Williams, Frederik Schaffalitzky, João Carreira, John Winn, Victor Lempitsky, Ken Chatfieldhttps://scholar.google.com/scholar?q=author%3A%22Andrew+Zisserman%22&hl=en&num=2Visual reconstructionThis book deals with vision as a computational problem. It presents visual reconstruction from the mechanical viewpoint, which is more natural for representation of a priori knowledge about visible surfaces or about distributions of visual quantities such as intensity …Very deep convolutional networks for large-scale image recognitionIn this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters …
5
Bernt Schiele71https://scholar.google.com/citations?user=z76PBfYAAAAJ&hl=en&num=2&oi=ao65820Professor, Max Planck Institute for Informatics, Saarland Informatics Campus, Saarland UniversityMario Fritz, Rodrigo Benenson, Mykhaylo Andriluka, Stefan Roth, Christian Wojek, Zeynep Akata, Marcus Rohrbach, Bastian Leibe, Leonid Pishchulin, Michael Stark, Matthias Hein, Mohamed Omran, James Crowley, Ales Leonardis, Peter Gehler, Anna Khoreva, Jan Hosang, Qianru Sun 孙倩茹, Bjoern Andres, Siyu Tanghttps://scholar.google.com/scholar?q=author%3A%22Bernt+Schiele%22&hl=en&num=2The cityscapes dataset for semantic urban scene understandingVisual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding …Pedestrian detection: An evaluation of the state of the artPedestrian detection is a key problem in computer vision, with several applications that have the potential to positively impact quality of life. In recent years, the number of approaches to detecting pedestrians in monocular images has grown steadily. However, multiple data sets …
6
Laurent Itti71https://scholar.google.com/citations?user=xhUvqK8AAAAJ&hl=en&num=2&oi=ao47892Professor of Computer Science, University of Southern CaliforniaChristof Koch, Ali Borji, Douglas Munoz, Christian Siagian, Pierre Baldi, Ernst Niebur, Linda Chang, Dicky Nauli Sihite, thomas ernst, Brian White, David J. Berg, Jochen Braun, Vidhya Navalpakkam, Susan Boehnke, PhD, Po-He Tseng, Terrell Mundhenk, Chin-Kai Chang, Farhan Baluch, Jiaping Zhao, Emmanuel Ittihttps://scholar.google.com/scholar?q=author%3A%22Laurent+Itti%22&hl=en&num=2A model of saliency-based visual attention for rapid scene analysisA visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in …Computational modelling of visual attentionFive important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment. First, the perceptual saliency of stimuli critically depends on the surrounding …
7
Pascal Fua71https://scholar.google.com/citations?user=kzFmAkYAAAAJ&hl=en&num=2&oi=ao55635Professor Computer Science, EPFLVincent Lepetit, Mathieu Salzmann, François Fleuret, Kevin Smith, Sabine Süsstrunk, Francesc Moreno-Noguer, Raquel Urtasun, Daniel Thalmann, Slobodan Ilic, Raphael Sznitman, David J Fleet, Olivier Faugeras, Dimitris Samarashttps://scholar.google.com/scholar?q=author%3A%22Pascal+Fua%22&hl=en&num=2SLIC superpixels compared to state-of-the-art superpixel methodsComputer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five …Brief: Binary robust independent elementary featuresWe propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using simple intensity difference tests. Furthermore, the descriptor similarity …
8
Guillermo Sapiro57https://scholar.google.com/citations?user=ISRNX3gAAAAJ&hl=en&num=2&oi=ao72764James B. Duke Professor at Duke University and Senior Research Scientist, Health AI, at Apple, Inc.Ron Kimmel, Allen Tannenbaum, Julien Mairal, Noam Harel, Pablo Sprechmann, Iman Aganj, Alex Bronstein, Paul Thompson, Francis Bach, S osher, Essa Yacoub, Jean Ponce, Ignacio Francisco Ramirez Paulino, Coloma Ballester, Facundo Mémoli, Kedar Patwardhan, Xue Bai, Michael J. Black, Michael Bronstein, Patrick Teohttps://scholar.google.com/scholar?q=author%3A%22Guillermo+Sapiro%22&hl=en&num=2Geodesic active contoursA novel scheme for the detection of object boundaries is presented. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The evolving contours naturally split and merge, allowing the simultaneous detection of …Image inpaintingInpainting, the technique of modifying an image in an undetectable form, is as ancient as art itself. The goals and applications of inpainting are numerous, from the restoration of damaged paintings and photographs to the removal/replacement of selected objects. In this …
9
Kai Yu57https://scholar.google.com/citations?user=y5zkBeMAAAAJ&hl=en&num=2&oi=ao25931Founder&CEO of Horizon Robotics , Founder of Baidu IDL and Baidu Autonomous Drivinghttps://scholar.google.com/scholar?q=author%3A%22Kai+Yu%22&hl=en&num=2Circulating angiogenic factors and the risk of preeclampsiaBackground The cause of preeclampsia remains unclear. Limited data suggest that excess circulating soluble fms-like tyrosine kinase 1 (sFlt-1), which binds placental growth factor (PlGF) and vascular endothelial growth factor (VEGF), may have a pathogenic role. Methods …3D convolutional neural networks for human action recognitionWe consider the automated recognition of human actions in surveillance videos. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. Convolutional neural networks (CNNs) are a type of deep model that can act …
10
Yaser Sheikh57https://scholar.google.com/citations?user=Yd4KvooAAAAJ&hl=en&num=2&oi=ao16791Director, Facebook Reality Labs (Pittsburgh)Tomas Simon, Takeo Kanade, Shih-En Wei, Hanbyul Joo, Zhe Cao, Hyun Soo Park, Jessica Hodgins, Jason Saragih, Varun Ramakrishna, Ginés Hidalgo, Takaaki Shiratori, Sohaib Khan, Eakta Jain, Ijaz Akhter, martial hebert, Natasha Kholgade Banerjee, Shohei Nobuhara, Omar Javedhttps://scholar.google.com/scholar?q=author%3A%22Yaser+Sheikh%22&hl=en&num=2OpenPose: realtime multi-person 2D pose estimation using Part Affinity FieldsRealtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses …Realtime multi-person 2d pose estimation using part affinity fieldsWe present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture …
11
Shree K. Nayar57https://scholar.google.com/scholar?q=author%3A%22Shree+K.+Nayar%22&hl=en&num=2Reflectance and texture of real-world surfacesIn this work, we investigate the visual appearance of real-world surfaces and the dependence of appearance on the geometry of imaging conditions. We discuss a new texture representation called the BTF (bidirectional texture function) which captures the …Visual learning and recognition of 3-D objects from appearanceThe problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two …
12
Subhashini Venugopalan43https://scholar.google.com/citations?user=TmWYBeEAAAAJ&hl=en&num=2&oi=ao12723University of Texas at AustinKate Saenko, Marcus Rohrbach, Trevor Darrell, Raymond Mooney, Lisa Anne M Hendricks, Jeff Donahue, Sergio Guadarrama, Varun Gulshan, Jesse Thomason, C.Pandu Ranganhttps://scholar.google.com/scholar?q=author%3A%22Subhashini+Venugopalan%22&hl=en&num=2Long-term recurrent convolutional networks for visual recognition and descriptionAbstract Models comprised of deep convolutional network layers have dominated recent image interpretation tasks; we investigate whether models which are also compositional, or" deep", temporally are effective on tasks involving visual sequences or label sequences. We …Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographsImportance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to …
13
Ross Girshick43https://scholar.google.com/citations?user=W8VIEZgAAAAJ&hl=en&num=2&oi=ao196069Research Scientist, Facebook AI Research (FAIR)Kaiming He, Piotr Dollár, Trevor Darrell, Jitendra Malik, Jeff Donahue, C. Lawrence Zitnick, bharath hariharan, Jian Sun, Deva Ramanan, Pedro Felzenszwalb, Georgia Gkioxari, Shaoqing Ren, Ali Farhadi, Yangqing Jia, Tsung-Yi Lin, David McAllester, Pablo Arbelaez, Joseph Redmon, Sergey Karayev, Sergio Guadarramahttps://scholar.google.com/scholar?q=author%3A%22Ross+Girshick%22&hl=en&num=2Object detection with discriminatively trained part-based modelsWe describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models …Focal loss for dense object detectionThe highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of …
14
Stefano Soatto43https://scholar.google.com/citations?user=lH1PdF8AAAAJ&hl=en&num=2&oi=ao25076Professor of Computer Science, UCLAPaolo Favaro, Anthony Yezzi, Yi Ma (马毅), Pietro Perona, Alessandro Chiuso, Hailin Jin, Shankar Sastry, Alessandro Achille, Andrea Vedaldi, Jana Kosecka, Avinash Ravichandran, Gianfranco Doretto, Daniel Cremers, Rene Vidal, Byung-Woo Hong, Pratik Chaudhari, Brian Fulkerson, Ying Nian Wu, Michalis Raptis, Alper Ayvacihttps://scholar.google.com/scholar?q=author%3A%22Stefano+Soatto%22&hl=en&num=2An invitation to 3-d vision: from images to geometric modelsThis book is intended to give students at the advanced undergraduate or introduc tory graduate level, and researchers in computer vision, robotics and computer graphics, a self-contained introduction to the geometry of three-dimensional (3-D) vision. This is the study of …Meta-learning with differentiable convex optimizationMany meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base …
15
Daniel Cremers43https://scholar.google.com/citations?user=cXQciMEAAAAJ&hl=en&num=2&oi=ao46926Technical University of MunichJürgen Sturm, Thomas Brox, Vladimir Golkov, Jakob Engel, Thomas Pock, Andreas Wedel, Emanuele Rodolà, Laura Leal-Taixé, Christoph Schnörr, Jörg Stückler, Caner Hazirbas, Michael Moeller, Horst Bischof, Christian Kerl, Bodo Rosenhahn, Thomas Schoenemann, Vladyslav Usenko, Stefano Soatto, Evgeny Strekalovskiy, Rui Wang (王锐)https://scholar.google.com/scholar?q=author%3A%22Daniel+Cremers%22&hl=en&num=2LSD-SLAM: Large-scale direct monocular SLAMWe propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the environment. Along with highly accurate pose estimation based on direct image alignment …A benchmark for the evaluation of RGB-D SLAM systemsIn this paper, we present a novel benchmark for the evaluation of RGB-D SLAM systems. We recorded a large set of image sequences from a Microsoft Kinect with highly accurate and time-synchronized ground truth camera poses from a motion capture system. The …
16
Hanspeter Pfister43https://scholar.google.com/citations?user=VWX-GMAAAAAJ&hl=en&num=2&oi=ao28065An Wang Professor of Computer Science, Harvard UniversityWojciech Matusik, Markus Gross, Matthias Zwicker, Arie Kaufman, Johanna Beyer, Markus Hadwiger, Michelle Anne Borkin, Bernd Bickel, Kalyan Sunkavalli, Fredo Durand, Won-Ki Jeong, Hugh C. Lauer, Alexander Lex, Deqing Sun, Nicolas Bonneel, Raghu Machiraju, Seymour Knowles-Barley, Leonard McMillan, Tim Weyrich, Kevin Dalehttps://scholar.google.com/scholar?q=author%3A%22Hanspeter+Pfister%22&hl=en&num=2Surfels: Surface elements as rendering primitivesSurface elements (surfels) are a powerful paradigm to efficiently render complex geometric objects at interactive frame rates. Unlike classical surface discretizations, ie, triangles or quadrilateral meshes, surfels are point primitives without explicit connectivity. Surfel …Surface splattingModern laser range and optical scanners need rendering techniques that can handle millions of points with high resolution textures. This paper describes a point rendering and texture filtering technique called surface splatting which directly renders opaque and …
17
Peter Belhumeur43https://scholar.google.com/citations?user=J8YyZugAAAAJ&hl=en&num=2&oi=ao44969Professor of Computer Science, Columbia UniversityDavid Kriegman, Shree Nayar, Neeraj Kumar, David W. Jacobs, Tolga Eren, Ravi Ramamoorthi, A Stephen Morse, Brian Anderson, Thomas Berg, Todd Zickler, Joao Hespanha, Gregory Hager, W. John Kress, Alexander C Berg, Satya Mallick, Dhruv Mahajan, Y. Richard Yang, Jinwei Gu, Steven Feiner, Sean Whitehttps://scholar.google.com/scholar?q=author%3A%22Peter+Belhumeur%22&hl=en&num=2Eigenfaces vs. fisherfaces: Recognition using class specific linear projectionWe develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the …From few to many: Illumination cone models for face recognition under variable lighting and poseWe present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possible illumination conditions, is a convex cone in the …
18
Ramesh Raskar43https://scholar.google.com/citations?user=8hpOmVgAAAAJ&hl=en&num=2&oi=ao35296Associate Professor, MIT Media LabAmit Agrawal, Gordon Wetzstein, Douglas Lanman, Achuta Kadambi, Otkrist Gupta, Paul Beardsley, Jeroen van Baar, Matthew Hirsch, Nikhil Naik, Ashok Veeraraghavan, Ankit Mohan, Ayush Bhandari, Greg Welch, Henry Fuchs, Paul H. Dietz, Barmak Heshmat, Thomas Willwacher, Shree Nayar, Oliver Bimber, Praneeth Vepakommahttps://scholar.google.com/scholar?q=author%3A%22Ramesh+Raskar%22&hl=en&num=2Spatial augmented reality: merging real and virtual worldsSpatial Augmented Reality is a rapidly emerging field which concerns everyone working in digital art and media who uses any aspects of augmented reality and is interested in cutting-edge technology of display technologies and the impact of computer graphics. We believe …Image-based visual hullsIn this paper, we describe an efficient image-based approach to computing and shading visual hulls from silhouette image data. Our algorithm takes advantage of epipolar geometry and incremental computation to achieve a constant rendering cost per rendered pixel. It …
19
Ali Farhadi43https://scholar.google.com/citations?user=jeOFRDsAAAAJ&hl=en&num=2&oi=ao53651Associate Professor, Computer Science and Engineering, University of WashingtonJoseph Redmon, Mohammad Rastegari, Santosh Kumar Divvala, Hannaneh Hajishirzi, Ross Girshick, Aniruddha Kembhavi, Roozbeh Mottaghi, David Forsyth, Abhinav Gupta, Minjoon Seo, Ian Endres, Derek Hoiem, Yejin Choi, Vicente Ordóñez, Dieter Fox, Hessam Bagherinezhad, Gunnar Atli Sigurdsson, Xiaolong Wang, Junyuan Xie, Min Sunhttps://scholar.google.com/scholar?q=author%3A%22Ali+Farhadi%22&hl=en&num=2Yolov3: An incremental improvementWe present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 …You only look once: Unified, real-time object detectionWe present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class …
20
Pietro Perona43https://scholar.google.com/citations?user=j29kMCwAAAAJ&hl=en&num=2&oi=ao103328California Institute of TechnologySerge Belongie, Piotr Dollár, Jitendra Malik, Li Fei-Fei, Christof Koch, Peter Welinder, Rob Fergus, Andrew Zisserman, Michael Maire, Stefano Soatto, Steve Branson, James Hays, Michael C. Burl, Tsung-Yi Lin, Deva Ramanan, Max Welling, Mario E. Munich, Grant Van Horn, Luis Goncalves, Xavier P. Burgos-Artizzuhttps://scholar.google.com/scholar?q=author%3A%22Pietro+Perona%22&hl=en&num=2Scale-space and edge detection using anisotropic diffusionA new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interregion smoothing. It is shown …Microsoft coco: Common objects in contextWe present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex …
21
Alan Cowen43https://scholar.google.com/citations?user=-i9gbsAAAAAJ&hl=en&num=2&oi=ao925University of California, BerkeleyDacher Keltner, Disa Sauter, Jessica L Tracy, Gautam Prasad, Florian Schroff, Hillary Anger Elfenbein, Marvin M. Chun, Brice Kuhl, Hartwig Adam, Yukiyasu Kamitani, Gaurav Nemade, Dorottya Demszky, Dana Alon (prev. Movshovitz-Attias), Daniel Cordaro, Rui Sun, Shanmukh Kamble, Tomoyasu HORIKAWA, Jennifer J. Sun, Ting Liu, Robert Thomas Knighthttps://scholar.google.com/scholar?q=author%3A%22Alan+Cowen%22&hl=en&num=2Self-report captures 27 distinct categories of emotion bridged by continuous gradientsEmotions are centered in subjective experiences that people represent, in part, with hundreds, if not thousands, of semantic terms. Claims about the distribution of reported emotional states and the boundaries between emotion categories—that is, the geometric …Mapping the passions: Toward a high-dimensional taxonomy of emotional experience and expressionWhat would a comprehensive atlas of human emotions include? For 50 years, scientists have sought to map emotion-related experience, expression, physiology, and recognition in terms of the “basic six”—anger, disgust, fear, happiness, sadness, and surprise. Claims …
22
Rob Fergus43https://scholar.google.com/citations?user=GgQ9GEkAAAAJ&hl=en&num=2&oi=ao84381Research Scientist, DeepMind. Professor of Computer Science, New York Universityhttps://scholar.google.com/scholar?q=author%3A%22Rob+Fergus%22&hl=en&num=2Visualizing and understanding convolutional networksAbstract Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al.[18]. However there is no clear understanding of why they perform so well, or how they might be improved. In this …Intriguing properties of neural networksDeep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn uninterpretable solutions that could have …
23
Yann LeCun43https://scholar.google.com/citations?user=WLN3QrAAAAAJ&hl=en&num=2&oi=ao206562Chief AI Scientist at Facebook & Silver Professor at the Courant Institute, New York UniversityYoshua Bengio, Leon Bottou, Patrick Haffner, Bernhard Boser, Richard E. Howard, Pierre Sermanet, Geoffrey Hinton, Marc'Aurelio Ranzato, Michael Mathieu, Clement Farabet, Patrice Simard, koray kavukcuoglu, Sumit Chopra, Joan Bruna, Eduard Sackinger, Raia Hadsell, Arthur Szlam, Rob Fergus, Corinna Cortes, Camille Coupriehttps://scholar.google.com/scholar?q=author%3A%22Yann+LeCun%22&hl=en&num=2Efficient backpropThe convergence of back-propagation learning is analyzed so as to explain common phenomenon observed by practitioners. Many undesirable behaviors of backprop can be avoided with tricks that are rarely exposed in serious technical publications. This paper …Gradient-based learning applied to document recognitionMultilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex …
24
Marc Pollefeys29https://scholar.google.com/citations?user=YYH0BjEAAAAJ&hl=en&num=2&oi=ao38537Director of Science, Microsoft HoloLens; Professor of Computer Science, ETH ZurichLuc Van Gool, Jan-Michael Frahm, Torsten Sattler, Maarten Vergauwen, Friedrich Fraundorfer, Sudipta N. Sinha, Reinhard Koch, David Gallup, Johannes L. Schönberger, Brian Clipp, Gim Hee Lee, Ruigang Yang, Lionel Heng, Christian Häne, Zach Christopher, Martin R. Oswald, Petri Tanskanen, Philippos Mordohai, Kevin Köser, Lubor Ladickyhttps://scholar.google.com/scholar?q=author%3A%22Marc+Pollefeys%22&hl=en&num=2Self-calibration and metric reconstruction inspite of varying and unknown intrinsic camera parametersIn this paper the theoretical and practical feasibility of self-calibration in the presence of varying intrinsic camera parameters is under investigation. The paper's main contribution is to propose a self-calibration method which efficiently deals with all kinds of constraints on …Visual modeling with a hand-held cameraIn this paper a complete system to build visual models from camera images is presented. The system can deal with uncalibrated image sequences acquired with a hand-held camera. Based on tracked or matched features the relations between multiple views are computed …
25
David Forsyth29https://scholar.google.com/citations?user=5H0arvkAAAAJ&hl=en&num=2&oi=ao37260Professor of Computer Science, University of Illinois, Urbana Champaignhttps://scholar.google.com/scholar?q=author%3A%22David+Forsyth%22&hl=en&num=2Matching words and picturesWe present a new approach for modeling multi-modal data sets, focusing on the specific case of segmented images with associated text. Learning the joint distribution of image regions and words has many applications. We consider in detail predicting words …Computer vision: A modern approach.This extraordinary book gives a uniquely modern view of computer vision. Offering a general survey of the whole computer vision enterprise along with sufficient detail for readers to be able to build useful applications, this book is invaluable in providing a strategic overview of …
26
Aaron Hertzmann29https://scholar.google.com/citations?user=ZcWO2AEAAAAJ&hl=en&num=2&oi=ao21384AdobeDavid J Fleet, Aseem Agarwala, Brian Curless, Jack M. Wang, Steve Seitz, Peter O'Donovan, Sam Roweis (Memorial), Zoran Popovic, Evangelos Kalogerakis, Rob Fergus, William T. Freeman, Nuria Oliver, PhD, Stephen DiVerdi, Martin de Lasa, David Salesin, Lorenzo Torresani, Sylvain Paris, Holger Winnemoeller, Ken Perlin, karan singhhttps://scholar.google.com/scholar?q=author%3A%22Aaron+Hertzmann%22&hl=en&num=2Removing camera shake from a single photographCamera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency-domain constraints on images, or overly simplified parametric forms for the motion path …Image analogiesThis paper describes a new framework for processing images by example, called “image analogies.” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “filtered” version of the other, is presented as “training …
27
Saurabh Gupta29https://scholar.google.com/citations?user=1HO5UacAAAAJ&hl=en&num=2&oi=ao7653University of Illinois Urbana-ChampaignJitendra Malik, Pablo Arbelaez, Ross Girshick, Hao Fang, C. Lawrence Zitnick, Margaret Mitchell, Abhinav Gupta, bharath hariharan, Piotr Dollár, Sergey Levine, Xiaodong He (何晓冬), Li Deng, Judy Hoffman, Devendra Singh Chaplot, Forrest Iandola, Rupesh Kumar Srivastava, Jianfeng Gao, John C. Platt, Shubham Tulsiani, Rahul Sukthankarhttps://scholar.google.com/scholar?q=author%3A%22Saurabh+Gupta%22&hl=en&num=2Learning rich features from RGB-D images for object detection and segmentationIn this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the …From captions to visual concepts and backThis paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to train visual detectors for …
28
Sylvain Gelly29https://scholar.google.com/citations?user=m7LvuTkAAAAJ&hl=en&num=2&oi=ao7512Google Brain Zurichhttps://scholar.google.com/scholar?q=author%3A%22Sylvain+Gelly%22&hl=en&num=2Challenging common assumptions in the unsupervised learning of disentangled representationsThe key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress …An image is worth 16x16 words: Transformers for image recognition at scaleWhile the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain …
29
Sergio Guadarrama29https://scholar.google.com/citations?user=gYiCq88AAAAJ&hl=en&num=2&oi=ao26622Senior SWE at Google BrainTrevor Darrell, Jeff Donahue, Ross Girshick, Kate Saenko, Yangqing Jia, Sergey Karayev, Kevin Murphy, Evan Shelhamer, Anoop Korattikara, Alireza Fathi, Zbigniew Wojna, Subhashini Venugopalan, Jonathan Huang, Ian Fischer, vivek rathod, Menglong Zhu, Yang Song, Marcus Rohrbach, Lisa Anne M Hendricks, Raymond Mooneyhttps://scholar.google.com/scholar?q=author%3A%22Sergio+Guadarrama%22&hl=en&num=2Caffe: Convolutional architecture for fast feature embeddingCaffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training …Long-term recurrent convolutional networks for visual recognition and descriptionAbstract Models comprised of deep convolutional network layers have dominated recent image interpretation tasks; we investigate whether models which are also compositional, or" deep", temporally are effective on tasks involving visual sequences or label sequences. We …
30
David Lowe29https://scholar.google.com/citations?user=8vs5HGYAAAAJ&hl=en&num=2&oi=ao117532Professor Emeritus, Computer Science Dept., University of British ColumbiaJames Little, Matthew Brown, Marius Muja, Sancho McCann, David Meger, Per-Erik Forssén, Peter D. Lawrence, Nando de Freitas, Kevin Lai, Dinesh K. Pai, Michael C. Yip, S.E. Salcudean, Robert Rohling, Gustavo Carneiro, Radu B. Rusu, Ankur Gupta, Robert J. Woodhamhttps://scholar.google.com/scholar?q=author%3A%22David+Lowe%22&hl=en&num=2Radial basis functions, multi-variable functional interpolation and adaptive networksThe relationship between learning in adaptive layered networks and the fitting of data with high dimensional surfaces is discussed. This leads naturally to a picture of generalization in terms of interpolation between known data points and suggests a rational approach to the …Changes in atmospheric constituents and in radiative forcing. Chapter 2[en] This chapter updates information taken from Chapters 3 to 6 of the IPCC Working Group I Third Assessment Report. It concerns itself with trends in forcing agents and their precursors since 1750, and estimates their contribution to the radiative forcing (RF) of the …
31
Simon Baker29https://scholar.google.com/citations?user=UcbjgQ0AAAAJ&hl=en&num=2&oi=ao67001Distinguished Engineer, nVidia Corporationhttps://scholar.google.com/scholar?q=author%3A%22Simon+Baker%22&hl=en&num=2The CMU pose, illumination, and expression (PIE) databaseBetween October 2000 and December 2000, we collected a database of over 40,000 facial images of 68 people. Using the CMU (Carnegie Mellon University) 3D Room, we imaged each person across 13 different poses, under 43 different illumination conditions, and with …Lucas-kanade 20 years on: A unifying frameworkAbstract Since the Lucas-Kanade algorithm was proposed in 1981 image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow and tracking to layered motion, mosaic construction, and face coding. Numerous …
32
Johannes Kopf29https://scholar.google.com/citations?user=E42NyKUAAAAJ&hl=en&num=2&oi=ao7323FacebookMichael F Cohen, Dani Lischinski, Richard Szeliski, Oliver Deussen, Daniel Cohen-Or, Jia-Bin Huang, Matt Uyttendaele, David Chuhttps://scholar.google.com/scholar?q=author%3A%22Johannes+Kopf%22&hl=en&num=2Joint bilateral upsamplingImage analysis and enhancement tasks such as tone mapping, colorization, stereo depth, and photomontage, often require computing a solution (eg, for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and memory costs often require that a …Deep photo: Model-based photograph enhancement and viewingIn this paper, we introduce a novel system for browsing, enhancing, and manipulating casual outdoor photographs by combining them with already existing georeferenced digital terrain and urban models. A simple interactive registration process is used to align a …
33
Dmitriy Aronov29https://scholar.google.com/citations?user=5LdTKg4AAAAJ&hl=en&num=2&oi=ao3789Department of Neuroscience, Columbia UniversityRafael Yuste, Michale S Fee, David W. Tank, Jesse Goldberg, Yuji Ikegaya, Gloster Aaron, David Ferster, Robert Froemke, Aaron Andalman, Jonathan Victor, Bence Ölveczky, Lena Veit, Yehezkel Ben-Ari, Timothy M. Otchy, Daniel S. Reich, ferenc mechler, Sam Lewallen, Amina Kinkhabwala, Carlos Portera-Cailliau, Dani Dumitriuhttps://scholar.google.com/scholar?q=author%3A%22Dmitriy+Aronov%22&hl=en&num=2Synfire chains and cortical songs: temporal modules of cortical activityHow can neural activity propagate through cortical networks built with weak, stochastic synapses? We find precise repetitions of spontaneous patterns of synaptic inputs in neocortical neurons in vivo and in vitro. These patterns repeat after minutes, maintaining …Attractor dynamics of network UP states in the neocortexThe cerebral cortex receives input from lower brain regions, and its function is traditionally considered to be processing that input through successive stages to reach an appropriate output 1, 2. However, the cortical circuit contains many interconnections, including those …
34
Chris Bregler29https://scholar.google.com/citations?user=MVGcpRsAAAAJ&hl=en&num=2&oi=ao15205GoogleJitendra Malik, Graham Taylor, Yann LeCun, Lorenzo Torresani, Michele Covell, David Forsyth, Aaron Hertzmann, Malcolm Slaney, Rob Fergus, Alexander Waibel, Thomas Brox, Pedro Sanderhttps://scholar.google.com/scholar?q=author%3A%22Chris+Bregler%22&hl=en&num=2Finding naked peopleThis paper demonstrates a content-based retrieval strategy that can tell whether there are naked people present in an image. No manual intervention is required. The approach combines color and texture properties to obtain an effective mask for skin regions. The skin …Towards accurate multi-person pose estimation in the wildWe propose a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task. It is a simple, yet powerful, top-down approach consisting of two stages. In the first stage, we predict the location and scale …
35
Kavita Bala29https://scholar.google.com/citations?user=Rh16nsIAAAAJ&hl=en&num=2&oi=ao10208Cornell UniversityNoah Snavely, Sean Bell, Shuang Zhao, Philip Dutré, Sylvain Paris, Fujun Luan, Ioannis Gkioulekas, Paul Upchurch, Julie Dorsey, Miloš Hašan, James Ferwerda, Steve Marschner, Milind Kulkarni, Philippe BEKAERT, Keshav Pingali, Edward H Adelson, Fredo Durand, Todd Zickler, Seth Teller, Balázs Kovácshttps://scholar.google.com/scholar?q=author%3A%22Kavita+Bala%22&hl=en&num=2Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networksIt is well known that contextual and multi-scale representations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest. Contextual …Advanced global illuminationThis book provides a fundamental understanding of global illumination algorithms. It discusses a broad class of algorithms for realistic image synthesis and introduces a theoretical basis for the algorithms presented. Topics include: physics of light transport …
36
Alexander Sorkine-Hornung29https://scholar.google.com/citations?user=K-g2p4cAAAAJ&hl=en&num=2&oi=ao8758FacebookMarkus Gross, Oliver Wang, Federico Perazzi, Yael Pritch, Henning Zimmer, Manuel Lang, Olga Sorkine-Hornung, Leif Kobbelt, Changil Kim, Philipp Krähenbühl, Brian McWilliams, Jean-Charles Bazin, Robert W. Sumner, Luc Van Gool, Simone Schaub-Meyer, Kaan Yücer, Jordi Pont-Tuset, Daniel Sýkora, Simon Heinzle, Mario Botschhttps://scholar.google.com/scholar?q=author%3A%22Alexander+Sorkine-Hornung%22&hl=en&num=2A benchmark dataset and evaluation methodology for video object segmentationOver the years, datasets and benchmarks have proven their fundamental importance in computer vision research, enabling targeted progress and objective comparisons in many fields. At the same time, legacy datasets may impend the evolution of a field due to saturated …Scene reconstruction from high spatio-angular resolution light fields.This paper describes a method for scene reconstruction of complex, detailed environments from 3D light fields. Densely sampled light fields in the order of 109 light rays allow us to capture the real world in unparalleled detail, but efficiently processing this amount of data to …
37
Armand Joulin29https://scholar.google.com/citations?user=kRJkDakAAAAJ&hl=en&num=2&oi=ao20708Research Scientist, Facebook AI ResearchPiotr Bojanowski, Edouard Grave, Tomas Mikolov, Hervé Jégou, Mathilde Caron, Li Fei-Fei, Francis Bach, Jean Ponce, Matthijs Douze, Julien Mairal, Sainbayar Sukhbaatar, Allan Jabri, Ishan Misra, Sumit Chopra, Jason Weston, Laurens van der Maaten, Angela Fan, Kevin Tang, Priya Goyal, Arthur Szlamhttps://scholar.google.com/scholar?q=author%3A%22Armand+Joulin%22&hl=en&num=2Enriching word vectors with subword informationContinuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation …Bag of tricks for efficient text classificationThis paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train …
38
Ashutosh Saxena29https://scholar.google.com/citations?user=J6iSjTcAAAAJ&hl=en&num=2&oi=ao15805CEO, Caspar.AI; Former Faculty, Computer Science, Cornell University. Stanford UniversityAndrew Ng, Hema Swetha Koppula, Ashesh Jain, Yun Jiang, Jaeyong Sung, Silvio Savarese, Ian Lenz, Min Sun, Ozan Sener, Bart Selman, Thorsten Joachims, Chenxia Wu, Tsuhan Chen, Amir R. Zamir, Dipendra Misra, Honglak Lee, Jiemi Zhang, Congcong Li, Zhaoyin Jia, Lawson L.S. Wonghttps://scholar.google.com/scholar?q=author%3A%22Ashutosh+Saxena%22&hl=en&num=2Make3d: Learning 3d scene structure from a single still imageWe consider the problem of estimating detailed 3D structure from a single still image of an unstructured environment. Our goal is to create 3D models that are both quantitatively accurate as well as visually pleasing. For each small homogeneous patch in the image, we …Deep learning for detecting robotic graspsWe consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. In this work, we apply a deep learning approach to solve this problem, which avoids time-consuming hand-design of features. This presents two main challenges …
39
Gordon Wyeth29https://scholar.google.com/scholar?q=author%3A%22Gordon+Wyeth%22&hl=en&num=2SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nightsLearning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to …RatSLAM: a hippocampal model for simultaneous localization and mappingThe work presents a new approach to the problem of simultaneous localization and mapping-SLAM-inspired by computational models of the hippocampus of rodents. The rodent hippocampus has been extensively studied with respect to navigation tasks, and …
40
Piotr Dollár29https://scholar.google.com/citations?user=a8Y2OJMAAAAJ&hl=en&num=2&oi=ao84287Facebook AI ResearchRoss Girshick, Pietro Perona, Serge Belongie, Kaiming He, C. Lawrence Zitnick, Tsung-Yi Lin, Georgia Gkioxari, Zhuowen Tu, Deva Ramanan, Priya Goyal, Saining Xie, Vincent Rabaud, Michael Maire, James Hays, bharath hariharan, Bernt Schiele, Xavier P. Burgos-Artizzu, Dayu Lin, Pedro O. Pinheiro, Christian Wojekhttps://scholar.google.com/scholar?q=author%3A%22Piotr+Doll%C3%A1r%22&hl=en&num=2Focal loss for dense object detectionThe highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of …Mask r-cnnWe present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R …
41
Gurtej Kanwar29https://scholar.google.com/citations?user=zK77P6MAAAAJ&hl=en&num=2&oi=ao222Massachusetts Institute of TechnologyPhiala Shanahan, Michael S. Albergo, Kyle Cranmer, Danilo J. Rezende, Sébastien Racanière, Daniel Hackett, Denis Boyda, William Detmold, Saman Amarasinghe, Shinjiro Sueda, Desai Chen, Danny M Kaufman, Jonathan Ragan-Kelley, Shoaib Kamil, Etienne Vouga, Wojciech Matusik, David I.W. Levin, George Papamakarios, Fredrik Kjolstad, Neill C. Warringtonhttps://scholar.google.com/scholar?q=author%3A%22Gurtej+Kanwar%22&hl=en&num=2Normalizing flows on tori and spheresNormalizing flows are a powerful tool for building expressive distributions in high dimensions. So far, most of the literature has concentrated on learning flows on Euclidean spaces. Some problems however, such as those involving angles, are defined on spaces …Equivariant flow-based sampling for lattice gauge theoryWe define a class of machine-learned flow-based sampling algorithms for lattice gauge theories that are gauge invariant by construction. We demonstrate the application of this framework to U (1) gauge theory in two spacetime dimensions, and find that, at small bare …
42
Sebastian Scherer29https://scholar.google.com/citations?user=gxoPfIYAAAAJ&hl=en&num=2&oi=ao5990Associate Research Professor, Carnegie Mellon UniversityDaniel Maturana, Sanjiv Singh, Sanjiban Choudhury, Shichao Yang, Sankalp Arora, Rogerio Bonatti, Weikun Zhen, Wenshan Wang, Zheng Fang, Ashish Kapoor, Supreeth Achar, Michael Kaess, Ratnesh Madaan, Po-Wei Chou, Geetesh Dubey, Yaoyu Hu, Yu Song, Cherie Ho, Azarakhsh Keipour, Joern Rehderhttps://scholar.google.com/scholar?q=author%3A%22Sebastian+Scherer%22&hl=en&num=2Voxnet: A 3d convolutional neural network for real-time object recognitionRobust object recognition is a crucial skill for robots operating autonomously in real world environments. Range sensors such as LiDAR and RGBD cameras are increasingly found in modern robotic systems, providing a rich source of 3D information that can aid in this task …3d convolutional neural networks for landing zone detection from lidarWe present a system for the detection of small and potentially obscured obstacles in vegetated terrain. The key novelty of this system is the coupling of a volumetric occupancy map with a 3D Convolutional Neural Network (CNN), which to the best of our knowledge has …
43
Sven Dickinson29https://scholar.google.com/citations?user=6TGwETYAAAAJ&hl=en&num=2&oi=ao9429Professor of Computer Science, University of Torontohttps://scholar.google.com/scholar?q=author%3A%22Sven+Dickinson%22&hl=en&num=2Turbopixels: Fast superpixels using geometric flowsWe describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation through a …Shock graphs and shape matchingWe have been developing a theory for the generic representation of 2-D shape, where structural descriptions are derived from the shocks (singularities) of a curve evolution process, acting on bounding contours. We now apply the theory to the problem of shape …
44
Stefanos Zafeiriou29https://scholar.google.com/citations?user=QKOH5iYAAAAJ&hl=en&num=2&oi=ao16872Professor, Imperial College LondonMaja Pantic, Jiankang Deng, Georgios (Yorgos) Tzimiropoulos, Yannis Panagakis, I. Pitas, Mihalis A. Nicolaou, George Trigeorgis, Björn Schuller, Epameinondas Antonakos, Shiyang Cheng, Grigorios G. Chrysos, Anastasios Tefas, Christos Sagonas, Dimitrios Kollias, Jia Guo, Niannan Xue, Anastasios (Tassos) Roussos, Patrick Snape, Yuxiang Zhou, Stylianos Ploumpishttps://scholar.google.com/scholar?q=author%3A%22Stefanos+Zafeiriou%22&hl=en&num=2Arcface: Additive angular margin loss for deep face recognitionOne of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that can enhance the discriminative power. Centre loss penalises the distance between deep …300 faces in-the-wild challenge: The first facial landmark localization challengeAutomatic facial point detection plays arguably the most important role in face analysis. Several methods have been proposed which reported their results on databases of both constrained and unconstrained conditions. Most of these databases provide annotations …
45
Zoran Popović29https://scholar.google.com/scholar?q=author%3A%22Zoran+Popovi%C4%87%22&hl=en&num=2Predicting protein structures with a multiplayer online gamePeople exert large amounts of problem-solving effort playing computer games. Simple image-and text-recognition tasks have been successfully 'crowd-sourced'through games 1, 2, 3, but it is not clear if more complex scientific problems can be solved with human-directed …ROSETTA3: an object-oriented software suite for the simulation and design of macromoleculesWe have recently completed a full rearchitecturing of the Rosetta molecular modeling program, generalizing and expanding its existing functionality. The new architecture enables the rapid prototyping of novel protocols by providing easy-to-use interfaces to powerful tools …
46
Zoubin Ghahramani29https://scholar.google.com/citations?user=0uTu7fYAAAAJ&hl=en&num=2&oi=ao68770Professor, University of Cambridge, and Distinguished Researcher, GoogleMichael I. Jordan, Daniel Wolpert, Geoffrey Hinton, Xiaojin Zhu, Yarin Gal, Katherine Heller, Matthew J. Beal, José Miguel Hernández-Lobato, Carl Edward Rasmussen, Tommi Jaakkola, David A. Knowles, Alexander G. D. G. Matthews, Sam Roweis (Memorial), Richard E Turner, Lawrence K Saul, Wei Chu(褚崴), Hugh Durrant-Whyte, Ryan P. Adams, Neil Houlsby, James Robert Lloydhttps://scholar.google.com/scholar?q=author%3A%22Zoubin+Ghahramani%22&hl=en&num=2Semi-supervised learning using gaussian fields and harmonic functionsAn approach to semi-supervised learning is proposed that is based on a Gaussian random field model. Labeled and unlabeled data are represented as vertices in a weighted graph, with edge weights encoding the similarity between instances. The learning problem is then …An introduction to variational methods for graphical modelsThis paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields). We present a number of examples of graphical models, including the QMR-DT database, the sigmoid …
47
Terry Sejnowski29https://scholar.google.com/scholar?q=author%3A%22Terry+Sejnowski%22&hl=en&num=2The effect of neural adaptation on population coding accuracyMost neurons in the primary visual cortex initially respond vigorously when a preferred stimulus is presented, but adapt as stimulation continues. The functional consequences of adaptation are unclear. Typically a reduction of firing rate would reduce single neuron …THE LANGUAGE OF THE BRAIN: The brain makes sense if our experiences by focusing closely on the timing of the impulses that flow through billions of …We can instantly search through a vast wealth of experiences and emotions. We can immediately recognize the face of a parent, spouse, friend or pet, whether in daylight, darkness, from above or sideways—a task that the computer vision system built into the most …
48
Piotr Dollar29https://scholar.google.com/citations?user=a8Y2OJMAAAAJ&hl=en&num=2&oi=ao84287Facebook AI ResearchRoss Girshick, Pietro Perona, Serge Belongie, Kaiming He, C. Lawrence Zitnick, Tsung-Yi Lin, Georgia Gkioxari, Zhuowen Tu, Deva Ramanan, Priya Goyal, Saining Xie, Vincent Rabaud, Michael Maire, James Hays, bharath hariharan, Bernt Schiele, Xavier P. Burgos-Artizzu, Dayu Lin, Pedro O. Pinheiro, Christian Wojekhttps://scholar.google.com/scholar?q=author%3A%22Piotr+Dollar%22&hl=en&num=2Focal loss for dense object detectionThe highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of …Mask r-cnnWe present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R …
49
Josef Sivic29https://scholar.google.com/citations?user=NCtKHnQAAAAJ&hl=en&num=2&oi=ao36142Czech Technical University, CIIRC, ELLIS Unit PragueAndrew Zisserman, Ivan Laptev, Bryan Russell, Tomas Pajdla, Alexei A. Efros, Akihiko TORII, William T. Freeman, Michael Isard, Relja Arandjelović / Реља Аранђелов..., Ondrej Chum, Mathieu Aubry, Jean Ponce, Leon Bottou, Abhinav Gupta, Maxime Oquab, Vincent Delaitre, Oliver Whyte, Antonio Torralbahttps://scholar.google.com/scholar?q=author%3A%22Josef+Sivic%22&hl=en&num=2Video Google: A text retrieval approach to object matching in videosWe describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite …Object retrieval with large vocabularies and fast spatial matchingIn this paper, we present a large-scale object retrieval system. The user supplies a query object by selecting a region of a query image, and the system returns a ranked list of images that contain the same object, retrieved from a large corpus. We demonstrate the scalability …
50
Marc Peter Deisenroth29https://scholar.google.com/scholar?q=author%3A%22Marc+Peter+Deisenroth%22&hl=en&num=2Deep reinforcement learning: A brief surveyDeep reinforcement learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higher-level understanding of the visual world. Currently, deep learning is enabling reinforcement …A survey on policy search for roboticsPolicy search is a subfield in reinforcement learning which focuses on finding good parameters for a given policy parametrization. It is well suited for robotics as it can cope with high-dimensional state and action spaces, one of the main challenges in robot learning. We …
51
Marc Alexa29https://scholar.google.com/citations?user=KNwXLLsAAAAJ&hl=en&num=2&oi=ao16463Professor of Computer Science, TU BerlinAndy Nealen, Daniel Cohen-Or, Mathias Eitz, Tamy Boubekeur, Kristian Hildebrand, Olga Sorkine-Hornung, Wolfgang Mueller, Wojciech Matusik, Hans-Peter Seidel, Markus Gross, Bernd Bickel, Claudio T. Silva, Shachar Fleishman, Philipp Herholz, Alexander G. Belyaev, Takeo Igarashi, Uwe Hahne, yaron lipman, Christian Rössl, James Hayshttps://scholar.google.com/scholar?q=author%3A%22Marc+Alexa%22&hl=en&num=2Laplacian surface editingSurface editing operations commonly require geometric details of the surface to be preserved as much as possible. We argue that geometric detail is an intrinsic property of a surface and that, consequently, surface editing is best performed by operating over an …Multi-level partition of unity implicitsWe present a new shape representation, the multi-level partition of unity implicit surface, that allows us to construct surface models from very large sets of points. There are three key ingredients to our approach: 1) piecewise quadratic functions that capture the local shape of …
52
Rahul Sukthankar29https://scholar.google.com/citations?user=bmZbi_UNs-oC&hl=en&num=2&oi=ao30013Google ResearchYan Ke, martial hebert, George Toderici, Mubarak Shah, Shumeet Baluja, Cordelia Schmid, Rong Jin, Marius Leordeanu, Sudheendra Vijayanarasimhan, Gita Sukthankar, Thomas Leung, Chen Sun, Susanna Ricco, Mahadev Satyanarayanan, James M. Rehg, David A. Ross, Li Fei-Fei, Sanketh Shetty, Michele Covell, Tat-Jen Chamhttps://scholar.google.com/scholar?q=author%3A%22Rahul+Sukthankar%22&hl=en&num=2Large-scale video classification with convolutional neural networksAbstract Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Encouraged by these results, we provide an extensive empirical evaluation of CNNs on large-scale video classification using a new …PCA-SIFT: A more distinctive representation for local image descriptorsStable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) recently evaluated a variety of approaches and identified the SIFT [DG Lowe, 1999] …
53
Matthias Nießner29https://scholar.google.com/citations?user=eUtEs6YAAAAJ&hl=en&num=2&oi=ao11807Professor of Computer Science, Technical University of Munichhttps://scholar.google.com/scholar?q=author%3A%22Matthias+Nie%C3%9Fner%22&hl=en&num=2Faceforensics++: Learning to detect manipulated facial imagesThe rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false …Volumetric and multi-view cnns for object classification on 3d dataAbstract 3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-the-art methods rely on CNNs to address this problem. Recently, we witness two types of CNNs …
54
Efstratios Gavves29https://scholar.google.com/citations?user=QqfCvsgAAAAJ&hl=en&num=2&oi=ao5664Associate Professor at University of AmsterdamCees G. M. Snoek, Arnold Smeulders, Basura Fernando, Tinne Tuytelaars, Ran Tao, Zhenyang Li, Max Welling, Hakan Bilen, Thomas Mensink, Amir Ghodrati, Andrea Vedaldi, Mihir Jain, Stephen Gould, Xirong Li (李锡荣), Noureldien Hussein, José Oramas M., Changyong Oh, Kirill Gavrilyuk, Shuai Liao, Yunlu Chenhttps://scholar.google.com/scholar?q=author%3A%22Efstratios+Gavves%22&hl=en&num=2Siamese instance search for trackingIn this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated …The sixth visual object tracking vot2018 challenge resultsAbstract The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision …
55
Andrew Fitzgibbon29https://scholar.google.com/citations?user=73t3lIcAAAAJ&hl=en&num=2&oi=ao40449MicrosoftJamie Shotton, Shahram Izadi, Pushmeet Kohli, Robert B Fisher, Toby Sharp, Andrew Zisserman, David Kim, David Molyneaux, Otmar Hilliges, Steve Hodges, Andrew Blake, Jonathan Taylor, Antonio Criminisi, Richard Newcombe, Philip Torr, Andrew Glennerster, Andrew Davison, Tom Cashman, Cem Keskin, Zach Christopherhttps://scholar.google.com/scholar?q=author%3A%22Andrew+Fitzgibbon%22&hl=en&num=2Kinectfusion: Real-time dense surface mapping and trackingWe present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single …Real-time human pose recognition in parts from single depth imagesWe propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose …
56
Greg Mori29https://scholar.google.com/citations?user=Bl9FSL0AAAAJ&hl=en&num=2&oi=ao15178Research Director, Borealis AI; Professor, School of Computing Science, Simon Fraser Universityhttps://scholar.google.com/scholar?q=author%3A%22Greg+Mori%22&hl=en&num=2Recognizing action at a distanceOur goal is to recognize human action at a distance, at resolutions where a whole person may be, say, 30 pixels tall. We introduce a novel motion descriptor based on optical flow measurements in a spatiotemporal volume for each stabilized human figure, and an …Recognizing objects in adversarial clutter: Breaking a visual CAPTCHAIn this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZ-Gimpy, examples of visual CAPTCHAs. A CAPTCHA (" Completely Automated Public Turing test to Tell Computers and Humans Apart") is a …
57
Josh Tenenbaum29https://scholar.google.com/scholar?q=author%3A%22Josh+Tenenbaum%22&hl=en&num=2Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivationLearning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. One of the key difficulties is insufficient exploration, resulting in an agent being unable to learn robust policies. Intrinsically motivated agents can …End-to-end differentiable physics for learning and controlWe present a differentiable physics engine that can be integrated as a module in deep neural networks for end-to-end learning. As a result, structured physics knowledge can be embedded into larger systems, allowing them, for example, to match observations by …
58
Naftali Tishby29https://scholar.google.com/scholar?q=author%3A%22Naftali+Tishby%22&hl=en&num=2The information bottleneck methodWe define the relevant information in a signal $ x\in X $ as being the information that this signal provides about another signal $ y\in\Y $. Examples include the information that face images provide about the names of the people portrayed, or the information that speech …Machine learning and the physical sciencesAbstract Machine learning (ML) encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. This article reviews in a selective way the recent research on the …
59
Raquel Urtasun29https://scholar.google.com/citations?user=jyxO2akAAAAJ&hl=en&num=2&oi=ao41295Professor, University of Toronto. Chief Scientist, Uber ATGSanja Fidler, Shenlong Wang, Andreas Geiger, Richard Zemel, Alexander Schwing, Bin Yang, Renjie Liao, Mengye Ren, Wei-Chiu Ma, Trevor Darrell, Pascal Fua, Wenyuan Zeng, Philip Lenz, Yukun Zhu, Antonio Torralba, Alan Yuille, Kaustav Kundu, Tamir Hazan, David J Fleet, Mathieu Salzmannhttps://scholar.google.com/scholar?q=author%3A%22Raquel+Urtasun%22&hl=en&num=2Are we ready for autonomous driving? the kitti vision benchmark suiteToday, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop …Vision meets robotics: The kitti datasetWe present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10–100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo …
60
Philip Torr29https://scholar.google.com/citations?user=kPxa2w0AAAAJ&hl=en&num=2&oi=ao54255Professor, University of OxfordPushmeet Kohli, Andrew Zisserman, Ming-Ming Cheng, 程明明, Vibhav Vineet, Stuart Golodetz, Roberto Cipolla, M. Pawan Kumar, Puneet K. Dokania, Shuai (Kyle) Zheng, 郑帅, Luca Bertinetto, Lubor Ladicky, David Murray, Anurag Arnab, Ondrej Miksik, Andrew Blake, Arasanathan Thayananthan, Carsten Rother, Thalaiyasingam Ajanthan, Li Zhang, Chris Russellhttps://scholar.google.com/scholar?q=author%3A%22Philip+Torr%22&hl=en&num=2Global contrast based salient region detectionAutomatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object …Learning to compare: Relation network for few-shot learningWe present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During …
61
Iain Matthews29https://scholar.google.com/citations?user=0ZXfitAAAAAJ&hl=en&num=2&oi=ao27032Epic Games / University of East Anglia / Carnegie Mellon UniversitySimon Baker, Patrick Lucey, Jeffrey Cohn, Takeo Kanade, Yaser Sheikh, Ralph Gross, Barry-John Theobald, Alina Bialkowski, Yisong Yue, Sridha Sridharan, Tomas Simon, Stephen Cox, Jing Xiao, Sarah Taylor, Juergen Luettin, Jason Saragih, Richard Harvey, Hanbyul Joo, Fernando De la Torre, Gerasimos Potamianoshttps://scholar.google.com/scholar?q=author%3A%22Iain+Matthews%22&hl=en&num=2Lucas-kanade 20 years on: A unifying frameworkAbstract Since the Lucas-Kanade algorithm was proposed in 1981 image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow and tracking to layered motion, mosaic construction, and face coding. Numerous …The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expressionIn 2000, the Cohn-Kanade (CK) database was released for the purpose of promoting research into automatically detecting individual facial expressions. Since then, the CK database has become one of the most widely used test-beds for algorithm development and …
62
Srihari Nelakuditi29https://scholar.google.com/citations?user=wEaHHWIAAAAJ&hl=en&num=2&oi=ao4277University of South Carolinahttps://scholar.google.com/scholar?q=author%3A%22Srihari+Nelakuditi%22&hl=en&num=2CSMA/CN: Carrier sense multiple access with collision notificationA wireless transmitter learns of a packet loss and infers collision only after completing the entire transmission. If the transmitter could detect the collision early [such as with carrier sense multiple access with collision detection (CSMA/CD) in wired networks], it could …AccelPrint: Imperfections of Accelerometers Make Smartphones Trackable.As mobile begins to overtake the fixed Internet access, ad networks have aggressively sought methods to track users on their mobile devices. While existing countermeasures and regulation focus on thwarting cookies and various device IDs, this paper submits a …
63
Cristian Sminchisescu29https://scholar.google.com/citations?user=LHTI1W8AAAAJ&hl=en&num=2&oi=ao12076Professor, Lund UniversityJoão Carreira, Dimitris N. Metaxas, Atul Kanaujia, Catalin Ionescu, Fuxin Li, Mihai Zanfir, Sven Dickinson, Andrei Zanfir, Bill Triggs, Liefeng Bo, Marius Leordeanu, Dragos Papava, Aleksis Pirinen, Rahul Sukthankar, Stefan Mathe, Allan D. Jepson, Adrian Ion, Guy Lebanon, Dan Banica, Max Wellinghttps://scholar.google.com/scholar?q=author%3A%22Cristian+Sminchisescu%22&hl=en&num=2Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environmentsWe introduce a new dataset, Human3. 6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next …CPMC: Automatic object segmentation using constrained parametric min-cutsWe present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and …
64
Luc Van Gool29https://scholar.google.com/citations?user=TwMib_QAAAAJ&hl=en&num=2&oi=ao150215professor computer vision ETH Zurich & KU Leuven, Head Toyota Lab TRACE @ KUL & ETHTinne Tuytelaars, Radu Timofte, Marc Pollefeys, Andrew Zisserman, Bastian Leibe, Dengxin Dai, Herbert Bay, Reinhard Koch, Helmut Grabner, Konrad Schindler, Vittorio Ferrari, Pascal Mueller, Chris Williams, Johan Wagemans, John Winn, Jordi Pont-Tuset, Christoph Strecha, Hayko Riemenschneider, Angela Yao, Limin Wanghttps://scholar.google.com/scholar?q=author%3A%22Luc+Van+Gool%22&hl=en&num=2Speeded-up robust features (SURF)This article presents a novel scale-and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be …Surf: Speeded up robust featuresIn this paper, we present a novel scale-and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and …
65
Winrich Freiwald29https://scholar.google.com/scholar?q=author%3A%22Winrich+Freiwald%22&hl=en&num=2A cortical region consisting entirely of face-selective cellsFace perception is a skill crucial to primates. In both humans and macaque monkeys, functional magnetic resonance imaging (fMRI) reveals a system of cortical regions that show increased blood flow when the subject views images of faces, compared with images of …Faces and objects in macaque cerebral cortexHow are different object categories organized by the visual system? Current evidence indicates that monkeys and humans process object categories in fundamentally different ways. Functional magnetic resonance imaging (fMRI) studies suggest that humans have a …
66
Chris Pal29https://scholar.google.com/citations?user=1ScWJOoAAAAJ&hl=en&num=2&oi=ao58497Professor, Polytechnique Montréal & Mila, Element AI, Canada CIFAR AI ChairEibe Frank, Ian H. Witten, Yoshua Bengio, Aaron Courville, Hugo Larochelle, Richard Szeliski, Henry Kautzhttps://scholar.google.com/scholar?q=author%3A%22Chris+Pal%22&hl=en&num=2Brain tumor segmentation with deep neural networksIn this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear …Learning conditional random fields for stereoState-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for example by modulating local smoothness costs with intensity gradients. In this paper we seek to …
67
Pierre Vandergheynst29https://scholar.google.com/citations?user=1p9NOFEAAAAJ&hl=en&num=2&oi=ao29731Professor of Electrical Engineering, Ecole Polytechnique Fédérale de Lausanne (EPFL)Pascal Frossard, Rémi Gribonval, Xavier Bresson, Yves Wiaux, Jean-Philippe Thiran, Laurent Jacques, Gilles Puy, Alexandre Alahi, David I Shuman, Michael Bronstein, Karin Schnass, Òscar Divorra Escoda, Benjamin Ricaud, Gianluca Monaci, Rosa Maria Figueras i Ventura, Mohammad Golbabaee, Nathanael Perraudin, Hossein Mamaghanian, Alexandre Schmid, Michaël Defferrardhttps://scholar.google.com/scholar?q=author%3A%22Pierre+Vandergheynst%22&hl=en&num=2Convolutional neural networks on graphs with fast localized spectral filteringIn this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' …The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domainsIn applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs. The emerging field of signal processing on graphs merges algebraic and spectral graph theoretic concepts with …
68
Erik Rodner29https://scholar.google.com/citations?user=2ItLnFgAAAAJ&hl=en&num=2&oi=ao3164University of Applied Sciences (HTW Berlin)Joachim Denzler, Alexander Freytag, Marcel Simon, Paul Bodesheim, Trevor Darrell, Kate Saenko, Michael Kemmler, Jeff Donahue, Judy Hoffman, Björn Fröhlich, Christoph Käding, Sven Sickert, Björn Barz, Yanira Guanche, Clemens-Alexander Brust, Markus Reichstein, Sergio Guadarrama, Miguel D. Mahecha, Andreas K. Maier, Marc Aubrevillehttps://scholar.google.com/scholar?q=author%3A%22Erik+Rodner%22&hl=en&num=2Neural activation constellations: Unsupervised part model discovery with convolutional networksPart models of object categories are essential for challenging recognition tasks, where differences in categories are subtle and only reflected in appearances of small parts of the object. We present an approach that is able to learn part models in a completely …Efficient learning of domain-invariant image representationsWe present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the target (test) domain to the source (training) …
69
Anthony Dick29https://scholar.google.com/citations?user=Y6wo5UwAAAAJ&hl=en&num=2&oi=ao6591Computer Science, University of Adelaidehttps://scholar.google.com/scholar?q=author%3A%22Anthony+Dick%22&hl=en&num=2The adolescent brain cognitive development (ABCD) study: imaging acquisition across 21 sitesThe ABCD study is recruiting and following the brain development and health of over 10,000 9–10 year olds through adolescence. The imaging component of the study was developed by the ABCD Data Analysis and Informatics Center (DAIC) and the ABCD Imaging …A survey of appearance models in visual object trackingVisual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties in handling complex …
70
Richard Russell29https://scholar.google.com/scholar?q=author%3A%22Richard+Russell%22&hl=en&num=2Host–microbe interactions have shaped the genetic architecture of inflammatory bowel diseaseCrohn's disease and ulcerative colitis, the two common forms of inflammatory bowel disease (IBD), affect over 2.5 million people of European ancestry, with rising prevalence in other populations 1. Genome-wide association studies and subsequent meta-analyses of these …Genome-wide meta-analysis increases to 71 the number of confirmed Crohn's disease susceptibility lociWe undertook a meta-analysis of six Crohn's disease genome-wide association studies (GWAS) comprising 6,333 affected individuals (cases) and 15,056 controls and followed up the top association signals in 15,694 cases, 14,026 controls and 414 parent-offspring trios …
71
Xin Tong29https://scholar.google.com/citations?user=P91a-UQAAAAJ&hl=en&num=2&oi=ao8425Principal Researcher Manager, Microsoft Research AsiaBaining Guo, Heung-Yeung Shum, Stephen Lin, Yue DONG, Jiaping Wang, Yang Liu, Jinxiang Chai, Pieter Peers, Peng-Shuai Wang, Ligang Liu, Xun Cao, Fabio Pellacini, Jiaolong Yang, Sing Bing Kang, Chunyu Sun, Zhouchen Lin, Lifeng Wang, Li-Yi Wei 魏立一, Jingdan Zhang, Xiao Lihttps://scholar.google.com/scholar?q=author%3A%22Xin+Tong%22&hl=en&num=2O-cnn: Octree-based convolutional neural networks for 3d shape analysisWe present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method takes the average normal vectors of a 3D model sampled in the finest leaf octants as input and performs 3D …Plenoptic samplingThis paper studies the problem of plenoptic sampling in image-based rendering (IBR). From a spectral analysis of light field signals and using the sampling theorem, we mathematically derive the analytical functions to determine the minimum sampling rate for light field …
72
Ken Goldberg29https://scholar.google.com/citations?user=8fztli4AAAAJ&hl=en&num=2&oi=ao24529Professor, UC Berkeley and UCSFPieter Abbeel, Dezhen Song, Frank van der Stappen, Jur van den Berg, John Canny, Michael Franklin, Jean Pouliot, Dmitry Berenson, Matthew T. Mason, Mark Faridani, Kris Hauser, Noah J. Cowan, Roland Siegwart, Kyle Reed, James F. O'Brien, Barak A. Pearlmutter, Michael Branicky, Michael Peshkin, Eric Paulos, David Kriegmanhttps://scholar.google.com/scholar?q=author%3A%22Ken+Goldberg%22&hl=en&num=2Eigentaste: A constant time collaborative filtering algorithmEigentaste is a collaborative filtering algorithm that uses universal queries to elicit real-valued user ratings on a common set of items and applies principal component analysis (PCA) to the resulting dense subset of the ratings matrix. PCA facilitates dimensionality …Combating COVID-19—The role of robotics in managing public health and infectious diseasesThe outbreak of COVID-19 has now become a pandemic. The new coronavirus has affected nearly all continents; at the time of writing, South Korea, Iran, Italy, and other European countries have experienced sharp increases in diagnosed cases. Globalization and …
73
Oriol Vinyals29https://scholar.google.com/citations?user=NkzyCvUAAAAJ&hl=en&num=2&oi=ao117438Research Scientist at Google DeepMindhttps://scholar.google.com/scholar?q=author%3A%22Oriol+Vinyals%22&hl=en&num=2Sequence to sequence learning with neural networksAbstract Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this …Tensorflow: Large-scale machine learning on heterogeneous distributed systemsTensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous systems …
74
Honglak Lee29https://scholar.google.com/citations?user=fmSHtE8AAAAJ&hl=en&num=2&oi=ao38348LG AI Research / U. MichiganAndrew Ng, Kihyuk Sohn, Scott Reed, Junhyuk Oh, Satinder Singh, Jimei Yang, Ruben Villegas, Lajanugen Logeswaran, Yijie Guo, Bernt Schiele, Seunghoon Hong, Yuting Zhang, Zeynep Akata, Kibok Lee, Xinchen Yan, Alexis Battle, Jinwoo Shin, Richard L. Lewis, Kimin Lee, Roger Grossehttps://scholar.google.com/scholar?q=author%3A%22Honglak+Lee%22&hl=en&num=2Efficient sparse coding algorithmsSparse coding provides a class of algorithms for finding succinct representations of stimuli; given only unlabeled input data, it discovers basis functions that capture higher-level features in the data. However, finding sparse codes remains a very difficult computational …Convolutional deep belief networks for scalable unsupervised learning of hierarchical representationsThere has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images remains a difficult problem. To address this problem, we present the convolutional deep …
75
Bernard Ghanem29https://scholar.google.com/citations?user=rVsGTeEAAAAJ&hl=en&num=2&oi=ao11449Associate Professor, King Abdullah University of Science and TechnologyNarendra Ahuja, Fabian Caba Heilbron, Ali Thabet, Matthias Müller, Adel Bibi, Tianzhu Zhang, Victor Escorcia, Juan Carlos Niebles, Silvio Giancola, Yancheng Bai, si liu, Yongqiang Zhang, Humam Alwassel, Baoyuan Wu, Mengmeng Xu (Frost), Guohao Li, Changsheng Xu, Jean Lahoud, Shyamal Buch, Vincent Casserhttps://scholar.google.com/scholar?q=author%3A%22Bernard+Ghanem%22&hl=en&num=2Activitynet: A large-scale video benchmark for human activity understandingIn spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which …Robust visual tracking via structured multi-task sparse learningIn this paper, we formulate object tracking in a particle filter framework as a structured multi-task sparse learning problem, which we denote as Structured Multi-Task Tracking (S-MTT). Since we model particles as linear combinations of dictionary templates that are updated …
76
Leon Glass29https://scholar.google.com/citations?user=8LN2i8MAAAAJ&hl=en&num=2&oi=ao39310Professor of Physiology, McGill UniversityAlvin Shrier, Michael C. Mackey, Roderick Edwards, Rafael Pérez Pascual, Claudia Lerma, Theodore J. Perkins, Katsumi Tateno, Kevin Hall, Thomas Quail, James J Collinshttps://scholar.google.com/scholar?q=author%3A%22Leon+Glass%22&hl=en&num=2PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signalsThe newly inaugurated Research Resource for Complex Physiologic Signals, which was created under the auspices of the National Center for Research Resources of the National Institutes of Health, is intended to stimulate current research and new investigations in the …Oscillation and chaos in physiological control systemsFirst-order nonlinear differential-delay equations describing physiological control systems are studied. The equations display a broad diversity of dynamical behavior including limit cycle oscillations, with a variety of wave forms, and apparently aperiodic or" chaotic" …
77
Yoshua Bengio29https://scholar.google.com/citations?user=kukA0LcAAAAJ&hl=en&num=2&oi=ao424390Professor of computer science, University of Montreal, Mila, IVADO, CIFARAaron Courville, Kyunghyun Cho, Ian Goodfellow, Pascal Vincent, Yann LeCun, Hugo Larochelle, Caglar Gulcehre, Dzmitry Bahdanau, David Warde-Farley, Razvan Pascanu, Xavier Glorot, Leon Bottou, Mehdi Mirza, Sherjil Ozair, James Bergstra, Anirudh Goyal, Olivier Delalleau, Patrick Haffner, Pascal Lamblin, Chris Palhttps://scholar.google.com/scholar?q=author%3A%22Yoshua+Bengio%22&hl=en&num=2Understanding the difficulty of training deep feedforward neural networksWhereas before 2006 it appears that deep multi-layer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with experimental results showing the superiority of deeper vs less deep architectures. All these …Neural machine translation by jointly learning to align and translateNeural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance …
78
Stephen Grossberg29https://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en&num=2&oi=ao80320Wang Professor of Cognitive and Neural Systems, Boston UniversityGail Carpenter, Ennio Mingolla, Daniel Bullock, John Reynolds, Gary Bradski, Frank Guenther, Eric Granger, Lonce Wyse, James R. Williamson, Praveen K. Pilly, Joshua W. Brown, Arash Yazdanbakhsh, Gregory Francis, Aaron R. Seitz, Dejan Todorovic, Douglas N Greve, Birgitta Dresp-Langley, Rajeev Raizada, Mark A. Rubin, Ian Boardman, PhDhttps://scholar.google.com/scholar?q=author%3A%22Stephen+Grossberg%22&hl=en&num=2A massively parallel architecture for a self-organizing neural pattern recognition machineA neural network architecture for the learning of recognition categories is derived. Real-time network dynamics are completely characterized through mathematical analysis and computer simulations. The architecture self-organizes and self-stabilizes its recognition …Absolute stability of global pattern formation and parallel memory storage by competitive neural networksSystems that are competitive and possess symmetric interactions admit a global Lyapunov function. However, a global Lyapunov function whose equilibrium set can be effectively analyzed has not yet been discovered. It remains an open question whether the Lyapunov …
79
Ming-Hsuan Yang29https://scholar.google.com/citations?user=p9-ohHsAAAAJ&hl=en&num=2&oi=ao77798Professor, University of California at Merced; Research Scientist, GoogleNarendra Ahuja, Jongwoo Lim, Jia-Bin Huang, Jinshan Pan, Yi-Hsuan Tsai, David Kriegman, Wei-Sheng Lai, Chao Ma, Lei Zhang, Jan Kautz, Jimei Yang, Sifei Liu, Deqing Sun, Kaihua Zhang, Hsin-Ying Lee, Zhe Hu, Yi Wu, Hung-Yu Tseng, Wei-Chih Hung, Xiaokang Yanghttps://scholar.google.com/scholar?q=author%3A%22Ming-Hsuan+Yang%22&hl=en&num=2Detecting faces in images: A surveyImages containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that …Online object tracking: A benchmarkObject tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the …
80
Christian Theobalt29https://scholar.google.com/citations?user=eIWg8NMAAAAJ&hl=en&num=2&oi=ao20636Professor, Max Planck Institute for Informatics, Saarland Informatics Campus, Saarland UniversityHans-Peter Seidel, Marcus Magnor, Edilson de Aguiar, Matthias Nießner, Carsten Stoll, Kim, Kwang In, Marc Stamminger, James Tompkin, Srinath Sridhar, Christian Richardt, Kiran Varanasi, Naveed Ahmed, Chenglei Wu, Levi Valgaerts, Antti Oulasvirta, Shahram Izadi, Yebin Liu, Jan Kautz, Nils Hasler, Gaurav Bharajhttps://scholar.google.com/scholar?q=author%3A%22Christian+Theobalt%22&hl=en&num=2Face2face: Real-time face capture and reenactment of rgb videosWe present a novel approach for real-time facial reenactment of a monocular target video sequence (eg, Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the …Free-viewpoint video of human actorsIn free-viewpoint video, the viewer can interactively choose his viewpoint in 3-D space to observe the action of a dynamic real-world scene from arbitrary perspectives. The human body and its motion plays a central role in most visual media and its structure can be …
81
Tomaso Poggio29https://scholar.google.com/citations?user=WgAGy7wAAAAJ&hl=en&num=2&oi=ao124250McDermott Professor in Brain Sciences, MITFederico Girosi, Maximilian Riesenhuber, Lorenzo Rosasco, Christof Koch, Sayan Mukherjee, Ryan M. Rifkin, Massimiliano Pontil, Thomas Vetter, Heinrich H. Bülthoff, Shimon Edelman, Roberto Brunelli, Earl K. Miller, Gabriel Kreiman, Theodoros Evgeniou, Manfred Fahle, Michael Jones, Huei-han Jhuang, alessandro verri, Lior Wolf, David Beymerhttps://scholar.google.com/scholar?q=author%3A%22Tomaso+Poggio%22&hl=en&num=2Networks for approximation and learningThe problem of the approximation of nonlinear mapping,(especially continuous mappings) is considered. Regularization theory and a theoretical framework for approximation (based on regularization techniques) that leads to a class of three-layer networks called regularization …Face recognition: Features versus templatesTwo new algorithms for computer recognition of human faces, one based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second based on almost-gray-level template matching, are …
82
Jan Peters29https://scholar.google.com/citations?user=gXj_GRwAAAAJ&hl=en&num=2&oi=ao39706Research Institute of Molecular Pathology (IMP)https://scholar.google.com/scholar?q=author%3A%22Jan+Peters%22&hl=en&num=2Reinforcement learning in robotics: A surveyReinforcement learning offers to robotics a framework and set of tools for the design of sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic problems provide both inspiration, impact, and validation for developments in reinforcement …How proteolysis drives the cell cycleOscillations in the activity of cyclin-dependent kinases (CDKs) promote progression through the eukaryotic cell cycle. This review examines how proteolysis regulates CDK activity—by degrading CDK activators or inhibitors—and also how proteolysis may directly trigger the …
83
Sugato Basu29https://scholar.google.com/citations?user=0kV69XQAAAAJ&hl=en&num=2&oi=ao8549Principal Scientist at GoogleRaymond Mooney, Arindam Banerjee, Mikhail Bilenko, Ian Davidson, Kiri Wagstaff, Nur Touba, Joydeep Ghosh, Christos Faloutsos, Brian Gallagher, Tina Eliassi-Rad, Hanghang Tong, Danai Koutra, Leman Akoglu, Biswanath Panda, Brian Kulis, Inderjit S. Dhillon, Srujana Merugu, Krupakar Pasupuleti, Pradyumna Narayana, D. Sculleyhttps://scholar.google.com/scholar?q=author%3A%22Sugato+Basu%22&hl=en&num=2Semi-supervised clustering by seedingSemi-supervised clustering uses a small amount of labeled data to aid and bias the clustering of unlabeled data. This paper explores the use of labeled data to generate initial seed clusters, as well as the use of constraints generated from labeled data to guide the …Integrating constraints and metric learning in semi-supervised clusteringSemi-supervised clustering employs a small amount of labeled data to aid unsupervised learning. Previous work in the area has utilized supervised data in one of two approaches: 1) constraint-based methods that guide the clustering algorithm towards a better grouping of …
84
Sarit Kraus29https://scholar.google.com/citations?user=PfgeYGwAAAAJ&hl=en&num=2&oi=ao25672Professor Of Computer Science, Bar-Ilan Universityhttps://scholar.google.com/scholar?q=author%3A%22Sarit+Kraus%22&hl=en&num=2Nonmonotonic reasoning, preferential models and cumulative logicsMany systems that exhibit nonmonotonic behavior have been described and studied already in the literature. The general notion of nonmonotonic reasoning, though, has almost always been described only negatively, by the property it does not enjoy, ie monotonicity. We study …Collaborative plans for complex group actionThe original formulation of SharedPlans by B. Grosz and C. Sidner (1990) was developed to provide a model of collaborative planning in which it was not necessary for one agent to have intentions-to toward an act of a different agent. Unlike other contemporaneous …
85
Jitendra Malik29https://scholar.google.com/citations?user=oY9R5YQAAAAJ&hl=en&num=2&oi=ao212288Professor of EECS, UC Berkeleyhttps://scholar.google.com/scholar?q=author%3A%22Jitendra+Malik%22&hl=en&num=2Scale-space and edge detection using anisotropic diffusionA new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interregion smoothing. It is shown …Normalized cuts and image segmentationWe propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph …
86
Olga Sorkine-Hornung29https://scholar.google.com/citations?user=GBU568oAAAAJ&hl=en&num=2&oi=ao15370Professor of Computer Science, ETH ZurichDaniele Panozzo, Daniel Cohen-Or, Alec Jacobson, Alexander Sorkine-Hornung, Marc Alexa, yaron lipman, Tong-Yee Lee, Hans-Peter Seidel, Ladislav Kavan, Andy Nealen, Yu-Shuen Wang, Marco Tarini, Ran Gal, Wang Yifan, Kenshi Takayama, Emily Whiting, Christian Rössl, Ariel Shamir, Takeo Igarashi, Oliver Glauserhttps://scholar.google.com/scholar?q=author%3A%22Olga+Sorkine-Hornung%22&hl=en&num=2Make it stand: balancing shapes for 3D fabricationImbalance suggests a feeling of dynamism and movement in static objects. It is therefore not surprising that many 3D models stand in impossibly balanced configurations. As long as the models remain in a computer this is of no consequence: the laws of physics do not apply …A fully progressive approach to single-image super-resolutionRecent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors …
87
David Fleet29https://scholar.google.com/citations?user=njOmQFsAAAAJ&hl=en&num=2&oi=ao30072Google Brain; University of Toronto; Universiity of Toronto Scarborough; Vector InstituteAllan D. Jepson, Marcus A Brubaker, Mohammad Norouzi, Aaron Hertzmann, Ali Punjani, John Barron, Michael J. Black, Jack M. Wang, David J Heeger, Raquel Urtasun, Leonid Sigal, Pascal Fua, John L. Rubinstein, Fartash Faghri, Sven Dickinson, Kaleem Siddiqi, Yair Weiss, Micha Livne, Yanshuai Cao, Kyros Kutulakoshttps://scholar.google.com/scholar?q=author%3A%22David+Fleet%22&hl=en&num=2Performance of optical flow techniquesWhile different optical flow techniques continue to appear, there has been a lack of quantitative evaluation of existing methods. For a common set of real and synthetic image sequences, we report the results of a number of regularly cited optical flow techniques …cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determinationSingle-particle electron cryomicroscopy (cryo-EM) is a powerful method for determining the structures of biological macromolecules. With automated microscopes, cryo-EM data can often be obtained in a few days. However, processing cryo-EM image data to reveal …
88
Margaret Livingstone29https://scholar.google.com/citations?user=P_3rGrsAAAAJ&hl=en&num=2&oi=ao24562Professor of Neurobiology, Harvard Medical Schoolhttps://scholar.google.com/scholar?q=author%3A%22Margaret+Livingstone%22&hl=en&num=2Segregation of form, color, movement, and depth: anatomy, physiology, and perceptionAnatomical and physiological observations in monkeys indicate that the primate visual system consists of several separate and independent subdivisions that analyze different aspects of the same retinal image: cells in cortical visual areas 1 and 2 and higher visual …Psychophysical evidence for separate channels for the perception of form, color, movement, and depthPhysiological and anatomical findings in the primate visual system, as well as clinical evidence in humans, suggest that different components of visual information processing are segregated into largely independent parallel pathways. Such a segregation leads to certain …
89
Xiaoou Tang29https://scholar.google.com/citations?user=qpBtpGsAAAAJ&hl=en&num=2&oi=ao93493The Chinese University of Hong KongXiaogang Wang, Chen Change Loy, Ping Luo (羅平), Jian Sun, Yu Qiao, Dahua Lin, Kaiming He, Shuicheng Yan, Fellow of ACM, SAEn..., Ziwei Liu, Zhouchen Lin, Limin Wang, Yuanjun Xiong, Yi Sun, Shuo Yang, Rong Xiao, Zhanpeng Zhang (张展鹏), Luc Van Gool, Shi Qiu, Bolei Zhou, Dacheng Taohttps://scholar.google.com/scholar?q=author%3A%22Xiaoou+Tang%22&hl=en&num=2Single image haze removal using dark channel priorIn this paper, we propose a simple but effective image prior-dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of outdoor haze-free images. It is based on a key observation-most local patches in outdoor haze-free …Image super-resolution using deep convolutional networksWe propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low …
90
Dan Roth29https://scholar.google.com/citations?user=E-bpPWgAAAAJ&hl=en&num=2&oi=ao32684Professor of Computer Science, University of PennsylvaniaScott Wen-tau Yih, Ming-Wei Chang, Xin Li, Vivek Srikumar, Daniel Khashabi, Alla Rozovskaya, Shyam Upadhyay, Yangqiu Song, Qiang Ning, Dan Goldwasser, Roni Khardon, Kai-Wei Chang, Stephen Mayhew, Kevin Small, Haoruo Peng, Sariel Har-Peled, Rodrigo de Salvo Braz, Chen-Tse Tsai, Ido Dagan, Quang Dohttps://scholar.google.com/scholar?q=author%3A%22Dan+Roth%22&hl=en&num=2Introduction to statistical relational learningAdvanced statistical modeling and knowledge representation techniques for a newly emerging area of machine learning and probabilistic reasoning; includes introductory material, tutorials for different proposed approaches, and applications. Handling inherent …Design challenges and misconceptions in named entity recognitionWe analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system. In particular, we address issues such as the representation of text chunks, the inference approach needed to combine local …
91
Mike Fairclough29https://scholar.google.com/scholar?q=author%3A%22Mike+Fairclough%22&hl=en&num=2My left-field lesson-Ancient land revivedBeing on a major archaeological site is an exciting educational opportunity and at West Rise we have embraced the Bronze Age in a big way. Five years ago, after hearing about the Bronze Age settlement from a local archaeologist, we asked the authority if we could lease …My Left-field Lesson-Welcome to Room 13Children have created magnificent artwork, developed their creative autonomy and expanded their minds (and ours) alongside reputable artists-in-residence, who are paid for completely by income generated by Room 13. The dark side of art Children respond to the …
92
Jianbo Shi29https://scholar.google.com/citations?user=Sm14jYIAAAAJ&hl=en&num=2&oi=ao45252University of PennsylvaniaJitendra Malik, Stella X. Yu, Timothee Cour, Hyun Soo Park, Ralph Gross, Praveen Srinivasan, Thomas Leung, Serge Belongie, Katerina Fragkiadaki, Hua Zhong, Abhinav Gupta, Larry Davis, Kostas Daniilidis, Simon Baker, Ryan Kennedy, Gang Song, Robert T Collins, Weiyu Zhang, Yang Wu (伍 洋), Jeffrey Cohnhttps://scholar.google.com/scholar?q=author%3A%22Jianbo+Shi%22&hl=en&num=2Normalized cuts and image segmentationWe propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression of an image. We treat image segmentation as a graph …Good features to trackNo feature-based vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard …
93
Risto Miikkulainen29https://scholar.google.com/citations?user=2SmbjHAAAAAJ&hl=en&num=2&oi=ao21963Professor of Computer Science, the University of Texas at Austinhttps://scholar.google.com/scholar?q=author%3A%22Risto+Miikkulainen%22&hl=en&num=2Evolving neural networks through augmenting topologiesAn important question in neuroevolution is how to gain an advantage from evolving neural network topologies along with weights. We present a method, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a …Designing neural networks through neuroevolutionMuch of recent machine learning has focused on deep learning, in which neural network weights are trained through variants of stochastic gradient descent. An alternative approach comes from the field of neuroevolution, which harnesses evolutionary algorithms to optimize …
94
Robert Sloan29https://scholar.google.com/citations?user=2tUoA-wAAAAJ&hl=en&num=2&oi=ao5399Professor of Computer Science, University of Illinois at ChicagoGyorgy Turan, Tom Messerges, Judy Goldsmith, Balazs Szorenyi, Richard J LeBlanc, Ugo Buy, Heikki Topi, Lillian N. Cassel, Sally Goldman, Ronald L. Rivest, Ouri Wolfson, Dhruv Mubayi, Stellan Ohlsson, Dana Angluin, Bhaskar DasGupta, Tanya Berger-Wolf, Cynthia Taylor, Dimitris Diochnos, Pradip Srimani, Carl K. Changhttps://scholar.google.com/scholar?q=author%3A%22Robert+Sloan%22&hl=en&num=2Examining smart-card security under the threat of power analysis attacksThis paper examines how monitoring power consumption signals might breach smart-card security. Both simple power analysis and differential power analysis attacks are investigated. The theory behind these attacks is reviewed. Then, we concentrate on showing how power …Investigations of Power Analysis Attacks on Smartcards.This paper presents actual results from monitoring smartcard power signals and introduces techniques that help maximize such side-channel information. Adversaries will obviously choose attacks that maximize sidechannel information, so it is very important that the …
95
Ian Spence14https://scholar.google.com/citations?user=hItr498AAAAJ&hl=en&num=2&oi=ao5743Professor Emeritus of Psychology, University of TorontoJing Feng, Stephan Lewandowsky, Jay Pratt, Jacek Gwizdka, Justin G Hollands, Howard Wainer, Colin DeYoung, Claude Alain, Juergen Symanzik, Michael J. McGuffin, Natasha Elena Ouslis, Brian Pereirahttps://scholar.google.com/scholar?q=author%3A%22Ian+Spence%22&hl=en&num=2Playing an action video game reduces gender differences in spatial cognitionWe demonstrate a previously unknown gender difference in the distribution of spatial attention, a basic capacity that supports higher-level spatial cognition. More remarkably, we found that playing an action video game can virtually eliminate this gender difference in …Use case modelingUse cases are a simple, straightforward--yet very powerful--way to express the functional requirements (or behaviors) of a system. Use cases have gained widespread acceptance because they make requirements less ambiguous by specifying exactly when and under …
96
Martin Styner14https://scholar.google.com/citations?user=waEzpjgAAAAJ&hl=en&num=2&oi=ao23329Associate Professor of Computer Science and Psychiatry, University of North Carolina at Chapel HillGuido Gerig, John H. Gilmore, Hongtu Zhu, Lucia Cevidanes, Beatriz Paniagua, Ipek Oguz, Rebecca Knickmeyer, Weili Lin, Jeffrey Lieberman, Marc Niethammer, Clement Vachet, Claudia Buss, Sonja Entringer, Francois Budin, Kelly Botteron MD, sr dager, Jerod Rasmussen, Jed Elison, Alan Evans, PhD, FRSC, FCAHS, Robert Schultzhttps://scholar.google.com/scholar?q=author%3A%22Martin+Styner%22&hl=en&num=2Comparison and evaluation of methods for liver segmentation from CT datasetsThis paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the" MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a …Differences in white matter fiber tract development present from 6 to 24 months in infants with autismObjective: Evidence from prospective studies of high-risk infants suggests that early symptoms of autism usually emerge late in the first or early in the second year of life after a period of relatively typical development. The authors prospectively examined white matter …
97
Nathaniel Daw14https://scholar.google.com/citations?user=BxlScrEAAAAJ&hl=en&num=2&oi=ao25864Professor of Neurocience and Psychology, Princeton UniversityYael Niv, Ben Seymour, Daphna Shohamy, Raymond J Dolan, Elizabeth Phelps, David Touretzky, John P. O'Doherty, Aaron Courville, Samuel Gershman, Prof. T.W. Robbins, Ross Otto, Sham M Kakade, Bradley Doll, Jonathan D. Cohen, Claire M. Gillan, Aaron M. Bornstein, Valerie Voon, Daphna Joel, Jian Li, Steve Fleminghttps://scholar.google.com/scholar?q=author%3A%22Nathaniel+Daw%22&hl=en&num=2Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral controlA broad range of neural and behavioral data suggests that the brain contains multiple systems for behavioral choice, including one associated with prefrontal cortex and another with dorsolateral striatum. However, such a surfeit of control raises an additional choice …Cortical substrates for exploratory decisions in humansDecision making in an uncertain environment poses a conflict between the opposing demands of gathering and exploiting information. In a classic illustration of this 'exploration–exploitation'dilemma 1, a gambler choosing between multiple slot machines balances the …
98
Steven Franconeri14https://scholar.google.com/citations?user=SSSCmfoAAAAJ&hl=en&num=2&oi=ao5634Professor, Northwestern UniversityDaniel J. Simons, George A. Alvarez, Michael Gleicher, James T. Enns, Andrew Hollingworth, Steve Haroz, Remco Chang, Christine Nothelfer, Cindy Xiong, Lane Harrison, Heeyoung Choo, Michael Correll, Jason Scimeca, Audrey Lustig Michal, Stephen Mitroff, Danielle Albers Szafir, Fumeng Yang, Robert Kosara, Kevin Ochsner, Brian D. Fisherhttps://scholar.google.com/scholar?q=author%3A%22Steven+Franconeri%22&hl=en&num=2Moving and looming stimuli capture attentionAttention capture is often operationally defined as speeded search performance when an otherwise nonpredictive stimulus happens to be the target of a visual search. That is, if a stimulus captures attention, it should be searched with priority even when it is irrelevant to …How many objects can you track?: Evidence for a resource-limited attentive tracking mechanismMuch of our interaction with the visual world requires us to isolate some currently important objects from other less important objects. This task becomes more difficult when objects move, or when our field of view moves relative to the world, requiring us to track these …
99
Sunil Hadap14https://scholar.google.com/citations?user=4g-njrYAAAAJ&hl=en&num=2&oi=ao3141Principal Applied Scientist, Lab126 - AmazonKalyan Sunkavalli, Nathan Carr, Hailin Jin, Eli Shechtman, Nadia Magnenat Thalmann/ Nadia Th..., Ravi Ramamoorthi, Michael Tao, Stephen DiVerdi, Dimitris Samaras, Jorge Lopez-Moreno, Zhuo Hui, Kevin Karsch, Erik Reinhard, Diego Gutierrez, Jitendra Malik, Ming Lin, Aswin C Sankaranarayanan, Fabian Langguth, Aravind Krishnaswamy, Steve Marschnerhttps://scholar.google.com/scholar?q=author%3A%22Sunil+Hadap%22&hl=en&num=2Depth from combining defocus and correspondence using light-field camerasLight-field cameras have recently become available to the consumer market. An array of micro-lenses captures enough information that one can refocus images after acquisition, as well as shift one's viewpoint within the subapertures of the main lens, effectively obtaining …Neural face editing with intrinsic image disentanglingTraditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other---a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial …