StillFast: An End-to-End Approach for
Short-Term Object Interaction Anticipation
F. Ragusa, G. M. Farinella, A. Furnari
FPV@IPLab - University of Catania
Next Vision s.r.l., Spin-off of the University of Catania
francesco.ragusa@unict.it
Abstract
Short Term Object Interaction Anticipation
StillFast Architecture
The anticipation problem has been studied considering different aspects such as predicting humans’ locations, predicting hands and objects trajectories, and forecasting actions and human-object interactions. In this paper, we studied the short-term object interaction anticipation problem from the egocentric point of view, proposing a new end-to-end architecture named StillFast. Our approach simultaneously processes a still image and a video detecting and localizing next-active objects, predicting the verb which describes the future interaction and determining when the interaction will start. Experiments on the large-scale egocentric dataset EGO4D show that our method outperformed state-of-the-art approaches on the considered task. Our method is ranked first in the public leaderboard of the EGO4D short term object interaction anticipation
challenge 2022 and it is the official baseline for the 2023 one. Please see the project web page for code and additional details: https://iplab.dmi.unict.it/stillfast/.
Ablation Study
Results
Different Heads
Proposed Head
Proposed Backbone
Qualitative Results
Success
Failure
Prediction Head