CSCI 3280

Introduction to Multimedia Systems

(2026 Spring)

Computer Science & Engineering

The Chinese University of Hong Kong

Announcement

​

• The project presentation will be hosted on April 16 with the final report due on April 26.

​

• The final exam is scheduled on April 27.

Grading

1

– You can bring your slides, notes or books.

– No calculator, laptops and cell phone (no access to Internet)

Media Types

Main Content

Communication

Storage

Compression

Modeling

Representation

Representation (1)

• Text:

– Basic definition

– Tokenization, stop words, stemming, normalization

– Bag of words, 1-of-N encoding

​

• Image:

– Color Model

– Sampling, quantization and coding

– Filtering (convolution), edge detection, deblurring

​

• Audio:

– Sampling, quantization and coding

– MFCC, LPC features

– Conformer

Representation (2)

• Video:

– Basic definition

– Interlacing, TV standards

– Computer animation

​

• Graphics:

– Basic definition (2D & 3D)

– Image-based rendering

Modeling (Learning)

• Text modeling:

– Word embedding (Glove, Word2vec)

– Transformer, GPT, Bert

​

• Image modeling:

– Resnet, Googlenet, Alexnet

​

• Video modeling:

– CNN+RNN, 3D Convolution, Two streams

​

• Multimedia fusion and learning:

– Different fusion methods, Multimodal Attention

Compression

• Entropy coding:

– Basic definition

– Run-Length Encoding

– Huffman coding

– LZ78, LZW

​

• Source coding:

– Basic definition

– DCT

– JPEG

System Design

• Design a AI system for a specific task

– Workflow (input/output, main steps etc.)

– Modeling method (deep learning or non-deep learning, what kind of models etc.)

– Pseudocode

​

• Example: how to design a system to detect driver fatigue driving (you can use camera, sensors etc.)?

LZ78

LZ78