Coursework

Topic Presentation

Select a topic to present in class. Must be approved by instructor.

Papers

- Video Analysis

The DeepFake Detection Challenge Dataset 
(link)

CLEVRER: Collision Events For Video Representation And Reasoning
(link)

- Semantic Video Understanding

Action recognition with spatial-temporal discriminative filter banks
(link)

Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
(link)


- Tracking

Combining detection and tracking for human pose estimation in videos
(link)

Multiple Object Tracking with Siamese Track-RCNN
(link)


- Efficient Learning and Inference

X3D: Expanding Architectures for Efficient Video Recognition
(link)

A Multigrid Method for Efficiently Training Video Models
(link)


- Multimodal

Audiovisual SlowFast Networks for Video Recognition
(link)

Music Gesture for Visual Sound Separation
(link)

VideoBERT: A Joint Model for Video and Language Representation Learning
(link)


- Lip Reading

Deep Lip Reading: A comparison of models and an online application
(link)

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
(link)

Lip Reading Sentences in the Wild
(link)

LipNet: End-to-End Sentence-level Lipreading
(link)

- VR

MEgATrack: Monochrome Egocentric Articulated Hand-Tracking for Virtual Reality
(link)

The Eyes Have It: An Integrated Eye and Face Model for Photorealistic Facial Animation
(link)