Schedule

Date

Aug 18

Presenters

Gedas

Topic

Course Overview;

Project Details

Paper Critique Details

Papers

Slides

intro slides

Overview of 2D CNNs

Aug 23

Gedas

[1] Large-scale Video Classification with Convolutional Neural Networks

[2] Long-term Recurrent Convolutional Networks for Visual Recognition and Description

Video Classification

pdf

Aug 25

Gedas

Video Classification

[3] Two-Stream Convolutional Networks for Action Recognition in Videos

pdf

[4] Convolutional Two-Stream Network Fusion for Video Action Recognition

pdf

[5] Learning Spatiotemporal Features with 3D Convolutional Networks

[6] Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

Aug 30

Gedas

Yi-Lin

Video Classification

pdf

Sep 1

Feng

Video Classification

[7] A Closer Look at Spatiotemporal Convolutions for Action Recognition

pdf

Yi-Lin

[8] Video Classification with Channel-Separated Convolutional Networks

pdf

Sep 6

No Class (Labor Day)

Sep 8

Gedas

Video Classification

[9] Non-local Neural Networks

pdf

[10] SlowFast Networks for Video Recognition

pdf

Sep 13

Hastings

Video Classification

[11] Videos as Space-Time Region Graphs

Gedas

[12] Long-Term Feature Banks for Detailed Video Understanding

pdf

Sep 15

Project Proposal

Sep 20

Jialu

Yunkui

[13] Compressed Video Action Recognition

[14] TSM: Temporal Shift Module for Efficient Video Understanding

Video Classification

pdf

Sep 22

Gedas

Optical Flow Prediction

[15] FlowNet: Learning Optical Flow with Convolutional Networks

pdf

[16] RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

pdf

Sep 27

Jialu

Maitrey

Object Detection and Tracking

[17] Flow-Guided Feature Aggregation for Video Object Detection

[18] Detect to Track and Track to Detect

pdf

Sep 29

Gedas

Qin

Object Detection and Tracking

[19] Tracking without Bells and Whistles

pdf

[20] Tracking Objects as Points

pdf

Oct 4

Qin

[21] One-Shot Video Object Segmentation

Video Object Segmentation

[22] RVOS: End-to-End Recurrent Network for Video Object Segmentation

Qian

pdf

Oct 6

Gedas

Video Object Segmentation

[23] Video Instance Segmentation

pdf

[24] Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation

pdf

[25] Generating Videos with Scene Dynamics

[26] MoCoGAN: Decomposing Motion and Content for Video Generation

Oct 11

Yunkui

Mohaiminul

Video Generation

pdf

Oct 13

Chun-Hung

Hastings

Self-Supervised Learning

[27] Unsupervised Learning of Visual Representations using Videos

pdf

[28] Learning Correspondence from the Cycle-consistency of Time

pdf

Oct 18

Project Milestone

Oct 20

Gedas

Self-Supervised Learning

[29] Tracking Emerges by Colorizing Videos

pdf

[30] Anticipating Visual Representations with Unlabeled Video

pdf

Oct 25

Self-Supervised Learning

[31] Unsupervised Learning of Depth and Ego-Motion from Video

Qian

Chun-Hung

[32] Learning image representations tied to ego-motion

pdf

Oct 27

Maitrey

Avinash

Self-Supervised Learning

[33] SpeedNet: Learning the Speediness in Videos

pdf

[34] Video Representation Learning by Dense Predictive Coding

pdf

Nov 1

Gedas

Self-Supervised Learning

[35] A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

pdf

Nov 3

Gedas

Multi-Modal Learning

[36] Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization

pdf

[37] Self-Supervised Learning by Cross-Modal Audio-Video Clustering

Nov 8

Yan-Bo

Zishun

Multi-Modal Learning

[38] Learning to Separate Object Sounds by Watching Unlabeled Video

[39] The Sound of Pixels

pdf

Nov 10

Zishun

Multi-Modal Learning

[40] HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

pdf

Avinash

[41] End-to-End Learning of Visual Representations from Uncurated Instructional Videos

pdf

Nov 15

Yan-Bo

Gedas

Multi-Modal Learning

[42] Dense-Captioning Events in Videos

[43] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

pdf

Nov 17

Gedas

Transformers for Video Analysis

[44] Is Space-Time Attention All You Need for Video Understanding?

pdf

[45] Perceiver: General Perception with Iterative Attention

pdf

Nov 22

Mohaiminul

Feng

Transformers for Video Analysis

[47] MERLOT: Multimodal Neural Script Knowledge Models

[46] VideoBERT: A Joint Model for Video and Language Representation Learning

pdf

Nov 24

No Class (Thanksgiving)

Nov 29

No Class

Dec 1

Final Project Presentation

About

Project Details

Paper Critique Details