activity
20172022
most citedA Comprehensive Study of Deep Video Action Recognition

115 citations · 176 across the 9 of their papers we have counts for

collaborators

15 papers

cs.CV2022

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

Feng Cheng, Mingze Xu, Yuanjun Xiong +4

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete…

cs.CV20211 cited

Video Contrastive Learning with Global Context

Haofei Kuang, Yi Zhu, Zhi Zhang +5

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastiv…

cs.CV20215 cited

SiamMOT: Siamese Multi-Object Tracking

Bing Shuai, Andrew Berneshawi, Xinyu Li +2

In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. Si…

cs.CV2021

SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation

Zhe Wang, Hao Chen, Xinyu Li +4

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos…

cs.CV2021

VidTr: Video Transformer Without Convolutions

Yanyi Zhang, Xinyu Li, Chunhui Liu +6

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal infor…

cs.CV2021

Selective Feature Compression for Efficient Activity Recognition Inference

Chunhui Liu, Xinyu Li, Hao Chen +2

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world appli…