activity
20202023
most citedDynamic Sampling Networks for Efficient Action Recognition in Videos

86 citations · 100 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2023

Memory-and-Anticipation Transformer for Online Action Understanding

Jiahao Wang, Guo Chen, Yifei Huang +2

Most existing forecasting systems are memory-based methods, which attempt to mimic human forecasting ability by employing various memory mechanisms and have progressed in temporal…

cs.CV202315 cited

VideoLLM: Modeling Video Sequence with Large Language Models

Guo Chen, Yin-Dong Zheng, Jiahao Wang +8

With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models ar…

cs.CV2023

MRSN: Multi-Relation Support Network for Video Action Detection

Yin-Dong Zheng, Guo Chen, Minglei Yuan +1

Action detection is a challenging video understanding task, requiring modeling spatio-temporal and interaction relations. Current methods usually model actor-actor and actor-contex…

cs.CV202214 cited

InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges

Guo Chen, Sen Xing, Zhe Chen +18

In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, includin…

cs.CV2022

Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022

Yin-Dong Zheng, Guo Chen, Jiahao Wang +2

Capturing the state changes of interacting objects is a key technology for understanding human-object interactions. This technical report describes our method using heterogeneous b…

cs.CV2022

Uncertainty-based Network for Few-shot Image Classification

Minglei Yuan, Qian Xu, Chunhao Cai +3

The transductive inference is an effective technique in the few-shot learning task, where query sets update prototypes to improve themselves. However, these methods optimize the mo…