G
Gao Huang
Researcher at Tsinghua University
Publications - 164
Citations - 43663
Gao Huang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 37, co-authored 124 publications receiving 26697 citations. Previous affiliations of Gao Huang include Cornell University & University of Science and Technology of China.
Papers
More filters
Journal ArticleDOI
Dynamic Spatial Focus for Efficient Compressed Video Action Recognition
TL;DR: Zhang et al. as mentioned in this paper proposed a dynamic spatial focus method for efficient compressed video action recognition (CoViFocus), which uses a light-weighted two-stream architecture to localize the task-relevant patches for both the RGB frames and motion vectors.
Journal ArticleDOI
Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism
TL;DR: Zhang et al. as discussed by the authors proposed a Social Environment ADjustment (SEAD) method, based on causal intervention rather than conventional likelihood, to remove the confounding effect of the social environment.
Journal ArticleDOI
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
Changyao Tian,Chenxin Tao,Jifeng Dai,Hao Li,Ziheng Li,Lewei Lu,Xiaogang Wang,Hongsheng Li,Gao Huang,Xizhou Zhu +9 more
TL;DR: Zhang et al. as mentioned in this paper proposed an Alternating Denoising Diffusion Process (ADDP) that integrates the two spaces within a single representation learning framework, and achieved competitive performance on unconditional generation, ImageNet classification, COCO detection, and ADE20k segmentation.
Journal ArticleDOI
Offline Prioritized Experience Replay
TL;DR: In this paper , a class of priority functions designed to prioritize highly-rewarding transitions, making them more frequently visited during training, is proposed to alleviate the distributional shift problem.
Posted Content
Tighter Bound Estimation of Sensitivity Analysis for Incremental and Decremental Data Modification
TL;DR: This work presents a method to calculate tighter bounds of a general linear score for the updated classifier such that it's more accurate to estimate the range of interest than existing papers.