Gang Hua
Microsoft
309 Papers
2.8K Citations
Gang Hua is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Facial recognition system. The author has an hindex of 60, co-authored 285 publications. Previous affiliations of Gang Hua include City University of Hong Kong & Honda.
Chat about Author
Papers
•Posted Content
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
TL;DR: A Two-Stream Consensus Network (TSCN) to simultaneously address weakly-supervised Temporal Action Localization challenges and a new attention normalization loss to encourage the predicted attention to act like a binary selection, and promote the precise localization of action instance boundaries.
Face Re-Lighting from a Single Image under Harsh Lighting Conditions
Yang Wang,Zicheng Liu,Gang Hua,Zhen Wen,Zhengyou Zhang,Dimitris Samaras +5 more
- 17 Jun 2007
TL;DR: This paper proposes a subregion based framework that uses a Markov Random Field to model the statistical distribution and spatial coherence of face texture, which makes the approach not only robust to harsh lighting conditions, but insensitive to partial occlusions as well.
Video Object Discovery and Co-segmentation with Extremely Weak Supervision
Le Wang,Gang Hua,Rahul Sukthankar,Jianru Xue,Nanning Zheng +4 more
- 06 Sep 2014
TL;DR: The proposed spatio-temporal energy minimization formulation for simultaneous video object discovery and co-segmentation across multiple videos containing irrelevant frames compares favorably with the state-of-the-art in all of these experiments.
Generating Descriptive Visual Words and Visual Phrases for Large-Scale Image Applications
TL;DR: Desc descriptive visual words (DVWs) and descriptive visual phrases (DVPs) are proposed as the visual correspondences to text words and phrases, where visual phrases refer to the frequently co-occurring visual word pairs.
89
•Posted Content
Poison Ink: Robust and Invisible Backdoor Attack.
TL;DR: This work proposes a robust and invisible backdoor attack called Poison Ink, which is not only general to different datasets and network architectures, but also flexible for different attack scenarios and has very strong resistance against many state-of-the-art defense techniques.
83