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
Fine-grained few shot learning with foreground object transformation
TL;DR: Zhang et al. as discussed by the authors proposed a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator to remove image background, which tends to increase the difficulty of fine-grained image classification as it amplifies the intra-class variance while reducing interclass variance.
Proceedings ArticleDOI
Contrastive Language-Image Pre-Training with Knowledge Graphs
TL;DR: This paper proposes a knowledge-based pre-training framework, dubbed Knowledge-CLIP, which injects semantic information into the widely used CLIP model, and can semantically align the representations in vision and language with higher quality, and enhance the reasoning ability across scenarios and modalities.
Journal ArticleDOI
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
Weijie Su,Xizhou Zhu,Chenxin Tao,Lewei Lu,Bin Li,Gao Huang,Yu Qiao,Xiaogang Wang,Jie Zhou,Jifeng Dai +9 more
TL;DR: In this article , the authors proposed a general multi-modal mutual information formula as a unified optimization target and demonstrate that all existing pre-training strategies are special cases of their framework.
Posted Content
Towards Learning Spatially Discriminative Feature Representations.
TL;DR: Zhang et al. as mentioned in this paper proposed a loss function, termed as CAM-loss, to constrain the embedded feature maps with the class activation maps (CAMs), which indicate the spatially discriminative regions of an image for particular categories.
Posted Content
FSD-10: A Dataset for Competitive Sports Content Analysis
Shenglan Liu,Xiang Liu,Gao Huang,Lin Feng,Lianyu Hu,Dong Jiang,Aibin Zhang,Yang Liu,Hong Qiao +8 more
TL;DR: A keyframe based temporal segment network (KTSN) for classification and achieve remarkable performance is proposed and is motivated by the idea that domain knowledge is of great concern in sports field.