13 citations
- Megvii (China)5 papers
- Australian National UniversityAU1 paper
- Beijing University of Posts and TelecommunicationsCN1 paper
- Chinese Academy of SciencesCN1 paper
- Chinese University of Hong KongHK1 paper
- Global Energy Interconnection Research Institute North AmericaUS1 paper
- Hong Kong University of Science and TechnologyHK1 paper
- Institute of Computing TechnologyCN1 paper
- Peking UniversityCN1 paper
- Tsinghua UniversityCN1 paper
6 papers · 1 filter
Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
Weixin Feng, Yuanjiang Wang, Lihua Ma +2
The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as…
WeightNet: Revisiting the Design Space of Weight Networks
Ningning Ma, Xiangyu Zhang, Jiawei Huang +1
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective…
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
Zhongdao Wang, Jingwei Zhang, Liang Zheng +4
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as t…
Attentive Normalization for Conditional Image Generation
Yi Wang, Ying-Cong Chen, Xiangyu Zhang +2
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled w…
A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
Shangbang Long, Yushuo Guan, Kaigui Bian +1
Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods…
Deep Fusion Network for Image Completion
Xin Hong, Pengfei Xiong, Renhe Ji +1
Deep image completion usually fails to harmonically blend the restored image into existing content, especially in the boundary area. This paper handles with this problem from a new…