Xinggang Wang
Huazhong University of Science and Technology
1 paper in the Anchorcite directory, published in 2020, cited 5,351 times in total.
ORCID profileResearch topics
- Domain Adaptation and Few-Shot Learning · 1 paper
- Advanced Neural Network Applications · 1 paper
- Human Pose and Action Recognition · 1 paper
Frequent co-authors
- Jingdong Wang · 1 paper
- Ke Sun · 1 paper
- Tianheng Cheng · 1 paper
- Borui Jiang · 1 paper
- Chaorui Deng · 1 paper
- Yang Sheng Zhao · 1 paper
- Dong Liu · 1 paper
- Yadong Mu · 1 paper
Papers
- Deep High-Resolution Representation Learning for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · 5,351 citations
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution…
Metadata from OpenAlex (CC0).