Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-...
Publications
3 shownCCNet: Criss-Cross Attention for Semantic Segmentation
Full-image dependencies provide useful contextual information to benefit visual understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for obtaining such...
ByteTrack: Multi-object Tracking by Associating Every Detection Box
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are...
Frequent Co-Authors
Researcher Info
- h-index
- 3
- Publications
- 3
- Citations
- 8,440
- Institution
- Huazhong University of Science and Technology
External Links
Identifiers
- ORCID
- 0000-0002-4582-7488
Impact Metrics
h-index
3
h-index: Number of publications with at least h citations each.