← authors · overview

• Dynamic Dual-attentive Aggregation Learning For Visible-infrared Person Re-identification
  2020 · 418 citations
• Anatomy-aware 3D Human Pose Estimation With Bone-based Pose Decomposition
  2020 · 272 citations
• TAP: Text-aware Pre-training For Text-vqa And Text-caption
  2020 · 96 citations
• SAT: 2D Semantics Assisted Training For 3D Visual Grounding
  2021 · 90 citations
• Asymmetric Distribution Measure For Few-shot Learning
  2020 · 80 citations
• Expressing Objects Just Like Words: Recurrent Visual Embedding For Image-text Matching
  2020 · 59 citations
• On Vocabulary Reliance In Scene Text Recognition
  2020 · 58 citations
• Global Image Sentiment Transfer
  2020 · 1 citations
• Clip-vip: Adapting Pre-trained Image-text Model To Video-language Representation Alignment
  2022
• Pixeldit: Pixel Diffusion Transformers For Image Generation
  2025
• Endomatcher: Generalizable Endoscopic Image Matcher Via Multi-domain Pre-training For Robot-assisted Surgery
  2025
• How Far Are Surgeons From Surgical World Models? A Pilot Study On Zero-shot Surgical Video Generation With Expert Assessment
  2025
• Surgllm: A Versatile Large Multimodal Model With Spatial Focus And Temporal Awareness For Surgical Video Understanding
  2025
• Mmig-bench: Towards Comprehensive And Explainable Evaluation Of Multi-modal Image Generation Models
  2025
• Memory Enhanced Embedding Learning For Cross-modal Video-text Retrieval
  2021