Yansong Tang
16 papers · 5 citations
Most-cited papers
- LAVT: Language-aware Vision Transformer For Referring Image Segmentation2021 · 335 citations
- SAM2-LOVE: Segment Anything Model 2 In Language-aided Audio-visual Scenes2025 · 4 citations
- Flash-vstream: Efficient Real-time Understanding For Long Video Streams2025
- Meta-cot: Enhancing Granularity And Generalization In Image Editing2026
Topics