Shiguang Shan
13 papers · 1 citations
Most-cited papers
- VRSTC: Occlusion-free Video Person Re-identification2019 · 192 citations
- Tokenize Anything Via Prompting2023 · 28 citations
- Generalized Face Liveness Detection Via De-fake Face Generator2024 · 7 citations
- Towards Robust Semantic Segmentation Against Patch-based Attack Via Attention Refinement2024 · 3 citations
- SHALE: A Scalable Benchmark For Fine-grained Hallucination Evaluation In Lvlms2025 · 1 citations
- Jodi: Unification Of Visual Generation And Understanding Via Joint Modeling2025
- Jodi: Unification Of Visual Generation And Understanding Via Joint Modeling2025
- Un\(^2\)clip: Improving Clip's Visual Detail Capturing Ability Via Inverting Unclip2025
Topics