Xiangtai Li
27 papers · 0 citations
Most-cited papers
- Involution: Inverting The Inherence Of Convolution For Visual Recognition2021 · 366 citations
- GFF: Gated Fully Fusion For Semantic Segmentation2019 · 133 citations
- RTMO: Towards High-performance One-stage Real-time Multi-person Pose Estimation2023 · 64 citations
- Polyphonicformer: Unified Query Learning For Depth-aware Video Panoptic Segmentation2021 · 35 citations
- Towards Language-driven Video Inpainting Via Multimodal Large Language Models2024 · 22 citations
- The 1st Solution For 7th LSVOS RVOS Track: Sasasa2va2025
- Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation And Methodology2025
- Human-in-context: Unified Cross-domain 3D Human Motion Modeling Via In-context Learning2025
- Diffdecompose: Layer-wise Decomposition Of Alpha-composited Images Via Diffusion Transformers2025
- Samtok: Representing Any Mask With Two Words2026
Topics