Xingdong Sheng

5 papers · 2024–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (17)

Venues

ICCV (2) AAAI (1) CVPR (1) ICML (1)

Top co-authors

Yichao Yan (3) Wenjun Zeng (2) Yifan liu (2) Yunhui Liu (2) Xin Jin (2) Congsheng Xu (2) Xiaokang Yang (2) Liang Xu (2) Runze Li (1) Jie Qin (1)

Research topics

Computer Vision (4) Artificial Intelligence (3) Machine Learning (3) Analysis (3) Core AI (3) Deep Learning (2) Application Areas (2) Data Science & Analytics (1) Robotics (1) Applications (1) Architectures (1) Capabilities (1) Core Methods (1) Domain-Specific (1) Generation (1)

Keywords

multimodal dataset (2) action recognition (2) motion capture (2) motion analysis (1) motion estimation (1) knowledge distillation (1) multimodal learning (1) egocentric vision (1) video understanding (1) human-object interaction (1) object tracking (1) vision-language model (1) body motion (1) gesture recognition (1) long-tail distribution (1) clip model (1) open vocabulary (1) hand gesture recognition (1) replacement training (1) stage division strategy (1)

Papers

LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation AAAI 2026 Enhancing Visual Localization with Cross-Domain Image Generation ICML 2025 General Compression Framework for Efficient Transformer Object Tracking ICCV 2025 Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions ICCV 2025 Inter-X: Towards Versatile Human-Human Interaction Analysis CVPR 2024