Profiles2020-2026
Gangshan Wu
Nanjing University
23Papers
16Last author
29Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers23
- CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot LearningAuthor 7 of 9CVPR 2026 · 47 citations
- In-the-wild Audio Spatialization with Flexible Text-guided LocalizationAuthor 5 of 5ACL 2025 · 2 citations
- Text-Guided Nonverbal Enhancement Based on Modality-Invariant and -Specific Representations for Video Speaking Style RecognitionAuthor 3 of 3AAAI 2025 · 2 citations
- Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy ConditioningAuthor 4 of 6CVPR 2025
- Sketch and Refine: Towards Fast and Accurate Lane DetectionAuthor 5 of 5AAAI 2024 · 27 citations
- SportsHHI: A Dataset for Human-Human Interaction Detection in Sports VideosAuthor 3 of 4CVPR 2024 · 9 citations
- RAVSS: Robust Audio-Visual Speech Separation in Multi-Speaker Scenarios with Missing Visual CuesAuthor 5 of 5ACM MM 2024 · 3 citations
- Robust Object Modeling for Visual TrackingAuthor 4 of 4ICCV 2023 · 165 citations
- Efficient Video Action Detection with Token Dropout and Context RefinementAuthor 4 of 5ICCV 2023 · 31 citations
- From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-resolutionAuthor 4 of 4AAAI 2023 · 26 citations
- Lightweight Super-Resolution Head for Human Pose EstimationAuthor 4 of 4ACM MM 2023 · 23 citations
- CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D DatasetsAuthor 3 of 4AAAI 2023 · 12 citations
- LinK: Linear Kernel for LiDAR-based 3D PerceptionAuthor 4 of 5CVPR 2023
- STMixer: A One-Stage Sparse Action DetectorAuthor 4 of 5CVPR 2023
- MixFormer: End-to-End Tracking with Iterative Mixed AttentionAuthor 4 of 4CVPR 2022 · 746 citations
- Negative Sample Matters: A Renaissance of Metric Learning for Temporal GroundingAuthor 5 of 5AAAI 2022 · 170 citations
- Heterogeneous Learning for Scene Graph GenerationAuthor 4 of 4ACM MM 2022 · 3 citations
- Relaxed Transformer Decoders for Direct Action Proposal GenerationAuthor 4 of 4ICCV 2021 · 220 citations
- MGSampler: An Explainable Sampling Strategy for Video Action RecognitionAuthor 4 of 4ICCV 2021 · 89 citations
- Target Adaptive Context Aggregation for Video Scene Graph GenerationAuthor 4 of 4ICCV 2021 · 80 citations
- Visual Relation of Interest DetectionAuthor 5 of 5ACM MM 2020 · 11 citations
- Memory Recursive Network for Single Image Super-ResolutionAuthor 4 of 4ACM MM 2020 · 4 citations
- Residual Feature Aggregation Network for Image Super-ResolutionAuthor 5 of 5CVPR 2020
