Gangshan Wu

Nanjing University — China

Computer Science · Physical Sciences

39h-index7.3kcitations320works2.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(70), Human Pose and Action Recognition(68), Multimodal Machine Learning Applications(53), Advanced Vision and Imaging(48), Advanced Image Processing Techniques(37)

Publications318 total

GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates
arXiv (Cornell University)·2026Open Access
GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates
ArXiv.org·2026Open Access
VMonarch: Efficient Video Diffusion Transformers with Structured Attention
arXiv (Cornell University)·2026Open Access
VMonarch: Efficient Video Diffusion Transformers with Structured Attention
ArXiv.org·2026Open Access
Cross-View and Cross-Modal Contrastive Learning for Radar Object Detection
IEEE Signal Processing Letters·2026
SwiTrack: Tri-State Switch for Cross-Modal Object Tracking
arXiv (Cornell University)·2025Open Access
Towards Practical Real-Time Low-Latency Music Source Separation
arXiv (Cornell University)·2025Open Access
SAM 2++: Tracking Anything at Any Granularity
arXiv (Cornell University)·2025Open Access
Towards Practical Real-Time Low-Latency Music Source Separation
2025
Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking
arXiv (Cornell University)·2025Open Access
NTIRE 2025 Challenge on Image Super-Resolution ($\times 4$): Methods and Results
2025· 1 cited
AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
2025· 1 cited
Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning
2025· 1 cited
In-the-wild Audio Spatialization with Flexible Text-guided Localization
arXiv (Cornell University)·2025Open Access
CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
arXiv (Cornell University)·2025Open Access
AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
arXiv (Cornell University)·2025Open Access
Text-Guided Nonverbal Enhancement Based on Modality-Invariant and -Specific Representations for Video Speaking Style Recognition
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection
arXiv (Cornell University)·2025Open Access
FSDM: An efficient video super-resolution method based on Frames-Shift Diffusion Model
Neural Networks·2025
JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 1 cited
page 1 of 16Next →

Frequent Co-authors

Limin Wang(22), Jie Liu(10), Jie Tang(8), Tongwei Ren(7), Yutao Cui(5), Cheng Jiang(3), Ran Ju(3), Wenjing Geng(3), Zhenzhi Wang(3), Zongcai Du(3), Jie Tang(3), Yawei Li(3), Kai Zhang(3), Radu Timofte(3), Yu Qiao(3), Chao Dong(3), Long Sun(3), Ling Ge(2), Zhan Tong(2), Jian-Chao Wu(2)