Hefeng Wu

Sun Yat-sen University — China

Computer Science · Physical Sciences

22h-index2.1kcitations107works1.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Video Surveillance and Tracking Methods(40), Advanced Image and Video Retrieval Techniques(29), Domain Adaptation and Few-Shot Learning(22), Text and Document Classification Technologies(13), Human Pose and Action Recognition(12)

Publications107 total

Diffusion-Driven 3D Gaussian Splatting for Occlusion-Free Egocentric Scene Reconstruction
2025
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
2025
RoboPearls: Editable Video Simulation for Robot Manipulation
arXiv (Cornell University)·2025Open Access
MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models
arXiv (Cornell University)·2025Open Access
RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation
arXiv (Cornell University)·2025Open Access
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
arXiv (Cornell University)·2025Open Access
MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models
2025· 1 citedOpen Access
SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
IEEE Transactions on Image Processing·2025· 1 cited
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
2025· 1 citedOpen Access
Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition
arXiv (Cornell University)·2024Open Access
Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models
arXiv (Cornell University)·2024Open Access
Improving Network Interpretability via Explanation Consistency Evaluation
arXiv (Cornell University)·2024Open Access
Retraction Note: Multipoint infrared laser-based detection and tracking for people counting
Neural Computing and Applications·2024Open Access
Dual-perspective semantic-aware representation blending for multi-label image recognition with partial labels
Expert Systems with Applications·2024· 11 cited
Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
arXiv (Cornell University)·2024Open Access
Improving Network Interpretability via Explanation Consistency Evaluation
IEEE Transactions on Multimedia·2024· 1 cited
Category-Adaptive Label Discovery and Noise Rejection for Multi-Label Recognition With Partial Positive Labels
IEEE Transactions on Multimedia·2024· 6 cited
Dual-View Data Hallucination With Semantic Relation Guidance for Few-Shot Image Recognition
IEEE Transactions on Multimedia·2024· 7 cited
Research on defect recognition technology of transmission line based on visual macromodeling
Applied Mathematics and Nonlinear Sciences·2024Open Access
Spatial–Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
IEEE Transactions on Image Processing·2023· 22 cited
page 1 of 6Next →

Frequent Co-authors

Liang Lin(24), Tianshui Chen(18), Xiaonan Luo(15), Ruomei Wang(10), Tao Pu(9), Lingbo Liu(7), Guanbin Li(7), Hanhui Li(7), Shujin Lin(7), Yuan Xie(4), Xiaolu Hui(3), Jiaqi Chen(3), Jin Zhan(3), Fei Wang(3), Xiangjian He(3), Ling Tian(3), Ning Liu(2), Yongchao Long(2), Changqing Zou(2), Qun Niu(2)