Changsheng Xu

Xiamen University — China

Computer Science · Physical Sciences

81h-index25.8kcitations900works3.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Video Analysis and Summarization(192), Advanced Image and Video Retrieval Techniques(190), Multimodal Machine Learning Applications(180), Human Pose and Action Recognition(128), Domain Adaptation and Few-Shot Learning(112)

Publications900 total

Real-world database evaluation of drug-associated vitreous opacities and machine learning for clinical interpretability
Frontiers in Cell and Developmental Biology·2026Open Access
THMM-CLIP: Task-Guided Hierarchical Multi-Modal Alignment for Rehearsal-Free Class Incremental Learning
ACM Transactions on Multimedia Computing Communications and Applications·2025
Code-Driven LLM Agent for One-Shot Explanatory Visual Question Answering
ACM Transactions on Multimedia Computing Communications and Applications·2025
Marketization of Data Elements and Corporate Green Innovation: Evidence from the Establishment of Data Trading Platforms in China
Sustainability·2025Open Access
VidCog: Empowering LLM with Long Video Understanding via Human-like Temporal Cognitive Loop
2025
Toward Visual Grounding: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 1 cited
A Comprehensive Survey on Evidential Deep Learning and its Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 3 cited
DMC <sup>3</sup> : Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering
2025Open Access
Granular Music Attribute Transformation with Proximal Policy Optimization Adapters for Diffusion Model
2025
A Large-Scale Dataset for Short-Video Topic Peak Prediction and a Large Heterogeneous Graph Model
2025
StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
2025Open Access
Building Embodied EvoAgent: A Brain-inspired Paradigm for Bridging Multimodal Large Models and World Models
2025
FORGET ME: Federated Unlearning for Face Generation Models
2025
Fine-tuning Bias Neurons for Fair Text-to-Image Generation
2025
EgoPrompt: Prompt Learning for Egocentric Action Recognition
2025· 1 citedOpen Access
VRtalk: Real-Time Interactive Intelligent Anime Avatars in Virtual Reality
2025
Health-oriented Multimodal Food Question Answering with Implicit and Explicit Knowledge
ACM Transactions on Multimedia Computing Communications and Applications·2025
Graph Prompts: Adapting Video Graph for Video Question Answering
2025
Metapath-Enhanced Language Model Pretraining on Text-Attributed Heterogeneous Graphs
ACM Transactions on Multimedia Computing Communications and Applications·2025Open Access
Class-Specific Knowledge-Guided Multimodal Prompt Tuning for Few-Shot Class-Incremental Learning
IEEE Transactions on Circuits and Systems for Video Technology·2025
page 1 of 45Next →

Frequent Co-authors

Tianzhu Zhang(14), Weiming Dong(7), Si Liu(7), Shuicheng Yan(7), Hanqing Lu(6), Junyu Gao(5), Ming–Hsuan Yang(5), Chongyang Ma(5), Fan Tang(5), Qi Tian(5), Shengsheng Qian(4), Ling‐Yu Duan(4), Min Xu(4), Matej Kristan(3), Aleš Leonardis(3), Jiřı́ Matas(3), Michael Felsberg(3), Roman Pflugfelder(3), Luka Čehovin Zajc(3), Tomáš Vojíř(3)