Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research interests include Multimodal Machine Learning Applications, Advanced Image and Video Retrieval Techniques, Domain Adaptation and Few-Shot Learning, and Face recognition and analysis.
ATCMD-Bench: Agentic Traditional Chinese Medicine diagnosis benchmark for Large Language Models via multi-agent simulation
Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels
Contrastive Transformer Learning With Proximity Data Generation for Text-Based Person Search
Spatial–Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels
Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels
Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction
Learning Consistent Global-Local Representation for Cross-Domain Facial Expression Recognition
Webly Supervised Fine-Grained Image Recognition with Graph Representation and Metric Learning
Fine-Grained Image Captioning With Global-Local Discriminative Objective
Efficient Crowd Counting via Structured Knowledge Transfer
Knowledge-Embedded Routing Network for Scene Graph Generation
Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Deep Reasoning with Knowledge Graph for Social Relationship Understanding
Recurrent Attentional Reinforcement Learning for Multi-Label Image Recognition
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
Multi-label Image Recognition by Recurrently Discovering Attentional Regions
DISC: Deep Image Saliency Computing via Progressive Representation Learning