Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research focused on Artificial intelligence and Scale (ratio), with related work in Encoder, Perception, Computer vision. Notable publications include 'DPA-MVSNet: Dynamic Context Perception Multi-view Stereo with transformers and data augmentation', 'PGNet: Position guided infrared small target detection', and 'A Lip-Reading Recognition Method that Integrates a 3D Dual-Stream Convolutional Neural Network'.
DPA-MVSNet: Dynamic Context Perception Multi-view Stereo with transformers and data augmentation
PGNet: Position guided infrared small target detection
Toward a dynamic tree-Mamba encoder for UAV tracking with vision-language
KCGAFormer: When Large-Kernel ConvFormer Meets KAN in Semantic Segmentation
EROCNet: Multi-Scale Spectral Synergy for Resource-Efficient Retinal Optical Coherence Tomography Diagnosis
A Lip-Reading Recognition Method that Integrates a 3D Dual-Stream Convolutional Neural Network
Improving Retrieval-Based Dialogue Systems: Fine-Grained Post-training Prompt Adaptation and Pairwise Optimization Fine-Tuning Strategy
One-Shot Classification Is Enough for Automatic Label Mapping
Oracle Bone Script Recognition Based on Multi-scale Feature Fusion and Knowledge Distillation
Enhancing Hand Feature Recognition with Limited Data via Multi-Scale Reconstruction Attention