已发表成果:
WOK 论文 226 篇;中文核心 9 篇;专利发明 8 个;
Spatial-Contextual Discrepancy Information Compensation for GAN Inversion
MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification
SPL-Net: Spatial-Semantic Patch Learning Network for Facial Attribute Recognition with Limited Labeled Data
Efficient sampling using feature matching and variable minimal structure size
PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition
Robust Multiple-Structure Geometric Model Fitting by Preserving Neighborhood Consistency
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
PERSONALIZED FEDERATED LEARNING ON LONG-TAILED DATA VIA ADVERSARIAL FEATURE AUGMENTATION
MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification
Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification
Federated Semi-Supervised Learning with Annotation Heterogeneity
Task-Aware Dual-Representation Network for Few-Shot Action Recognition
Orientation-Aware Pedestrian Attribute Recognition Based on Graph Convolution Network
TCNet: A Novel Triple-Cooperative Network for Video Object Detection
PARFormer: Transformer-Based Multi-Task Network for Pedestrian Attribute Recognition
Class-Aware Dual-Supervised Aggregation Network for Video Object Detection
DGRNet: A Dual-Level Graph Relation Network for Video Object Detection
Multi-Motion Segmentation via Co-Attention-Induced Heterogeneous Model Fitting
Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
A Dual-Path Transformer Network for Scene Text Detection
ERBNet: An Effective Representation Based Network for Unbiased Scene Graph Generation
Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking
Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation
DQFORMER: Dynamic Query Transformer for Lane Detection
Label-Noise Learning with Intrinsically Long-Tailed Data