已发表成果:
WOK 论文 150 篇;中文核心 12 篇;专利发明 5 个;图书及章节 1 本;
An End-to-End Scene Text Detector with Dynamic Attention
TRL: Transformer based refinement learning for hybrid-supervised semantic segmentation
Dimension-aware attention for efficient mobile networks
DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition
Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
When Sparse Neural Network Meets Label Noise Learning: A Multistage Learning Framework
When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework
Learning meta-adversarial features via multi-stage adaptation network for robust visual object tracking
Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples
FastVOD-Net: A Real-Time and High-Accuracy Video Object Detector
Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition
MULTI-FOCUS GUIDED SEMANTIC AGGREGATION FOR VIDEO OBJECT DETECTION
LEARNING CORRELATION FOR ONLINE MULTIPLE OBJECT TRACKING
BOUNDING BOX DISTRIBUTION LEARNING AND CENTER POINT CALIBRATION FOR ROBUST VISUAL TRACKING
Co-Clustering on Bipartite Graphs for Robust Model Fitting
DUALFEAT: DUAL FEATURE AGGREGATION FOR VIDEO OBJECT DETECTION
GUIDED SAMPLING BASED FEATURE AGGREGATION FOR VIDEO OBJECT DETECTION
MDNET: MOTION DISTINCTION NETWORK FOR EFFECTIVE ACTION RECOGNITION
EGNET: A NOVEL EDGE GUIDED NETWORK FOR INSTANCE SEGMENTATION
MSFL-Net: Multi-Semantic Feature Learning Network for Occluded Person Re-Identification
Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition