Area of research
Computer Vision and Pattern Recognition · Media Technology
Research interest
Research interests include Subjectivity, Leverage (statistics), Perception, Image (mathematics), Artificial intelligence, and Materials science.
Self-powered position-sensitive TiO2/PZT/p-GaN UV detector with long working distance
Remote sensing image semantic segmentation via class-guided structural interaction and boundary perception
Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample
RQFormer: Rotated Query Transformer for end-to-end oriented object detection
CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
Cross-Class Bias Rectification for Point Cloud Few-Shot Segmentation
Context-aware and part alignment for visible-infrared person re-identification
Diverse Image Captioning via Conditional Variational Autoencoder and Dual Contrastive Learning
Swin Transformer Embedding UNet for Remote Sensing Image Semantic Segmentation
Info-FPN: An Informative Feature Pyramid Network for object detection in remote sensing images
Spatial-Temporal Based Multihead Self-Attention for Remote Sensing Image Change Detection
ResT-ReID: Transformer block-based residual learning for person re-identification
CLT-Det: Correlation Learning Based on Transformer for Detecting Dense Objects in Remote Sensing Images
Multi-source collaborative enhanced for remote sensing images semantic segmentation
Incremental learning with neural networks for computer vision: a survey
TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
Few-Shot Object Detection via Context-Aware Aggregation for Remote Sensing Images
Learning image aesthetic subjectivity from attribute-aware relational reasoning network
Weakly Supervised Few-Shot Semantic Segmentation via Pseudo Mask Enhancement and Meta Learning
Survey for person re-identification based on coarse-to-fine feature learning
Cyclic Self-attention for Point Cloud Recognition
Multi-Stage Fusion and Multi-Source Attention Network for Multi-Modal Remote Sensing Image Segmentation
Spatial hierarchy perception and hard samples metric learning for high-resolution remote sensing image object detection
AMC-Net: Attentive modality-consistent network for visible-infrared person re-identification
Point cloud recognition based on lightweight embeddable attention module
Video Object Segmentation and Tracking
Person image synthesis through siamese generative adversarial network
Structural similarity preserving GAN for infrared and visible image fusion
Diverse sample generation with multi-branch conditional generative adversarial network for remote sensing objects detection
Multiobjective ResNet pruning by means of EMOAs for remote sensing scene classification