Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research focused on Artificial intelligence and Feature (linguistics), with related work in Discriminative model, Upsampling, Closed captioning. Notable publications include 'DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking', 'SDDNet: A Fast and Accurate Network for Surface Defect Detection', and 'An Efficient Method of Crowd Aggregation Computation in Public Areas'.
Focal and Global Spatial-Temporal Transformer for Skeleton-Based Action Recognition
Visualizing Large-Scale Spatial Time Series with GeoChron
Client Selection and Resource Allocation for Federated Learning in Digital-Twin-Enabled Industrial Internet of Things
Align and Tell: Boosting Text-Video Retrieval With Local Alignment and Fine-Grained Supervision
Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes
Stability analysis for nonlinear switched singular systems via T-S fuzzy modeling
Aspect-Aware Graph Attention Network for Heterogeneous Information Networks
FT-HID: a large-scale RGB-D dataset for first- and third-person human interaction analysis
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
SDDNet: A Fast and Accurate Network for Surface Defect Detection
Trear: Transformer-Based RGB-D Egocentric Action Recognition
A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
Discriminative Feature Learning for Thorax Disease Classification in Chest X-ray Images
Transformer guided geometry model for flow-based unsupervised visual odometry
New stability conditions of CPSs with multiple transportation channels under DoS attacks
Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation
Joint Attribute Manipulation and Modality Alignment Learning for Composing Text and Image to Image Retrieval
A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement
An Efficient Method of Crowd Aggregation Computation in Public Areas
LG-CNN: From local parts to global discrimination for fine-grained recognition