Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research interests include Advanced Image and Video Retrieval Techniques, Human Pose and Action Recognition, Face and Expression Recognition, and Domain Adaptation and Few-Shot Learning.
Bridging Synthetic and Real Images: A Transferable and Multiple Consistency Aided Fundus Image Enhancement Framework
Coarse-To-Fine Deep Video Coding with Hyperprior-Guided Mode Prediction
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Learning based Multi-modality Image and Video Compression
FVC: A New Framework towards Deep Video Compression in Feature Space
VoxelContext-Net: An Octree based Framework for Point Cloud Compression
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition
VDM-DA: Virtual Domain Modeling for Source Data-Free Domain Adaptation
Human-Centric Spatio-Temporal Video Grounding With Visual Transformers
Transformer3D-Det: Improving 3D Object Detection by Vote Refinement
STVGBert: A Visual-linguistic Transformer based Framework for Spatio-temporal Video Grounding
SRDAN: Scale-aware and Range-aware Domain Adaptation Network for Cross-dataset 3D Object Detection
An End-to-End Learning Framework for Video Compression
Content Adaptive and Error Propagation Aware Deep Video Compression
Improving Deep Video Compression by Resolution-Adaptive Flow Coding
Multi-Dimensional Pruning: A Unified Framework for Model Compression
Model Compression Using Progressive Channel Pruning
Dense Video Captioning Using Graph-Based Sentence Summarization
Channel Pruning Guided by Classification Loss and Feature Importance
DVC: An End-To-End Deep Video Compression Framework
P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization
Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation
Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition
Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation
Generalized Latent Multi-View Subspace Clustering
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection