Area of research
Computer Vision and Pattern Recognition
Research interest
Research interests include Advanced Image and Video Retrieval Techniques, Advanced Vision and Imaging, Generative Adversarial Networks and Image Synthesis, and Image Retrieval and Classification Techniques.
LLM <sup>3</sup> : Large Language Model-based Task and Motion Planning with Motion Failure Reasoning
An Important Pick-and-Pass Gated Refinement Network for Salient Object Detection in Optical Remote Sensing Images
Study on the Effect of Non-Linear Ventilation Pipe Composite Measures on the Slope Permafrost Subgrade
Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering
Trajectory Prediction with Latent Belief Energy-Based Model
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
A Study of Local Optima for Learning Feature Interactions using Neural Networks
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Interpretable CNNs for Object Classification
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
Interpreting CNNs via Decision Trees
A tale of two explanations: Enhancing human trust by explaining robot behavior
Emergence of analogy from relation learning
Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
Neural Information Processing Systems 2019cited by 41position: last
Interpretable Convolutional Neural Networks
Interpreting CNN Knowledge via an Explanatory Graph
Learning Descriptor Networks for 3D Shape Synthesis and Analysis
Cooperative Training of Descriptor and Generator Networks
Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching
Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet
Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
Learning Fine-Grained Image Similarity with Deep Ranking
Cross-View Action Modeling, Learning, and Recognition
Learning Actionlet Ensemble for 3D Human Action Recognition
Cosegmentation and Cosketch by Unsupervised Learning
Mining actionlet ensemble for action recognition with depth cameras
An Embodied, Augmented Reality Coding Platform for Pair Programming
RI: Small: Visual Reasoning and Self-questioning for Explainable Visual Question Answering
RI: Small: A Unified Compositional Model for Explainable Video-based Human Activity Parsing
RI: Small: Modeling and Learning Visual Similarities Under Adverse Visual Conditions
RI: Small: Mining and Learning Visual Contexts for Video Scene Understanding
Collaborative Research: Sino-USA Summer School in Vision, Learning, Pattern Recognition VLPR 2010
RI: Small: Computational Models of Context-awareness and Selective Attention for Persistent Visual Target Tracking
CAREER: Visual Analysis of High-Dimensional Motion: A Distributed/Collaborative Approach
Transductive Learning for Retrieving and Mining Visual Contents
Essential Surfaces and the Topology of 3-Manifolds
U.S.-China Cooperative Research: Fluid Mechanics Investiga-tions of a High Interaction Magnetohydrodynamic Generator