Area of research
Computer Vision and Pattern Recognition
Research interest
Research interests include Human Pose and Action Recognition, Advanced Image and Video Retrieval Techniques, Multimodal Machine Learning Applications, and Generative Adversarial Networks and Image Synthesis.
Human-level few-shot concept induction through minimax entropy learning.
Synthesizing Diverse and Physically Stable Grasps With Arbitrary Hand Structures Using Differentiable Force Closure Estimator
In situ bidirectional human-robot value alignment
Scene Reconstruction with Functional Objects for Robot Autonomy
Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry
Cascaded Parsing of Human-Object Interaction Recognition.
In situ bidirectional human-robot value alignment.
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
Understanding Physical Effects for Effective Tool-Use
Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaboration
Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation.
Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
Hierarchical Human Semantic Parsing with Comprehensive Part-Relation Modeling
CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models
Interpretable CNNs for Object Classification
Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
Extraction of an Explanatory Graph to Interpret a CNN
Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns
A Generalized Earley Parser for Human Activity Parsing and Prediction
Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering
Patching interpretable <scp>And‐Or‐Graph</scp> knowledge representation using augmented reality
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines
Interpretable CNNs for Object Classification
LEMMA: A Multi-view Dataset for L Earning Multi-agent Multi-task Activities
A Competence-Aware Curriculum for Visual Concepts Learning via Question Answering
Introduction to Monte Carlo Methods
RI: Small: Inferring the "Dark Matter" and "Dark Energy" from Image and Video
CDI-Type II: Collaborative Research: Joint Image-Text Parsing and Reasoning for Analyzing Social and Political News Events
RI: Small: Learning and Inference with And-Or Graphs for Image Understanding
RI: Large Scale Object Recognition and Ground Truth Representation Using Stochastic Image Grammar
US-China Workshop on Computer Vision
Learning Fundamentals Atomic Image Structures From Natural Images, Video and Shapes
CAREER: Stochastic Modeling and Computing of Visual Patterns: From Descriptive to Generative Methods
CAREER: Stochastic Modeling and Computing of Visual Patterns: From Descriptive to Generative Methods
Learning Probability Models for Surface Appearance and Shape by Minimax Entropy Principle