← back to search

Song‐Chun Zhu

Central Conservatory of Music · CN
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.
h-index
73
citations
20,610
works
628
NIH funding
primary concept
email

Recent publications

Human-level few-shot concept induction through minimax entropy learning.
2024cited by 2position: contributordoi
Computer Vision
2023cited by 108position: firstdoi
Synthesizing Diverse and Physically Stable Grasps With Arbitrary Hand Structures Using Differentiable Force Closure Estimator
IEEE Robotics and Automation Letters 2022cited by 83position: contributordoi
In situ bidirectional human-robot value alignment
Science Robotics 2022cited by 72position: lastdoi
Scene Reconstruction with Functional Objects for Robot Autonomy
International Journal of Computer Vision 2022cited by 26position: contributordoi
Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry
IEEE Transactions on Pattern Analysis and Machine Intelligence 2022cited by 16position: contributordoi
Cascaded Parsing of Human-Object Interaction Recognition.
2022cited by 14position: contributordoi
In situ bidirectional human-robot value alignment.
2022cited by 11position: contributordoi
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
Lecture Notes in Computer Science 2022cited by 10position: contributordoi
Understanding Physical Effects for Effective Tool-Use
IEEE Robotics and Automation Letters 2022cited by 10position: contributordoi
Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaboration
IEEE Robotics and Automation Letters 2022cited by 7position: contributordoi
Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation.
2022cited by 4position: contributordoi
Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021cited by 189position: middledoi
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
2021cited by 94position: lastdoi
Hierarchical Human Semantic Parsing with Comprehensive Part-Relation Modeling
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 86position: lastdoi
CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models
iScience 2021cited by 58position: lastdoi
Interpretable CNNs for Object Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 56position: contributordoi
Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 44position: lastdoi
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
2021cited by 44position: middledoi
Extraction of an Explanatory Graph to Interpret a CNN
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 29position: contributordoi
Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 25position: contributordoi
A Generalized Earley Parser for Human Activity Parsing and Prediction
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 22position: contributordoi
Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021cited by 8position: contributordoi
Patching interpretable <scp>And‐Or‐Graph</scp> knowledge representation using augmented reality
Applied AI Letters 2021cited by 4position: contributordoi
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Engineering 2020cited by 119position: lastdoi
CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines
Proceedings of the AAAI Conference on Artificial Intelligence 2020cited by 65position: lastdoi
Interpretable CNNs for Object Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence 2020cited by 63position: lastdoi
LEMMA: A Multi-view Dataset for L Earning Multi-agent Multi-task Activities
Lecture Notes in Computer Science 2020cited by 27position: contributordoi
A Competence-Aware Curriculum for Visual Concepts Learning via Question Answering
Lecture Notes in Computer Science 2020cited by 13position: contributordoi
Introduction to Monte Carlo Methods
2020cited by 11position: lastdoi

Grants

RI: Small: Inferring the "Dark Matter" and "Dark Energy" from Image and Video
NSF1423305$454,4002014–2018PIRePORTER
CDI-Type II: Collaborative Research: Joint Image-Text Parsing and Reasoning for Analyzing Social and Political News Events
NSF1028381$1,299,9982010–2016PIRePORTER
RI: Small: Learning and Inference with And-Or Graphs for Image Understanding
NSF1018751$450,0002010–2015PIRePORTER
RI: Large Scale Object Recognition and Ground Truth Representation Using Stochastic Image Grammar
NSF0713652$459,6742007–2011PIRePORTER
US-China Workshop on Computer Vision
NSF0527138$33,0002005–2007PIRePORTER
Learning Fundamentals Atomic Image Structures From Natural Images, Video and Shapes
NSF0222967$340,0582002–2005PIRePORTER
CAREER: Stochastic Modeling and Computing of Visual Patterns: From Descriptive to Generative Methods
NSF0244763$274,2482002–2007PIRePORTER
CAREER: Stochastic Modeling and Computing of Visual Patterns: From Descriptive to Generative Methods
NSF0092664$130,1522001–2002PIRePORTER
Learning Probability Models for Surface Appearance and Shape by Minimax Entropy Principle
NSF9877127$368,6151999–2003PIRePORTER

Frequent collaborators

· 19 papers (2019–2024)Ying Wu · Guangdong Polytechnic of Science and Technology14 papers (2013–2023)Adrian Barbu · Florida State University13 papers (2020–2020)Wenguan Wang · Zhejiang Lab10 papers (2018–2022)Yixin Zhu · Peking University9 papers (2015–2022) · 9 papers (2019–2024)Siyuan Qi · Beijing Academy of Artificial Intelligence8 papers (2017–2021)Yibiao Zhao · The Thousand7 papers (2013–2016)Yuanlu Xu · Meta (United States)7 papers (2016–2021)Siniša Todorović · Oregon State University7 papers (2012–2021)Quanshi Zhang · Shanghai Jiao Tong University6 papers (2017–2020)Ping Wei · Machine Intelligence Research Institute5 papers (2013–2018)Jianwen Xie · Baidu (China)5 papers (2017–2021)Nanning Zheng · Xi'an Jiaotong University4 papers (2013–2018)Zilong Zheng · Qufu Normal University4 papers (2018–2022)Xiaobai Liu · San Diego State University4 papers (2016–2021)Dan Xie · Applied Materials (United States)4 papers (2012–2017)Hangxin Liu · Beijing Institute for General Artificial Intelligence (BIGAI)4 papers (2019–2022)Tianmin Shu · Johns Hopkins University4 papers (2015–2018)Baoxiong Jia · Beijing Academy of Artificial Intelligence3 papers (2018–2019)