Long time collaborators
  • David Mumford, doctoral dissertation advisor at Harvard in 1992-1996 and postdoc advisor at Brown 1996-1997.
  • Yingnian Wu, collaborator at Harvard and UCLA, 1994 -- now.
  • Harry Shum , collaborator at Microsoft Research Asia 1998-2008
  • Sinisa Todorovic, collaborator on Stochastic image grammar, 2009 -now
  • Mun Wai Lee, collaborator at IAI on text generation, NLP and query, 2006-now.
  • Adrian Barbu, collaborator at Florida State on Monte Carlo computing and learning 2006-now.
  • Tianfu Wu, Collaborator from LHI and UCLA on top-down/bottom-up scheduling and policy, 2006-now
  • Tae Eun Choi, collaborator at OV for scene understanding 2006-2015.
  • Francis Steen, collaborator at UCLA on communications and visual persuasion, 2010--now
  • Tim Groeling, collaborator at UCLA on political communications, 2010-now
  • Joyce Chai, collaborator at Michigan State on NLP and situated dialogues, 2013-now.
  • Michael Ryoo, collaborator at JPL on activity recognition and aerail video, 2013-now.
  • Li Cai and Girlie Delacruz, collaborators in education, 2014-now.
  • Pablo Garcia, collaborator at Stanford Research International (SRI) on robotics, 2014-2016.
People who I have shared grants with in the US:

    Adrian Barbu (FSU), Elias Bareinboim (Purdue), Terry Boult (UCCS), Joyce Chai (MSU), Stuart Geman (Brown), Pablo Garcia (SRI), Tim Groeling (UCLA), Abhinav Gupta (CMU), Martial Hebert (CMU), Derek Hoiem (UIUC), Nancy Kanwisher (MIT), Daphane Koller (Stanford), Feifei Li (Stanford), Jitendra Malik (UC Berkeley), Mike Miller (JHU), Judea Pearl (UCLA), Pietro Perona (Caltech), Deva Ramanan (UC Irvine), Brian Scholl (Yale), Francis Steen (UCLA), Josh Tenenbaum (MIT), Sinisa Todorovic (Oregon State), Antonio Torralba (MIT), Ying Wu (Norhtwestern), Yingnian Wu (UCLA), Alan Yuille (UCLA), Cheng Zhai (UIUC).

Ph.D. Students supervised in the US:
  • Zhuowen Tu, [CS] Ph.D. 2002, Image Parsing by Data-Driven Markov Chain Monte Carlo.
  • Cheng-En Guo, [CS] Ph.D. 2004, A Mathematical Theory for Texton and Primal Sketch.
  • Adrian Barbu, [CS] Ph.D. 2005, Cluster Sampling and Its Applications in Segmentation, Stereo and Motion
  • Yizhou Wang, [CS] Ph.D. 2005, Modeling Complex Motion: Photometric, Geometric, Topological, and Dynamic Aspects
  • Feng Han, [CS] Ph.D. 2005, Computing 3D Scene From A Single Image by Bottom-up/Top-Down Bayesian Inference
  • Romeo Maciuca, [Stat] Ph.D 2006, MCMC Analysis: First Hitting Times, Visiting Scheme, and Auxiliary Variables
  • Zijian Xu, [Stat] Ph.D 2007, A Hierarchical Compositional Model for Representation and Sketching of High-resolution Human Images
  • Kent Shi, [Stat] Ph.D 2009, Mapping Natural Image Patches by Explicit and Implicit Manifolds
  • Jacob Porway, [Stat] Ph.D 2010 A Hierarchical and Contextual Model for Learning and Recognizing Highly Variant Visual Categories
  • Zhangzhang Si [Stat] Ph.D 2011 Learning And-Or Templates for Object Recognition by Information Projection
  • Mingtian Zhao [Stat] Ph.D 2011 A Statistical and Computational theory for the Art of Painting
  • Tianfu Wu [Stat] Ph.D 2011 Integration and Goal-guided Scheduling of Bottom-up and Top-Down Computing Processes in Hierarchical Models
  • Benjamin Yao [Stat] Ph.D 2011 Learning Spatial-Temporal Models for Understanding Actions and Events in Video
  • Wenze Hu [Stat] Ph.D 2012 Integrating 3D and 2D Representations for View-invariant Object Recognition
  • Brandon Rothrock [CS] Ph.D 2013 Stochastic Image Grammars for Human Pose Estimation
  • Maria Pavlovskaia [Stat] Ph.D 2014 Mapping Highly Non-convex Energy Landscapes in Clustering, Grammar and Curriculum Learning
  • Jungseock Joo [CS] Ph.D 2015 Visual Persuasion in Mass Media: A Computational Framework for Understanding Visual Communication
  • Yibiao Zhao [Stat] Ph.D 2015 A Quest for Visual Commonsense: Scene Understanding by Functional and Physics Reasoning
  • Seyoung Park [CS] Ph.D 2016 Attribute Grammar for Joint Parsing of Human Attribute, Part and Pose
  • Amy Morrow [Stat] Ph.D 2016 Learning and Inferring Perceptual Causality from Videos
  • Dan Xie [Stat] Ph.D 2016 Inferring the Intentions and Attentions of Agents from Videos.
  • Weixin Li [CS] Ph.D 2017 Joint Image-Text Topic Detection and Tracking for Analyzing Social and Political News Events
  • Bruce Nie [Stat] on Human Actions Recognition and 3D Pose Reconstruction
  • Yang Lu [Stat] on Learning Multi-layer And-or Graph
  • Joey Chengcheng Yu [Stat] on Single View 3D Scene Reconstruction Using Visual Commonsense
  • Hang Qi [CS] on Joint Spatial, Temporal, and Causal Inference and Restricted Turng Test via Storyline Queries
  • Yixin Zhu [CS] on Tool Recognition, Utility Learning and Human-Robot Collaboration
  • Yuanlu Xu [CS] on Spatial and Temporal Reasoning for Understanding Scene and Event
  • Siyuan Qi [CS] on Robot Task Planning based on Scene Understanding
  • Nishant Shukla [CS] on Fluent Learning in Tasks and Semantic Grounding with Vision and Language
  • Tianmin Shu [Stat] on Social Affordance Learning and Robot-Human Collaboration
  • Yang Liu [Stat] on Task-Oriented Vision
  • Mitchell Hill [Stat] on Visualizing the Energy Landscape in Inference and Learning
  • Lifeng Fan [Stat] on Modeling and Learning Social Interactions and Social Norms
  • Arjun Akula [Stat] on Learning by Dialogues and Explainable AI
  • Ruiqi Gao [Stat] on Generative Learning
  • Hanlin Zhu [CS] on Semantic Grounding and Embedding in Vision-Language Learning
  • Siyuan Huang [Stat] on Joint Parsing for Scene Reconstruction and Understanding
  • Feng Shi [CS] on VPU Chips for Vision and Learning
  • Mark Edmond [CS] on Robotics Manipulations
Postdocs supervised in the US
  • Xiuwen Liu, Postdoc 1999-2000, Texture modeling and Julesz ensemble
  • Hong Chen, Postdoc 2003-2006, Human face, hair, and cloth modeling and sketching
  • Haifeng Gong, Postdoc 2007-2009, Intrackability: An information Theoretical Criterion for pursuing Hybrid Video Representations
  • Liang Lin, Postdoc 2007-2009, Layered Graph Matching
  • Mingtao Pei Research Associate 2009-2011, Event understanding and Intent Prediction in Video
  • Tianfu Wu Postdoc 2011-2014, Decision policy and learning and-or graph for object detection and tracking.
  • Bo Zheng Research Associate 2012-2013, 3D scene parsing by reasoning physical stability and risk
  • Kewei Tu Postdoc 2012-2014, Joint video and text parsing, query answering, and grammar learning
  • Xiaobai Liu Postdoc 2013-2015, Attributed grammar for scene understanding, camera calibration and 3D reconstruction
  • Caiming Xiong Postdoc 2014-2015, Robot Learning from demonstrations.
  • Wei Liang Research Associate, 2013-2015, Container recognition and causality inferrence
  • Quanshi Zhang Postdoc 2014-, Webscale lifelong Communicative Learning.
  • Ping Wei Postdoc 2015-, Inferring the Mind of Agents in Video: Belief, Intent, and Attention
  • Lei Qin Research Associate, 2016-2017, Spatial-temporal Reasoning for Event Understanding
  • Jianwen Xie Postdoc 2016-, Generative and Decriptive Models (Deep Networks) for Learning
  • Yi-Qing Wang Postdoc 2016-, Fundmental Limits of Learning
  • Changsong Liu Postdoc 2016-, Communicative Learning and Situated Dialogues
Visiting Ph.D students supervised in the US
  • Zhi Han (Xi'an JiaoTong University) Visiting Ph.D Student 2009-2011, Video Primal Sketch: A Middle Level Generic Representation of Video
  • Shuo Wang (Peking University) Visiting Ph.D Student 2011-2013, Scene Modeling and Recognition with Tangram Model
  • Ping Wei (Xi'an JiaoTong University) Visiting Ph.D Student 2011-2012, Modeling 4DHOI and Concurrent Action and Affordance
  • Jifeng Dai (TsingHua University) Visiting Ph.D Student 2012-2013, Unsupervised learning for co-segmentation and image parsing
  • Li Bo ( Beijing Institute of Technology) Visiting Ph.D Student 2014-2016, Modeling Occlusion for vehicle detection, parsing, and fluent reasoning.
  • Wenguan Wang ( Beijing Inst. of Tech.) Visiting Ph.D Student 2016-2018, Joint parsing of human poses, attributes and actions by QA learning
Students co-supervised in Lotus Hill Research Institute, China (partial list):
  • Lin Liang (Ph.D 2007 Beijing Institute of Technology);
  • Zeng Kun (Ph.D 2007 Institute of Automation, Chinese Academy of Science);
  • Peng Shaowu (Ph.D 2008 Huazhong University of Science and Technology)
  • Suo Jinli (Ph.D 2010 Institute of Computing, Chinese Academy of Science);
  • Yang Xiong (Ph.D 2010 Huazhong University of Science and Technology);
  • Zhao Youdong (Ph.D 2010 Beijing Institute of Technology);
  • Zhou Quan (Ph.D 2012 Huazhong University of Science and Technology);
  • Yang Cong (Ph.D 2012 Shenyang institute of Automation, Chinese Academy of Science);
  • Zhang Jiangen (Ph.D, 2012 Beijing Institute of Technology);
  • Zhu Jun (Ph.D, 2013 Shanghai JiaoTong University);
  • Xie Yi (Ph.D, 2013 Beijing Institute of Technology);
  • Song Xi (Ph.D, 2014 Beijing Institute of Technology);
© S.-C. Zhu