Some Invited Talks
- Keynote at CVPR Workshop on Causality in Vision, June, 2021.
Perceptual Causality:Learning and Inferring Causality from Visual Observations and Interactions
- Keynote at China3D Vision Symposium, June, 2021.
Task-oriented 3D Scene Understanding
- Keynote at CICAI CAAI International Conference on AI, June, 2021.
Explainable AI: How Machines Gain Justified Human Trust
- Keynote at ACL Asia, December, 2020
Explainable AI: How Machines Gain Justified Human Trust
- Keynote at Beijing Academy of AI, October, 2019.
Towards General AI: From "Big Data" to "Big Task"
- Keynote at World AI Conference, Shanghai, August, 2019
Dark, Beyond Deep: a Paradigm Shift in AI Research
- Keynote at CVPR Workshop on Explainable AI, Long Beach, CA, June 2019
Explainable AI: How Machines Gain Justified Trust from Humans
- Openning Speech at CVPR Workshop on 3D Scene Understanding, Long Beach ,CA, June 2019
Some Thoughts and Principles for 3D Scene Understanding
- Keynote at CVPR Workshop on vision Meets Cognition, Long Beach ,CA, June 2019
VR Platforms for Training and Evaluating Autonomous Agents: Small-Data for Big-Tasks
- Keynote at ACM TURC Conference, Chengdu, May, 2019
Artificial Intelligence: The Era of Big Integration
- Keynote at Tsinghua AI Summit, Sanya Math Forum, March, 2019
Explainable AI: How Machines Gain Justified Trust from Humans
- Lecture at the Symposium Honoring David Mumford, CMSA, Harvard University, August, 2018
Artificial Intelligence: The Era of Big Integration
- Lecture at the Rama Chellapa 65 Birthday Symposium, June, 2018
Building a "telescope" to Look Into Very High-Dimensional Image Universe
- Distinguished Lecture at Hongkong PolyU, June, 2018
Artificial Intelligence: The Era of Big Integration
- Keynote at Int'l Conf. on Image Processing, Beijing, September, 2017
A Tale of Three Probabilistic Families: Descriptive, Generative and Discriminative Models [ppt slides]
- Symposium at NLPR, Beijing,September, 2017
Dark, Beyond Deep: A Paradigm Shift for Computer Vision
- Workshop on Human-Machine Interaction, Beijing,September, 2017
A Conitive Architecture for Human-Machine Teaming.
- Keynote at Int'l Workshop on Vision Meets Cognition, at CVPR, Hawaii, June, 2017.
Dark, Beyond Deep
- Invited Talk at the Int'l Workshop on Vision and Language, at CVPR, Hawaii, June, 2017.
Vision + Language: Why and How
- Invited Talk at Microsoft Faculty Summit, Seattle, June 2017.
Dark, Beyond Deep
- Invited Talk at Hongkong Chinese University, June, 2017.
Dark, Beyond Deep
- Invited Talk at SNAP Inc. April, 2017.
Advanced Topics in Vision and AI Research
- Special Workshop for Zhu and associates, Microsoft Research Asia, September, 2016.
A Cognitive Architecture for Human-Robot Teaming
- Computer Science Coloquium, Princeton University, Nov. 2015.
A Cognitive Architecture for Human-Robot Collaborations based on Spatial, Temporal and Causal And-Or Graph.
- Keynote
at the AI symposium on Human-Robot Interactions, Nov. 2015.
A Cognitive Architecture for Human-Robot Collaborations based on Spatial, Temporal and Causal And-Or Graph.
- CVPR workshop on Vision Meets Cognition : Function, Physics, Intent and Causality, June 2015.
Rethink Vision from the Perspective of an Agent: Task-centered Representation, inference and learning.
[ppt slides]
- CVPR workshop on Language and Vision , June. 2015.
Joint Video-Text Parsing for Understanding Scenes and events and Query Answering
[ppt slides]
-
CogSci Workshop on Physical and Social Scene Understanding, July 2015.
Understanding Scenes and Events by Reasoning Physics and Causality.
- Distinguished Lecture series, Dept. of Computer Sceience and Engineering, UCSD, Nov. 2014.
Scene Understanding by Reasoning Functionality, Physics, Intents and Causality.
- National Cheng Kung University, Taiwan, September 2014.
Understanding Scenes and Events by Joint Spatial, Temporal, and Causal Inference
- Academia Sinica, Taiwan, September, 2014
Lecture 1: Pursuing a Unified Statistical Model for Regimes of Image Patterns.
Lecture 2: Understanding Scenes and Events by Joint Spatial, Temporal, and Causal Inference
- National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Science, July 2014
Beyond What and Where: Reasoning Function, Physics, Intent and Causality [ppt_slides]
- Institute of AI and Robotics, Xi'an Jiaotong University, July 2014
Beyond What and Where: Reasoning Function, Physics, Intent and Causality
-
CVPR workshop on Vision Meets Cognition: Function, Physics, Intent and Causality, June 2014
Beyond What and Where: Spatial, Temporal and Causal Parsing with Commonsense Knowledge
- Stanford Workshop on AI and Knowledge, April, 2014.
Understanding Video and Text by Joint Spatial, Temporal, and Causal Inference [ppt_slides]
- UC Berkeley Vision Seminar, April, 2014.
Beyond What and Where: Joint Video-Text Inference with Commonsense Reasoning
- Computer Science and Engineering Department Distinguished Speaker series, SUNY Buffalo, Feb. 2014.
Understanding Video and Text by Joint Spatial, Temporal, and Causal Inference
- Center for Image Science, Johns Hopkins University, Feb. 2014.
Pursuing a Unified Representsation and Model of Visual Knowledge
- Scene Understanding workshop at CVPR, June 2013
Scene Understanding by Inferring the "Dark Matters": Physics, Funcationality, Causality and Minds [ppt_slides]
- Third Conference of Tsinghua Sanya International Mathematics Forum, Jan, 2013
Stochastic Sets and Regimes of Mathematical Models of Images [ppt slides]
- Seminar at Peking University, August, 2012
Understanding images and Video by joint Spatial, Temporal and Causal Inference
- Beijing Int'l Summer School on Vision, Cognition and Learning, August, 2012
Lecture 1: Object and scene representation and parsing [ppt slides]
Lecture 2: Event parsing and inferring agent’s intents and goals [ppt slides]
Lecture 3: Open problems and challenges in vision, learning and cognition [ppt slides]
- Tutorial at the Stochastic Image Grammar (SiG), June, 2012
Lecture 1: Spatial AND-OR graph for representing the scene-object-part-primitive hierarchy [ppt slides]
Lecture 2: Causal AND-OR graphs (C-AOG) for representing the causal-action recursion for reasoning [ppt slides]
Lecture 3: Information projection for learning S-AOG, T-AOG, C-AOG [ppt slides]
- UC Riverside EE Colloqium, January, 2012
Learning Visual Knowledge by Information Projection [ppt_slides]
- UC LA CS seminar, May, 2012
Spatial, temporal, and Causal Inference for Understabding Image and Video
- NSF Workshop on Frontier of Vision, August, 2011.
Lecture 1: Hack, Math, and Stat [ppt slides ]
Lecture 2: Visual Conceptualization by Stochastic Sets [ppt slides ]
- IPAM Summer School on Probabilistic Models of Cognition, July, 2011.
Lecture 1: Learning And-Or Graph Representations for Objects and Events
Lecture 2: Top-down/Bottom-up Inference in And-Or graphs
- Microsoft Research Asia, August 2010
The Joy of Ambiguities in Vision and Visual Arts [ppt_slides]
- Seminar at the Redwood Center for Theoretical Neuroscience at UC Berkeley on November 12, 2009
Information Scaling and Perceptual Transitions in Natural Images and Video [ppt_slides]
- Beijing Summer School on Vision, Learning, and Pattern Recognition, July 2009,
Lecture 1: Pursuing Manifolds in the Universe of Images [pdf]
Lecture 2: Inference in And-Or Graphs [pdf]
- The J.K. Aggarwal Lecture, a plenary speech at the ICPR08, Dec.10, 2008,
Pursuing Implicit and Explicit Manifolds by Information projection [
pdf ]
- Plenary Speech at the Chinese Conference on Pattern Recognition, Oct. Beijing,
- Psychology Workshop on Natural Environments Tasks and Intelligence, March, 2008, UT Austin,
Information Scaling and Manifolds Learning in Natural Images and Video
- Computer Vision Distinguished Speaker Series, Univ. of Central Florida, March, 2008,
Visual Learning and Conceptualization: pursuing manifolds in the universe of images.
- NIPS workshop on the Grammar of Vision, Dec. 2007, Van Couver, Canada,
Object Category by Stochastic Grammar
- Object Video Seminar, Nov. 2007,
Object Recognition in Natural and Aerial Images
- Int'l Workshop on Object Categorization, Oct. 2007, Rio, Brazil.
Object Category Modeling, Learning, and Recognition by Stochastic Grammar [pdf]
- MIT Vision Symposium, May, 2007, Cambridge, MA.
Object Category Modeling, Learning, and Recognition by Stochastic Grammar. [pdf]
- Symposium on the Mathematics of Perception, June, 2007. Newport, RI.
Quest for a Stochastic Grammar of Images. [pdf]
- Chinese Academy of Science, Institute of Computing Seminar, Mar. 2007, Beijing.
Computer Vision and High Performance Computing. [pdf]
- ChangJiang Scholar Lectureship, Huazhong University of Science and Technology, Mar. 2007,
Foundation and Trend in Computer Vision. [pdf]
- Workshop on Texture and Natural Image Processing, Jan. 2007, Paris, France.
Texture, Texton and Primal Sketch: Integrating MRF and Wavelets [pdf]
- International Symposium on Vision by Brains and Machines, Nov. 2006, MonteVideo, Uruguay.
Visual Learning with Implicit and Explicit Manifolds [pdf]
- Dragon Star Lecture Series, July 2006,
Modeling, Learning, and Conceptualizing Visual Patterns.
- Int'l Workshop on Semantic Learning, June 2006,
Knowledge Representation and Learning Schemes for Large Object Categories [pdf]
- IMA workshop on Visual Learning and Recognition, May 2006,
Advocate for Generative Models. [pdf]
- Neyman seminar, Berkeley Statistics Department, April 2005,
Cluster Sampling and Data-Driven Markov Chain Monte Carlo [pdf]
- Math Science Research Institute, Berkeley, Workshop on Visual Recognition, Mar. 2005,
Context Sensitive Graph Grammar and Top-down/Bottom-up Inference[pdf]
- Math Science Research Institute, Berkeley, Workshop on Low-Middle level Vision, Feb. 2005,
From Primal Sketch to 2 1/2 D Sketch [pdf]
- Math Science Research Institute, Berkeley, Workshop on Introduction to Vision Jan. 2005,
Seeing as Statistical Inference [pdf]
- IPAM workshop on Multiscale Geometric Analysis, 2004
From Scaling Laws of Natural Images to Regimes of Image Models [pdf]
- GRC on Sensory Coding and the Natural Environments, 2004
- Technical Univ. of Denmark, 2003 [pdf]
- Int'l Workshop
on High-Level Knowledge in 3D Modeling and Motion Analysis 2003 [pdf]
- Inti'l
Workshop on Object Recognition 2003
Visual
Inference by Markov Chain Monte Carlo Methods [pdf]
- University of South California, 2003
- A talk to the Psychology Dept. at UCLA, "A
Math Theory for Texture, Texton, Primal Sketch and Gestalt Fields"
[pdf]
- Los Alamos National
Lab, 2002 [Talk1.pdf], [Talk2.pdf],
[Talk3.pdf]
- Robotics
institute, Carnegie Mellon University, 2002
- 1st Cape
Cod workshop on Monte Carlo Methods, 2002
- 2nd Int'l
workshop on Texture, 2002
- Interface meeting 2002
- Kodak research lab., 2001.
- Microsoft Research Beijing, 2001.
- Univ. of California, Los Angeles, 2001.
- 1st Bayes
Vision Workshop, San. Francisco, 2001
- The
Abdus Salum International Centre for Theoretical Physics, Italy, (Teaching
Short Courses), 2000.
- Institute for Mathematics
and its Applications, 2000.
- Microsoft Research, Beijing, 2000.
- Pattern Theory Seminar, Brown University, 2000.
- AI seminar, Carnegie
Mellon University, 2000.
- Workshop
on Generic Object Recognition, Corfu, Greece, 1999.
- School of Mathematics,
Georgia Institute of Technology, 1999.
- Brown University, 1999.
- University of Chicago, 1999.
- Centre Int'l
De Recontres Math, Marseille, FRANCE. 1998.
- Institute of Henri Poincare, Paris, France. 1998.
- Inria at Antipolis, FRANCE. 1998.