- International Symposium on Non-Photorealistic Animation and Rendering, France, Jun, 2010
Topic: From Video Content Extraction to Painterly Animation [Demo01] [Demo02] [Demo03] [Demo04] [Demo05]
- Advanced Digital Science Center, Singapore, Oct., 2011
Topic: Key Advances in Image and Video Parsing
- School of Electrical and Computer Engineering at Carnegie Mellon University, U.S., Jun., 2012
Topic: Latent Structured Learning with Non-Convex Optimization
- ACM International Conference on Multimedia, Spain, Oct., 2013
Topic: Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition [Slides] [Demo]
- Microsoft eScience Workshop 2013, Beijing, Oct., 2013
Topic: Distributed Learning Systems for Large-Scale Object Detection [Slides]
- VALSE: Vision And Learning Seminar, China, April, 2014
Topic: Inference and Learning with Grammar Models for Visual Recognition [Slides]
- IEEE International Conference on Multimedia and Expo, China, July, 2014
Topic: Sparse Representation Learning for Data Driven Parsing
- ACM International Conference on Multimedia, U.S., Oct., 2014
Topic: Deep Structured Models for Human Activity Recognition [Slides]
- ACM Multimedia Tutorial (Half-Day), Australia, Oct., 2015
Topic: Human-centric Images and Videos Analysis [Slides]
- IEEE International Conference on Computer Vision, Chile, Dec., 2015
Topic: Contextualized Convolutional Neural Network for Human Parsing [Slides]
- Asian Conference on Machine Learning, Hong Kong, Nov., 2015
Topic: Deep Similarity Learning for Person Verification
- IEEE Computer Vision and Pattern Recognition, United States, Jun., 2016
Topic: Deep Structured Scene Parsing by Learning with Image Descriptions [Slides]
- ACM Turing 50th Celebration Conference – China, May, 2017
Topic: Beyond Supervised Deep Learning for Visual Understanding [Slides]