Lecture Series in Intelligent Perception and Computing
题 目 （TITLE）： Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing
讲 座 人 （SPEAKER）: Jian Zhao, Assistant Professor, Chinese Academy of Military Science
主 持 人 (CHAIR)： Ran He
时 间 (TIME)：16:00pm, August 29 (Thursday), 2019
地 点 (VENUE)： 1610 Meeting Room,16 Floor, Intelligent Building
Though great progresses have been made in recent years, the performance of human-centric image analysis in real-world scenarios is still far from being satisfactory. In this talk, we systematically investigate the problem of human-centric analysis based on deep learning, from face recognition for exploring the identity information to human parsing for exploring the fine-grained semantic information. We start by designing pose-invariant face recognition approaches, which aim to address unconstrained face recognition with large/extreme pose variations. Thereafter, we propose age-invariant face recognition algorithms, which elegantly learn disentangled facial representations and photorealistic cross-age faces to solve cross-age face recognition. To enable more detailed human-centric analysis, we then introduce a novel strategy for instance-agnostic human parsing. Finally, we propose a novel nested adversarial learning strategy to address the challenging instance-level human parsing (multi-human parsing), and construct a new large-scale and fine-grained benchmark dataset to further push the research frontier of human-centric image analysis and crowded scene understanding.
Dr. Jian Zhao is currently an Assistant Professor with Chinese Academy of Military Science, Beijing, China. Dr. Jian Zhao received his Ph.D. degree from National University of Singapore (NUS) in 2019 under the supervision of Assist. Prof. Jiashi Feng, Assoc. Prof. Shuicheng Yan, and Prof. Hengzhu Liu. He has published cutting-edge papers on unconstrained/large-scale/low-shot face verification/identification and human parsing as the first author (including NIPS, CVPR, ECCV, IJCAI, AAAI, ACM MM; T-PAMI, IJCV). He has won the Lee Hwee Kuan Award (Gold Award) on PREMIA 2019 as the first author. He has won the “Best Student Paper Award” on ACM MM 2018 as the first author. He has won the top-3 awards several times on world-wide competitions on face recognition, human parsing and pose estimation as the first author. His main research interests include deep learning, pattern recognition, computer vision and multimedia. In particular, his research is focused on developing deep neural network models and algorithms for human-centric image understanding, applied to facial analytics, image generation, super resolution, model compression, and human parsing.