报告题目：Towards More Robust Person Re-identification with Group Consistency and Background-bias Elimination
报告人：李鸿升(Research Assistant Professor, CUHK-Sense Time Joint Laboratory at the Chinese University of Hong Kong)
In this talk, I will introduce three of our latest CVPR'18 papers on person re-identification. Similarity learning is vital for person re-identification. Benefited from deep neural networks (DNN), current approaches can learn accurate similarity metrics and robust feature embeddings. However, most of them impose only local constraints for supervision. In the first part of my talk, I will introduce incorporating constraints on large image groups for similarity learning by combining the CRFs with deep neural networks. The proposed method aims to learn more robust visual similarity metrics for image pairs while taking into account the dependencies from all the images in the group. Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities. In the second part of my talk, I will introduce the background-bias problem in existing person re-ID datasets and algorithms. Existing deep learning models are biased to capture too much relevance between background appearances of person images. We for the first time identify this problem and proposed an online-background augmentation scheme and a person-region guided pooling deep neural network to solve this problem. Experiments demonstrate the robustness and effectiveness of our proposed algorithm.
Hongsheng Li is currently a research assistant professor in the CUHK-Sense Time Joint Laboratory at the Chinese University of Hong Kong. He received the bachelor degree in automation from East China University of Science and Technology, and the master and doctorate degrees in computer science from Lehigh University, United States, in 2006, 2010, and 2012, respectively. From 2013-2015, he was an associate professor in the School of Electronic Engineering at University of Electronic Science and Technology of China. He has published over 30 papers in top computer vision conferences, CVPR/ICCV/ECCV. He won the first place in Object Detection from Videos (VID) task of Image Net 2016 challenge as a team leader. His research interests include computer vision, machine learning, and medical image analysis.