加入收藏夹
联系我们
关于本站
个人主页
西电导航
西安电子科技大学
    当前位置:首页>>学术讲座
Person Re-identification: Benchmarks and Our Solutions
时间:2017-07-12 11:59    点击:   所属单位:电子工程学院
讲座名称 Person Re-identification: Benchmarks and Our Solutions
讲座时间 2017-07-16 09:30:00
讲座地点 老校区主楼III区430
讲座人 Prof. Qi Tian
讲座人介绍
Qi Tian is currently a Full Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA). He was a tenured Associate Professor from 2008-2012 and a tenure-track Assistant Professor from 2002-2008. During 2008-2009, he took one-year Faculty Leave at Microsoft Research Asia (MSRA) as Lead Researcher in the Media Computing Group. 
Dr. Tian received his Ph.D. in ECE from University of Illinois at Urbana-Champaign (UIUC) in 2002 and received his B.E. in Electronic Engineering from Tsinghua University in 1992 and M.S. in ECE from Drexel University in 1996, respectively. Dr. Tian’s research interests include multimedia information retrieval, computer vision, pattern recognition and bioinformatics and published over 380 refereed journal and conference papers (including 90 IEEE/ACM Transactions papers and 67 CCF Category A conference papers). He was the co-author of a Best Paper in ACM ICMR 2015, a Best Paper in PCM 2013, a Best Paper in MMM 2013, a Best Paper in ACM ICIMCS 2012, a Top 10% Paper Award in MMSP 2011, a Best Student Paper in ICASSP 2006, and co-author of a Best Student Paper Candidate in ICME 2015, and a Best Paper Candidate in PCM 2007.
Dr. Tian research projects are funded by ARO, NSF, DHS, Google, FXPAL, NEC, SALSI, CIAS, Akiira Media Systems, HP, Blippar and UTSA. He received 2017 UTSA President’s Distinguished Award for Research Achievement, 2016 UTSA Innovation Award, 2014 Research Achievement Awards from College of Science, UTSA, 2010 Google Faculty Award, and 2010 ACM Service Award. He is the associate editor of IEEE Transactions on Multimedia (TMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Multimedia System Journal (MMSJ), and in the Editorial Board of Journal of Multimedia (JMM) and Journal of Machine Vision and Applications (MVA).  Dr. Tian is the Guest Editor of IEEE Transactions on Multimedia, Journal of Computer Vision and Image Understanding, etc. 
Dr. Tian is a Fellow of IEEE. 田奇教授被评为2016年多媒体领域最有影响力的Top 10学者之一(by Aminer.org)。 田奇教授也是教育部长江讲座教授和中科院海外评审专家, 
URL: http://www.cs.utsa.edu/~qitian
Email: qi.tian@utsa.edu
 
讲座内容
Person re-identification (re-id) is a promising way towards automatic video surveillance. As research hotspot in recent years, there has been an urgent demand for building a solid benchmarking framework, including comprehensive datasets and effective baselines. 
To benchmark a large scale person re-id dataset, we propose a new high quality frame-based dataset for person re-identification titled “Market-1501”, which contains over 32,000 annotated bounding boxes, plus a distractor set of over 500K images. Different from traditional datasets which use hand-drawn bounding boxes that are unavailable under realistic settings, we produce the dataset with Deformable Part Model (DPM) as pedestrian detector. Moreover, this dataset is collected in an open system, where each identity has multiple images under each camera. We propose an unsupervised Bag-of-Words representation and treat the person re-identification as a special task of image search, which is demonstrated very efficient and effective.
To further push the person re-identification to practical applications, we propose a new video based dataset titled “MARS”, which is the largest video re-id dataset to date. Containing 1,261 identities and over 20,000 tracklets, it provides rich visual information compared to image-based datasets. The tracklets are automatically generated by the DPM as pedestrian detector and the GMMCP tracker. Extensive evaluation of the state-of-the-art methods including the space-time descriptors are presented. We further show that CNN in classification mode can be trained from scratch using the consecutive bounding boxes of each identity.
Finally, we present “Person Re-identification in the Wild (PRW)” dataset for evaluating end-to-end re-id methods from raw video frames to the identification results. We address the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification. A discriminatively trained ID-discriminative Embedding (IDE) in the person subspace using convolutional neural network (CNN) features and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement are introduced to aid the identification.
 
转载请注明出处:西安电子科技大学学术信息网
如果您有学术信息或学术动态,欢迎投稿。我们将在第一时间确认并收录,投稿邮箱: meeting@xidian.edu.cn
Copyright © 2011-2017 西安电子科技大学 
开发维护:电子工程学院网络信息中心  管理员:meeting@xidian.edu.cn 站长统计: