报告题目： Person Re-identification: Benchmarks and Our Solutions

报告人： 田奇 教授

单位：美国德州大学圣安东尼奥分校

报告时间： 2016年8月13日下午15:00-16:30

报告地点： 屯溪路校区逸夫科教楼408会议室

报告摘要： 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.

报告人简介：

田奇博士于1992年在清华大学获学士学位，于2002年在美国伊利诺伊大学香槟城分校(UIUC)获得博士学位。田博士曾在微软亚洲研究院媒体计算组工作，任职首席研究员。田博士现为美国德州大学圣安东尼奥分校计算机系正教授。

田博士在美国ARO、NSF、DHS、Google、NEC、HP等科研项目支持下，在多媒体信息检索、计算机视觉、模式识别、生物信息学等领域开展了广泛深入的研究，在国内外学术期刊和会议上发表论文超过320篇，取得了重要的学术进展和广泛的同行关注，获得了ICMR、ICME、PCM、MMM、ICIMCS、ICASSP等国际著名学术会议最佳论文/最佳学生论文奖。

田奇博士是国际著名学术期刊IEEE T-MM、T-CSVT、MMSJ、MVA的副主编或编委会成员，亦担任过IEEE T-MM、CVIU等著名学术期刊客座主编之职。田博士于2010年获ACM学会学术服务奖，2014年获国家基金委海外杰青，2016年当选IEEE Fellow。

百富策略bfball手机版