学　术

　　为加强我校各学科之间的学术交流，搭建教师学术交流平台，促进教师学术水平提升和跨学科合作，教师发展中心开展跨学科学术沙龙活动。

　　本次活动教师发展中心特别邀请了伦敦大学玛丽皇后学院朱霞天博士，与我校师生共同探讨Person Re-Identification by Discriminative Selection in Video Ranking。具体安排如下，欢迎感兴趣的师生参加。

　　一、主　题：Person Re-Identification by Discriminative Selection in Video Ranking　　

　　二、主讲人：伦敦大学玛丽皇后学院 朱霞天博士

　　三、时　间：1月8日（周五）下午14:00

　　四、地　点：清水河校区经管大楼宾诺咖啡

　　五、主持人：计算机科学与工程学院　叶茂教授

　　六、承办单位：计算机科学与工程学院

　　七、交流内容：

　　Current person re-identification (ReID) methods typically rely on single-frame imagery 　features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios. Single-frame (single-shot) based visual appearance matching is inherently limited for person ReID in public spaces due to the challenging visual ambiguity and uncertainty arising from non-overlapping camera views where viewing condition changes can cause significant people appearance variations. This talk will present our recent research work on video ranking for robust cross-view people identity matching. Specifically, we propose a novel model to automatically select the most discriminative video fragments from noisy/incomplete image sequences of people from which reliable space-time and appearance features can be computed, whilst simultaneously learning a video ranking function for person ReID. Using the PRID2011, iLIDS-VID, and HDA+ image sequence datasets, we extensively conducted comparative evaluations to demonstrate the advantages of the proposed model over contemporary gait recognition, holistic image sequence matching and state-of-the-art single-/multi-shot ReID methods.　　

　　八、主讲人简介：

　　Xiatian Zhu finished the PhD degree in computer vision from Queen Mary University of London in 2015, the Master and Bachelor degrees from University of Electronic Science and Technology of China (UESTC) in 2009 and 2006 respectively. He has been a research consultant on the EU SmartPrevent Project at Vision Semantics Limited. He graduated by an outstanding publication output at the highest level in computer vision, with 9 papers over 3.5 years including 3 major journal papers:

　　International Journal of Computer Vision (IJCV) paper (2015), IEEE Transactions NNLS paper (2015), and 1 IEEE Transactions PAMI paper under minor revision; 6 top-tier international conference papers: AAAI’16, ECCV’14, IEEE CVPR’14, IEEE ICCV’13, IEEE ICDM’13, BMVC’12. His PhD thesis has been nominated by the external examiners to enter the 2016 British Machine Vision Association Best PhD Thesis Competition (The Sullivan Doctoral Thesis Prize). He has also won many competitive research supporting grants including 2014 ECCV Student Travel Grant, 2013 IEEE PAMI-TC ICCV Student Travel Grant, 2013 BMVA International Conference Bursary, 2013 QMUL Post-graduate Research Fund. His research interests include person re-identification and video understanding in visual surveillance, multi-source data structure discovery, data clustering, and random forests.

　　欲参与本次沙龙的师生，请于1月7日（周四）16:00（限额30人，额满为止）前以邮件形式将本人相关信息（包括姓名、所在单位、移动电话、邮箱、研究方向）发送至cfd@uestc.edu.cn。

　　联系人：袁老师   电话：61830230

　　　　　　　　　　　　　　　　　　　　　　人力资源部教师发展中心

　　　　　　　　　　　　　　　　　　　　　　　　2016年1月6日