报告题目:Large-scale Visual Search
时 间:2017年5月14日(周日)下午14:45
地 点:信息工程学院31-904
报告人简介:
Qi Tian is currently a Full Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA). Dr. Tian’s research interests include multimedia information retrieval, computer vision, pattern recognition and bioinformatics and published over 370 refereed journal and conference papers (including 88 IEEE/ACM Transactions papers and 67 CCF Category A conference papers). 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;并获得国家杰出青年资助(海外杰青)。之前他曾是清华大学神经与认知中心的讲席教授,中科院计算所客座研究员,中国科技大学,浙江大学,西安交通大学,西电大学,北京交通大学等客座教授。
讲座摘要:
Coupled with the massive social multimedia data and mobile visual search applications, techniques towards large-scale visual search and recognition are emerging. With the development of local invariant visual features and great success in deep learning, recent decade has witnessed the fast advance of large-scale image search. Current state-of-the-art image search algorithms and systems are motivated by the classic bag-of-visual-words model and the scalable index structure, and further powered by the deep learning techniques. Generally, an image search system is involved with several key modules, including feature representation, visual codebook construction, feature quantization, index strategy, and scoring scheme. Besides, post-processing techniques, such as geometric verification, query expansion and multi-modal fusion, can be plugged in to boost the retrieval performance.
In the first part of the talk, I will introduce those related works in each module as mentioned above and discuss the key research problems. In the second part, I will introduce our research work on large scale image search. We have done comprehensive work on feature representation, feature quantization, scalable indexing, spatial verification, et al. Several representative works (i.e., fast geometric verification, a novel co-indexing scheme, and codebook-training-free strategy, recent work in image retrieval with deep learning) will be discussed and the related demos will be shown. In the third part, I will discuss the potential research directions and promising applications on large scale image search.