Advanced Lecture Series in Pattern Recognition
题 目 (TITLE)：Large-scale Visual Search
讲 座 人 (SPEAKER)：Prof. Tian Qi (University of Texas at San Antonio)
主 持 人 (CHAIR)：Dr. Cheng Jian
时 间 (TIME)：August 13(Wednesday), 2014, 14:00 PM
地 点 (VENUE)：No.2 Conference Room (3rd floor), Intelligence Building
With the emergence of massive social multimedia data and prevalence of mobile visual search applications, techniques towards large-scale visual search and recognition are desired. Recent decade has witnessed the fast advance of large-scale image search, thanks to introduction of bag-of-visual-words model based on local invariant features and the scalable index structure. Generally, an image search system is involved with several key modules, including feature extraction, visual codebook learning, feature quantization, index strategy, scoring scheme, and post processing. 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 make an overview of large-scale visual search and discuss two milestones. In the second part, I will figure out four key problems on visual feature representation, feature quantization, image indexing, and post-processing in the framework of image search. To address those problems, we have conducted comprehensive work. I will introduce our recent representative works and show the related demos. On feature representation, we have developed a set of binary features, including USB, COGE, etc, and designed a new regional feature. On feature quantization, I will introduce our work on codebook learning and efficient quantization. On image indexing, a series of our recently proposed indexing schemes will be introduced, such as cross-index, coupled multi-index, super-image index, cascade category-aware index. Last but not least, on post-processing, I will introduce our work on geometric verification and query expansion. In the third part, I will make a summarization and discuss the potential applications.
Qi Tian is currently a Full Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA). During 2008-2009, he took one-year Faculty Leave at Microsoft Research Asia (MSRA) in the Media Computing Group. He received his Ph.D. in ECE from University of Illinois at Urbana-Champaign (UIUC) in 2002 and his B.E and M.S degrees from Tsinghua University and Drexel University in 1992 and 1996, respectively, all from electronic engineering. Dr. Tian’s research interests focus on multimedia information retrieval and computer vision and published over 240 refereed journal and conference papers. He received the Best Paper Award in PCM 2013, ACM ICIMCS 2012 and MMM 2013, a Top 10% Paper Award in MMSP 2011, the Best Student Paper Award in ICASSP 2006, and was a co-author of a Best Paper Candidate in PCM 2007. His research projects are funded by NSF, ARO, DHS, Google, FXPAL, NEC, SALSI, CIAS, Akiira Media Systems, HP and UTSA. He received 2010 ACM Service Award. He is the Guest Editors of IEEE Transactions on Multimedia, Journal of Computer Vision and Image Understanding, etc, and is the Associate Editor of IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) and in the Editorial Board of Journal of Multimedia (JMM) and Journal of Machine Vision and Applications (MVA). He is the Guest or Adjunct Professor in Institute of Computing Technology, Chinese Academy of Science, Xi’an Jiaotong University, USTC, Zhejing University, Xidian University and a Chaired Professor in Tsinghua University.