Multimedia retrieval is a problem of finding the data points from a database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this talk, we first present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multi-wise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. Then, we present our recent work on hashing and quantization.
Jingkuan Song is a full professor with University of Electronic Science and Technology of China (UESTC). He received his Ph.D. degree in Computer Science from The University of Queensland in 2014. He has worked as Postdoctoral Research Fellow at Columbia University and University of Trento. His research interests include large-scale multimedia retrieval， image/video segmentation and image/video annotation using hashing, graph learning and deep learning techniques. He was the winner of the Best Paper Award in ICPR 2016, Best Student Paper Award in ADC 2017 and Best Paper Honorable Mention Award in SIGIR 2017.
宋井宽，第十四批国家“青年千人”计划拟入选者，电子科技大学“校百人”计划获得者，电子科技大学计算机科学与工程学院教授，分别于2016年和2014年在美国哥伦比亚大学和意大利特伦托大学从事博士后研究。其研究方向覆盖多媒体、计算机视觉、深度学习等。近五年发表学术论文70余篇，包括ACM Multimedia, CVPR, ICCV, ECCV, SIGMOD, SIGIR, TPAMI, TIP, TKDE，TMM等在内的国际顶级会议（CCF A类）和期刊。多次任职国际SCI期刊（客座）编委，多次担任国际会议的程序委员会委员，以及多个国际顶级期刊的审稿人。获得ICPR 2016 最佳论文奖、ADC 2017最佳学生论文奖及SIGIR 2017最佳论文Honorable Mention奖等。