20180110-1 周文罡：Pseudo-supervised Deep Learning for Image Search

报告嘉宾：周文罡（中国科学技术大学）

报告时间：2018年01月10日（星期三）晚20:00（北京时间）

报告题目：Pseudo-supervised Deep Learning for Image Search

主持人：王楠楠（西安电子科技大学）

报告摘要：

Recent years has witnessed the great success of deep learning in a variety of vision tasks. In most cases, deep learning is conducted in a supervised way. As for image search, since the category number of potential objects is difficult to enumerate, it is infeasible to collect the expected training data for training data devoted to image search. As a result, most works on image search simply leverage the activations from pre-trained deep learning model. To this end, we explore deep learning in a pseudo-supervised paradigm and orient it for image retrieval. We approach it from different perspectives and propose three algorithms. Experiments demonstrate the effectiveness and potential of pseudo-supervised deep learning in retrieval task.

报告相关文献列表：

[1] Wengang Zhou, Houqiang Li, Jian Sun, and Qi Tian, “Collaborative Index Embedding for Image Retrieval,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Feb. 2017.

[2] Min Wang, Wengang Zhou, Qi Tian, and Houqiang Li, “A General Framework for Linear Distance Preserving Hashing,” IEEE Transactions on Image Processing (TIP), vol. 27, no. 2, pp. 907-922, Aug. 2017.

[3] Min Wang, Wengang Zhou, Qi Tian, Zheng-jun Zha, and Houqiang Li, "Linear Distance Preserving Pseudo-Supervised and Unsupervised Hashing," ACM International Conference on Multimedia (MM), pp. 1257-1266, long paper, 1257-1266, 2016.

报告人简介：

Dr. Wengang Zhou received his PhD degree in the Department of Electronic Engineering and Information Science (EEIS), University of Science and Technology of China (USTC) in 2011. He is currently an associate professor in USTC. Before that, he worked as a post-doctorate researcher in the Computer Science Department, University of Texas at San Antonio (UTSA). His research interests include multimedia content analysis & retrieval and computer vision. He has published over 80 research papers in journals including IEEE T-PAMI, IEEE T-IP, and IEEE T-MM, and in conferences including IEEE CVPR and ACM Multimedia. He is the recipient of the Best Paper award in the ACM ICMICS 2012, the Excellent Doctoral Dissertation Award of Chinese Academy of Science in 2013, and the Young Elite Scientists Sponsorship Program by CAST 2016. He severs as the reviewer for IEEE T-PAMI, IEEE T-IP, IEEE T-CSVT, IEEE T-MM, CVPR, ACM MM, ICCV, ECCV, etc.

讲者个人主页：http://staff.ustc.edu.cn/~zhwg/index.html

特别鸣谢本次Webinar主要组织者：

VOOC责任委员：王楠楠（西安电子科技大学）

VODB协调理事：王乃岩（北京图森未来科技有限公司）

活动参与方式：

1、VALSE Webinar活动全部网上依托VALSE QQ群的“群视频”功能在线进行，活动时讲者会上传PPT或共享屏幕，听众可以看到Slides，听到讲者的语音，并通过文字或语音与讲者交互；

2、为参加活动，需加入VALSE QQ群，目前A、B、C、D、E、F群已满，除讲者等嘉宾外，只能申请加入VALSE G群，群号：669280237。申请加入时需验证姓名、单位和身份，缺一不可。入群后，请实名，姓名身份单位。身份：学校及科研单位人员T；企业研发I；博士D；硕士M

3、为参加活动，请下载安装Windows QQ最新版，群视频不支持非Windows的系统，如Mac，Linux等，手机QQ可以听语音，但不能看视频slides；

4、在活动开始前10分钟左右，主持人会开启群视频，并发送邀请各群群友加入的链接，参加者直接点击进入即可；

5、活动过程中，请勿送花、棒棒糖等道具，也不要说无关话语，以免影响活动正常进行；

6、活动过程中，如出现听不到或看不到视频等问题，建议退出再重新进入，一般都能解决问题；

7、建议务必在速度较快的网络上参加活动，优先采用有线网络连接。

[slides]