VALSE

VALSE 首页 活动通知 好文作者面授招 查看内容

20150722-22 谢凌曦:Image Classification and Retrieval are ONE

2015-7-19 21:02| 发布者: 彭玺ASTAR| 查看: 6337| 评论: 0

摘要: 【15-22期VALSE Webinar活动】报告嘉宾2:谢凌曦(清华大学)主持人:报告题目:Image Classification and Retrieval are ONE. 报告时间:2015年7月22日晚21:00(北京时间)文章信息: Lingxi Xie, Richang Hong, Bo Z ...

【15-22期VALSE Webinar活动】

报告嘉宾2:
 谢凌曦 (清华大学)
主持人:张兆翔(中科院自动化所)
报告题目:Image Classification and Retrieval are ONE. [Slides]
报告时间:2015年7月22日晚21:00(北京时间)
文章信息:
[1] Lingxi Xie, Richang Hong, Bo Zhang and Qi Tian, Image Classification and Retrieval are ONE, ICMR, Shanghai, China, June 23-26, 2015.
报告摘要: We demonstrate that the essentials of image classification and retrieval are the same, since both tasks could be tackled by measuring the similarity between images. To this end, we propose ONE (Online Nearest-neighbor Estimation), a unified algorithm for both image classification and retrieval. ONE is surprisingly simple, which only involves manual object definition, regional description and nearest-neighbor search. We take advantage of PCA and PQ approximation and GPU parallelization to scale our algorithm up to large-scale image search. Experimental results verify that ONE achieves state-of-the-art accuracy in a wide range of image classification and retrieval benchmarks.
报告人简介: Lingxi Xie received the B.E. degree from the Department of Computer Science and Technology, Tsinghua University, China, in 2010, and the Ph.D. degree in engineering from the same university, in 2015. He was a research intern in Microsoft Research Asia from August 2013 to January 2014, and from September 2014 to June 2015. He was a visiting researcher at the Department of Computer Science at the University of Texas at San Antonio (UTSA) from February to July 2014. His research interests include computer vision, multimedia information retrieval and machine learning.

最新评论

小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2021-1-25 22:45 , Processed in 0.013236 second(s), 15 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

返回顶部