Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2013

Abstract

Instance Search (INS) is a realistic problem initiated by TRECVID, which is to retrieve all occurrences of the querying object, location, or person from a large video collection. It is a fundamental problem with many applications, and also a challenging problem different from the traditional concept or near-duplicate (ND) search, since the relevancy is defined at instance level. True responses could exhibit various visual variations, such as being small on the image with different background, or showing a non-homography spatial configuration. Based on the Bag-of-Words model, we propose two techniques tailored for Instance Search. Specifically, we explore the use of (1) an elastic spatial topology checking technique based on Delaunay Triangulation (DT), and (2) a practical background context modeling method by simulating the “stare” behavior of human eyes. With DT, we improve the quality of visual matching by accumulating evidence from local topology-preserving patches, significantly boosting the ranks of topology consistent results. On the other hand, we increase the information quantity for visual matching with the“stare”model, such that instances appearing in both similar and different background can be highly ranked as results. The proposed techniques are evaluated on the INS datasets of TRECVID, achieving large performance gain with small computation overhead, compared with several existing methods.

Keywords

context modeling, instance search, spatial topology checking, TRECVID

Discipline

Data Storage Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 3rd ACM International Conference on Multimedia Retrieval, ICMR 2013, Dallas, Texas, April 16-20

First Page

57

Last Page

64

ISBN

9781450320337

Identifier

10.1145/2461466.2461477

Publisher

ACM

City or Country

Dallas, Texas

Download

Share

COinS