Event Detection with Zero Example : Select the Right and Suppress the Wrong Concepts

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

13 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationICMR '16 : Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval
PublisherACM New York
Pages127-134
ISBN (Print)978-1-4503-4359-6
Publication statusPublished - 6 Jun 2016

Conference

TitleACM International Conference on Multimedia Retrieval
PlaceUnited States
Period6 - 9 June 2016

Abstract

Complex video event detection without visual examples is a very challenging issue in multimedia retrieval. We present a state-of-the-art framework for event search without any need of exemplar videos and textual metadata in search corpus. To perform event search given only query words, the core of our framework is a large, pre-built bank of concept detectors which can understand the content of a video in the perspective of object, scene, action and activity concepts. Leveraging such knowledge can effectively narrow the semantic gap between textual query and the visual content of videos. Besides the large concept bank, this paper focuses on two challenges that largely affect the retrieval performance when the size of the concept bank increases: (1) How to choose the right concepts in the concept bank to accurately represent the query; (2) if noisy concepts are inevitably chosen, how to minimize their influence. We share our novel insights on these particular problems, which paves the way for a practical system that achieves the best performance in NIST TRECVID 2015.

Research Area(s)

  • Multimedia Event Detection, Video Search, 0Ex, Concept Selection, Semantic Pooling, Concept Bank

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Event Detection with Zero Example : Select the Right and Suppress the Wrong Concepts. / Lu, Yi-Jie; Zhang, Hao; de Boer, Maaike; Ngo, Chong-Wah.

ICMR '16 : Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval . ACM New York, 2016. p. 127-134.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review