Skip to main navigation Skip to search Skip to main content

Clip-based similarity measure for hierarchical video retrieval

Yuxin Peng, Chong-Wah Ngo

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

This paper proposes a new approach and algorithm for the similarity measure of video clips. The similarity is mainly based on two bipartite graph matching algorithms: maximum matching (MM) and optimal matching (OM). MM is able to rapidly filter irrelevant video clips, while OM is capable of ranking the similarity of clips according to the visual and granularity factors. Based on MM and OM, a hierarchical video retrieval framework is constructed for the approximate matching of video clips. To allow the matching between a query and a long video, an online clip segmentation algorithm is also proposed to rapidly locate candidate clips for similarity measure. The validity of the retrieval framework is theoretically proved and empirically verified on a video database of 21 hours. Copyright 2004 ACM.
Original languageEnglish
Title of host publicationMIR'04 - Proceedings of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval
PublisherAssociation for Computing Machinery
Pages53-60
ISBN (Print)9781581139402
DOIs
Publication statusPublished - Oct 2004
Event6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR'04) - New York, NY, United States
Duration: 15 Oct 200416 Oct 2004

Conference

Conference6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR'04)
PlaceUnited States
CityNew York, NY
Period15/10/0416/10/04

Research Keywords

  • Clip-based similarity
  • Hierarchical video retrieval

Fingerprint

Dive into the research topics of 'Clip-based similarity measure for hierarchical video retrieval'. Together they form a unique fingerprint.

Cite this