The impact of global and local features on multiple sequence alignment clustering-based near-duplicate video retrieval

Yandan Wang, Guojun Lu, Mohammed Belkhatir, Christopher H. Messom

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Traditionally, the performance of Near-Duplicate Video Retrieval (NDVR) is enhanced through different video features, matching scheme and indexing methods. The video features have been intensively investigated and it has been shown that local features outperform global features in terms of accuracy. However, local features have the expensive computational problem. Therefore, indexing structure is introduced to assist in scaling up, whilst the accuracy will drop slightly or dramatically in most time by using indexing approaches. Recent progress shows that NDVR based on clustering could reduce searching space while maintains equivalent retrieval accuracy compared to that of non-clustering based. In this paper, we will continue to evaluate clustering based NDVR, but using popular global and local features. Before conducting NDVR, dataset will be pre-processed offline into groups by using clustering algorithm that near-duplicate videos (NDVs) are assembled in the same cluster. Each cluster will be represented by member video or the centroid. The query video will then be compared to the representative videos instead of all videos in database (non-clustering based). Our experiment shows that clustering-based NDVR using global and local features outperforms than that of non-clustering based in terms of both retrieval accuracy and speed.
Original languageEnglish
Title of host publicationAdvances in Multimedia Information Processing - PCM 2013
Subtitle of host publication14th Pacific-Rim Conference on Multimedia, Nanjing, China, December 13-16, 2013, Proceedings
EditorsBenoit Huet, Chong-Wah Ngo, Jinhui Tang, Zhi-Hua Zhou, Alexander G. Hauptmann, Shuicheng Yan
Place of PublicationCham [Switzerland]
PublisherSpringer
Pages669 - 677
Number of pages9
ISBN (Electronic)9783319037318
ISBN (Print)9783319037301
DOIs
Publication statusPublished - 2013
EventPacific-Rim Conference on Multimedia 2013 - Nanjing, China
Duration: 13 Dec 201316 Dec 2013
Conference number: 14th
https://link.springer.com/book/10.1007/978-3-319-03731-8 (Conference Proceedings)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume8294
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferencePacific-Rim Conference on Multimedia 2013
Abbreviated titlePCM 2013
Country/TerritoryChina
CityNanjing
Period13/12/1316/12/13
Internet address

Keywords

  • Clustering
  • Near-duplicate video retrieval
  • Visual words

Cite this