Searching for near-duplicate video sequences from a scalable sequence aligner

Leonardo S. de Oliveira (1) , Zenilton Kleber G. Do Patrocínio Jr. (1) , Silvio Jamil F. Guimarães (1) , Guillaume Gravier (2)

1 VIPLAB - Audio-visual Information Processing Lab [Sao Gabriel]
2 TEXMEX - Multimedia content-based indexing

Near-duplicate video sequence identification consists in identifying real positions of a specific video clip in a video stream stored in a database. To address this problem, we propose a new approach based on a scalable sequence aligner borrowed from proteomics. Sequence alignment is performed on symbolic representations of features extracted from the input videos, based on an algorithm originally applied to bio-informatics. Experimental results demonstrate that our method performance achieved 94% recall with 100% precision, with an average searching time of about 1 second.

Domaines: Multimédia [cs.MM]

Leonardo S. de Oliveira, Zenilton Kleber G. Do Patrocínio Jr., Silvio Jamil F. Guimarães, Guillaume Gravier. Searching for near-duplicate video sequences from a scalable sequence aligner. IEEE International Symposium on Multimedia, 2013, United States. pp.4. ⟨hal-00906327⟩