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

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00906327
Contributor : Guillaume Gravier <>
Submitted on : Tuesday, November 19, 2013 - 3:24:31 PM
Last modification on : Friday, November 16, 2018 - 1:27:12 AM
Long-term archiving on : Thursday, February 20, 2014 - 9:27:32 AM

File

ISM2013SVAP_v2.3.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00906327, version 1

Citation

Leonardo de Oliveira, Zenilton Kleber Do Patrocínio Jr., Silvio Jamil 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⟩

Share

Metrics

Record views

1244

Files downloads

218