Fast Action Localization in Large-Scale Video Archives

Andrei Stoian 1 Marin Ferecatu 1 Jenny Benois-Pineau 2 Michel Crucianu 1
1 CEDRIC - Centre d'études et de recherche en informatique et communications
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
Abstract : Finding content in large video archives has so far required textual annotation to enable search by keywords. Our aim is to support retrieval from such archives using queries based on the example video clips that contain meaningful human actions. We propose a solution for the scalable search of actions in large-scale archives by leveraging the complementarity between the description at the frame level and the aggregation in time of descriptors. To permit fast search, we introduce a two-level cascade. The inexpensive first level employs aggregation to filter out a large part of the video. At the second level, aided by feature selection, a more discriminative comparison by frame alignment ranks the remaining video sequences. We improve upon the state of the art on popular data sets, and we introduce and show the results on a novel video archive data set that is significantly larger than previous ones.
Keywords : scalability Action localization cascade feature selection global alignment (GA)
Document type :
Journal articles
Complete list of metadatas
https://hal.archives-ouvertes.fr/hal-01436992
Contributor : Jenny Benois-Pineau <>
Submitted on : Monday, January 16, 2017 - 7:39:39 PM
Last modification on : Thursday, February 6, 2020 - 2:16:06 PM

Identifiers

Collections

CNRS | CNAM | UNIV-BORDEAUX | LABRI | UNIV-HESAM | CEDRIC-CNAM

Citation

Andrei Stoian, Marin Ferecatu, Jenny Benois-Pineau, Michel Crucianu. Fast Action Localization in Large-Scale Video Archives. IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2015, IEEE Transactions on Circuits and Systems for Video Technology, 26 (10), pp.1917 - 1930. ⟨10.1109/TCSVT.2015.2475835⟩. ⟨hal-01436992⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

177

Contact

Informations

CCSD