[SFC15] Fast action localization in large scale video archives

Revue Internationale avec comité de lecture : Journal IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 26(10), pp. 1917-1930, 2015, (doi:10.1109/TCSVT.2015.2475835)

Mots clés: action localization, detector cascade, global alignment, scalability, feature selection

Résumé: 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 example video clips which 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 results on a novel video archive data set that is significantly larger than previous ones.

Equipe: vertigo
Collaboration: LaBRI


@article {
title="{Fast action localization in large scale video archives}",
author="A. Stoian and M. Ferecatu and M. Crucianu and J. Benois-Pineau",
journal="IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)",