Event retrieval in large video collections with circulant temporal encoding

Jérôme Revaud 1 Matthijs Douze 1 Cordelia Schmid 1 Hervé Jégou 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper presents an approach for large-scale event retrieval. Given a video clip of a specific event, e.g., the wedding of Prince William and Kate Middleton, the goal is to retrieve other videos representing the same event from a dataset of over 100k videos. Our approach encodes the frame descriptors of a video to jointly represent their appearance and temporal order. It exploits the properties of circulant matrices to compare the videos in the frequency domain. This offers a significant gain in complexity and accurately localizes the matching parts of videos. Furthermore, we extend product quantization to complex vectors in order to compress our descriptors, and to compare them in the compressed domain. Our method outperforms the state of the art both in search quality and query time on two large-scale video benchmarks for copy detection, Trecvid and CCweb. Finally, we introduce a challenging dataset for event retrieval, EVVE, and report the performance on this dataset.
Type de document :
Communication dans un congrès
CVPR 2013 - International Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. IEEE, pp.2459-2466, 2013, 〈10.1109/CVPR.2013.318〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00801714
Contributeur : Hervé Jégou <>
Soumis le : lundi 18 mars 2013 - 16:59:11
Dernière modification le : mercredi 16 mai 2018 - 11:23:05
Document(s) archivé(s) le : dimanche 2 avril 2017 - 14:09:27

Fichiers

revaud_event.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Jérôme Revaud, Matthijs Douze, Cordelia Schmid, Hervé Jégou. Event retrieval in large video collections with circulant temporal encoding. CVPR 2013 - International Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. IEEE, pp.2459-2466, 2013, 〈10.1109/CVPR.2013.318〉. 〈hal-00801714〉

Partager

Métriques

Consultations de la notice

4627

Téléchargements de fichiers

5297