Temporal Matching Kernel with Explicit Feature Maps

Abstract : This paper proposes a framework for content-based video retrieval that addresses various tasks as particular event retrieval , copy detection or video synchronization. Given a video query, the method is able to efficiently retrieve, from a large collection, similar video events or near-duplicates with temporarily consistent excerpts. As a byproduct of the representation, it provides a precise temporal alignment of the query and the detected video excerpts. Our method converts a series of frame descriptors into a single visual-temporal descriptor, called a temporal invariant match kernel. This representation takes into account the relative positions of the visual frames: the frame descriptors are jointly encoded with their timestamps. When matching two videos, the method produces a score function for all possible relative timestamps, which is maximized to obtain both the similarity score and the relative time offset. Then, we propose two complementary contributions to further improve the detection and localization performance. The first is a novel query expansion method that takes advantage of the joint descriptor/timestamp representation to automatically align the first result set and produce an enriched temporal query. In contrast to other query expansion methods proposed for videos, it preserves the localization capability. Second, we improve the localization trade-off between quality and representation size by using several complementary temporal match kernels. We evaluate our approach on benchmarks for particular event retrieval, copy detection and video synchronization. Our experiments show that our approach achieve excellent detection and localization results.
Type de document :
Communication dans un congrès
ACM Multimedia 2018, Oct 2015, Brisbane, Australia. ACM Press, pp.1-10, 〈10.1145/2733373.2806228〉
Liste complète des métadonnées

Littérature citée [6 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01842277
Contributeur : Teddy Furon <>
Soumis le : mercredi 18 juillet 2018 - 10:05:37
Dernière modification le : jeudi 15 novembre 2018 - 11:59:01
Document(s) archivé(s) le : vendredi 19 octobre 2018 - 18:00:20

Fichier

p381-poullot.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Sébastien Poullot, Shunsuke Tsukatani, Anh Phuong Nguyen, Hervé Jégou, Shin'Ichi Satoh. Temporal Matching Kernel with Explicit Feature Maps. ACM Multimedia 2018, Oct 2015, Brisbane, Australia. ACM Press, pp.1-10, 〈10.1145/2733373.2806228〉. 〈hal-01842277〉

Partager

Métriques

Consultations de la notice

129

Téléchargements de fichiers

25