Audiovisual annotation procedure for multi-view field recordings - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Audiovisual annotation procedure for multi-view field recordings

Résumé

Audio and video parts of an audiovisual document interact to produce an audiovisual, or multi-modal, perception. Yet, automatic analysis on these documents are usually based on separate audio and video annotations. Regarding the audiovisual content, these annotations could be incomplete, or not relevant. Besides, the expanding possibilities of creating audiovisual documents lead to consider different kinds of contents, including videos filmed in uncontrolled conditions (i.e. fields recordings), or scenes filmed from different points of view (multi-view). In this paper we propose an original procedure to produce manual annotations in different contexts, including multi-modal and multi-view documents. This procedure, based on using both audio and video annotations, ensures consistency considering audio or video only, and provides additionally audiovisual information at a richer level. Finally, different applications are made possible when considering such annotated data. In particular, we present an example application in a network of recordings in which our annotations allow multi-source retrieval using mono or multi-modal queries.
Fichier principal
Vignette du fichier
guyot_24726.pdf (748.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03635046 , version 1 (08-04-2022)

Identifiants

  • HAL Id : hal-03635046 , version 1
  • OATAO : 24726

Citer

Patrice Guyot, Thierry Malon, Geoffrey Roman Jimenez, Sylvie Chambon, Vincent Charvillat, et al.. Audiovisual annotation procedure for multi-view field recordings. 25th International Conference on Multimedia Modeling (MMM 2019), Jan 2019, Thessaloniki, Greece. pp.399-410. ⟨hal-03635046⟩
16 Consultations
9 Téléchargements

Partager

Gmail Facebook X LinkedIn More