Recognizing Emotions from Video in a Continuous 2D Space

Abstract : This paper proposes an effective system for continuous facial affect recognition from videos. The system operates in a continuous 2D emotional space, characterized by evaluation and activation factors. It makes use, for each video frame, of a classification method able to output the exact location (2D point coordinates) of a still facial image in that space. It also exploits the Kalman filtering technique to control the 2D point movement along the affective space over time and to improve the robustness of the method by predicting its future locations in cases of temporal facial occlusions or inaccurate tracking.
Type de document :
Communication dans un congrès
Pedro Campos; Nicholas Graham; Joaquim Jorge; Nuno Nunes; Philippe Palanque; Marco Winckler. 13th International Conference on Human-Computer Interaction (INTERACT), Sep 2011, Lisbon, Portugal. Springer, Lecture Notes in Computer Science, LNCS-6949 (Part IV), pp.600-603, 2011, Human-Computer Interaction – INTERACT 2011. 〈10.1007/978-3-642-23768-3_92〉
Liste complète des métadonnées

Littérature citée [5 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01596928
Contributeur : Hal Ifip <>
Soumis le : jeudi 28 septembre 2017 - 10:20:01
Dernière modification le : mardi 10 octobre 2017 - 13:32:29
Document(s) archivé(s) le : vendredi 29 décembre 2017 - 14:02:49

Fichier

978-3-642-23768-3_92_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Sergio Ballano, Isabelle Hupont, Eva Cerezo, Sandra Baldassarri. Recognizing Emotions from Video in a Continuous 2D Space. Pedro Campos; Nicholas Graham; Joaquim Jorge; Nuno Nunes; Philippe Palanque; Marco Winckler. 13th International Conference on Human-Computer Interaction (INTERACT), Sep 2011, Lisbon, Portugal. Springer, Lecture Notes in Computer Science, LNCS-6949 (Part IV), pp.600-603, 2011, Human-Computer Interaction – INTERACT 2011. 〈10.1007/978-3-642-23768-3_92〉. 〈hal-01596928〉

Partager

Métriques

Consultations de la notice

32

Téléchargements de fichiers

9