BENet: A lightweight bottom-up framework for context-aware emotion recognition - Université Jean-Monnet-Saint-Étienne Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

BENet: A lightweight bottom-up framework for context-aware emotion recognition

Tristan Cladière
  • Fonction : Auteur
  • PersonId : 1279817
Olivier Alata
Christophe Ducottet
Hubert Konik
  • Fonction : Auteur
  • PersonId : 837648
Anne Claire Legrand
  • Fonction : Auteur
  • PersonId : 850061

Résumé

Emotion recognition from images is a challenging task. The latest and most common approach to solve this problem is to fuse information from different contexts, such as person-centric features, scene features, object features, interactions features and so on. This requires specialized pre-trained models, and multiple pre-processing steps, resulting in long and complex frameworks, not always practicable in real time scenario with limited resources. Moreover, these methods do not deal with person detection, and treat each subject sequentially, which is even slower for scenes with many people. Therefore, we propose a new approach, based on a single end-to-end trainable architecture that can both detect and process all subjects simultaneously by creating emotion maps. We also introduce a new multitask training protocol which enhances the model predictions. Finally, we present a new baseline for emotion recognition on EMOTIC dataset, which considers the detection of the agents. Our code is available at https://github.com/TristanCladiere/BENet.git.
Fichier principal
Vignette du fichier
ACIVS_23_final.pdf (1.9 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

ujm-04194014 , version 1 (01-09-2023)

Identifiants

  • HAL Id : ujm-04194014 , version 1

Citer

Tristan Cladière, Olivier Alata, Christophe Ducottet, Hubert Konik, Anne Claire Legrand. BENet: A lightweight bottom-up framework for context-aware emotion recognition. ACIVS 2023 (Advanced Concepts for Intelligent Vision Systems), Aug 2023, Kumamoto, Japan. ⟨ujm-04194014⟩
81 Consultations
66 Téléchargements

Partager

Gmail Facebook X LinkedIn More