Multimodal Learning for Detecting Stress under Missing Modalities - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Multimodal Learning for Detecting Stress under Missing Modalities

Résumé

Dealing with missing modalities is critical for many real-life applications. In this work, we propose a scalable framework for detecting stress induced by specific triggers in multimodal data with missing modalities. Our method has two key components: (i) aligning all modalities in the space of the strongest modality (the video) for learning a joint embedding space and (ii) a Masked Multimodal Transformer, leveraging inter- and intra-modality correlations while handling missing modalities. We validate our method through experiments on the StressID dataset, where we set the new state of the art while demonstrating its robustness across various modality scenarios and its high potential for real-life applications.
Fichier principal
Vignette du fichier
WiCV___camera_ready (3).pdf (429.69 Ko) Télécharger le fichier
thumbnail.gif (2.81 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04635922 , version 1 (04-07-2024)

Licence

Identifiants

  • HAL Id : hal-04635922 , version 1

Citer

Julie Mordacq, Leo Milecki, Maria Vakalopoulou, Steve Oudot, Vicky Kalogeiton. Multimodal Learning for Detecting Stress under Missing Modalities. WiCV 2024 - Women in Computer Vision workshop In conjunction with CVPR, Jun 2024, Seattle, United States. ⟨hal-04635922⟩
203 Consultations
113 Téléchargements

Partager

More