Deep Pain : Exploiting Long Short-Term Memory Networks for Facial Expression Classification
Rodríguez López, Pau (Universitat Autònoma de Barcelona)
Cucurull, Guillem (Centre de Visió per Computador)
Gonzàlez, Jordi (Centre de Visió per Computador)
Gonfaus, Josep M. (Centre de Visió per Computador)
Nasrollahi, Kamal (Aalborg Universitet)
Moeslund, Thomas B. (Aalborg Universitet)
Roca, F. Xavier (Universitat Autònoma de Barcelona)

Fecha:	2022
Resumen:	Pain is an unpleasant feeling that has been shown to be an important factor for the recovery of patients. Since this is costly in human resources and difficult to do objectively, there is the need for automatic systems to measure it. In this paper, contrary to current state-of-the-art techniques in pain assessment, which are based on facial features only, we suggest that the performance can be enhanced by feeding the raw frames to deep learning models, outperforming the latest state-of-the-art results while also directly facing the problem of imbalanced data. As a baseline, our approach first uses convolutional neural networks (CNNs) to learn facial features from VGG_Faces, which are then linked to a long short-term memory to exploit the temporal relation between video frames. We further compare the performances of using the so popular schema based on the canonically normalized appearance versus taking into account the whole image. As a result, we outperform current state-of-the-art area under the curve performance in the UNBC-McMaster Shoulder Pain Expression Archive Database. In addition, to evaluate the generalization properties of our proposed methodology on facial motion recognition, we also report competitive results in the Cohn Kanade+ facial expression database.
Ayudas:	Ministerio de Economía y Competitividad TIN2015-65464-R Generalitat de Catalunya 2016/FI_B-01163
Nota:	This work was support in part by the COST Action IC1307 iV&L Net (European Network on Integrating Vision and Language) through COST (European Cooperation in Science and Technology).
Derechos:	Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió acceptada per publicar
Materia:	Affective computing ; Computer applications ; Cybercare industry applications ; Human factors engineering in medicine and biology ; Medical services ; Monitoring ; Patient monitoring computers and information processing ; Pattern recognition
Publicado en:	IEEE Transactions on Cybernetics (Q1:Human-Computer Interaction), Vol. 52, Num. 5 (May 2022) , p. 3314-3324, ISSN 2168-2275

DOI: 10.1109/TCYB.2017.2662199

Postprint 13 p, 2.3 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados