In the field of body affect recognition, the majority of literature is based on experiments performed on datasets where trained actors simulate emotional reactions. These acted and unnatural expressions differ from the more challenging genuine emotions, thus leading to less valuable results. In this paper, a solution for basic non-acted emotion recognition based on 3D skeleton and Deep Neural Networks (DNNs) is provided. The proposed work introduces three majors contributions. First, temporal local movements performed by subjects are examined frame-by-frame, unlike the current state-of-the-art in non-acted body affect recognition where only static or global body features are considered. Second, an original set of global and time-dependent features for body movement description is provided. Third, this is one of the first works to use deep learning methods in the current non-acted body affect recognition literature. Due to the novelty of the topic, only the UCLIC dataset is currently considered the benchmark for comparative tests. On the latter, the proposed method outperforms all the competitors.

Deep Temporal Analysis for Non-Acted Body Affect Recognition / Avola, D.; Cinque, L.; Fagioli, A.; Foresti, G. L.; Massaroni, C.. - In: IEEE TRANSACTIONS ON AFFECTIVE COMPUTING. - ISSN 1949-3045. - (2022), pp. 1-12. [10.1109/TAFFC.2020.3003816]

Deep Temporal Analysis for Non-Acted Body Affect Recognition

Avola D.
Primo
;
Cinque L.;Fagioli A.;Foresti G. L.;Massaroni C.
2022

Abstract

In the field of body affect recognition, the majority of literature is based on experiments performed on datasets where trained actors simulate emotional reactions. These acted and unnatural expressions differ from the more challenging genuine emotions, thus leading to less valuable results. In this paper, a solution for basic non-acted emotion recognition based on 3D skeleton and Deep Neural Networks (DNNs) is provided. The proposed work introduces three majors contributions. First, temporal local movements performed by subjects are examined frame-by-frame, unlike the current state-of-the-art in non-acted body affect recognition where only static or global body features are considered. Second, an original set of global and time-dependent features for body movement description is provided. Third, this is one of the first works to use deep learning methods in the current non-acted body affect recognition literature. Due to the novelty of the topic, only the UCLIC dataset is currently considered the benchmark for comparative tests. On the latter, the proposed method outperforms all the competitors.
2022
3D skeleton; Automatic emotion recognition; Body movement; Deep learning; Long short-term memory (LSTM); Non-acted affective computing; Recurrent neural network (RNN)
01 Pubblicazione su rivista::01a Articolo in rivista
Deep Temporal Analysis for Non-Acted Body Affect Recognition / Avola, D.; Cinque, L.; Fagioli, A.; Foresti, G. L.; Massaroni, C.. - In: IEEE TRANSACTIONS ON AFFECTIVE COMPUTING. - ISSN 1949-3045. - (2022), pp. 1-12. [10.1109/TAFFC.2020.3003816]
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1619769
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 17
social impact