Multimodal First Impression Analysis with Deep Residual Networks

Abstract : People form first impressions about the personalities of unfamiliar individuals even after very brief interactions with them. In this study we present and evaluate several models that mimic this automatic social behavior. Specifically, we present several models trained on a large dataset of short YouTube video blog posts for predicting apparent Big Five personality traits of people and whether they seem suitable to be recommended to a job interview. Along with presenting our audiovisual approach and results that won the third place in the ChaLearn First Impressions Challenge, we investigate modeling in different modalities including audio only, visual only, language only, audiovisual, and combination of audiovisual and language. Our results demonstrate that the best performance could be obtained using a fusion of all data modalities.
Liste complète des métadonnées

https://hal.inria.fr/hal-01668375
Contributeur : Isabelle Guyon <>
Soumis le : mercredi 20 décembre 2017 - 08:04:56
Dernière modification le : jeudi 5 avril 2018 - 12:30:26

Identifiants

Citation

Yağmur Güçlütürk, Umut Güçlü, Xavier Baró, Hugo Jair Escalante, Isabelle Guyon, et al.. Multimodal First Impression Analysis with Deep Residual Networks. IEEE Transactions on Affective Computing, 2017, PP (99), pp.1-14. 〈10.1109/TAFFC.2017.2751469〉. 〈hal-01668375〉

Partager

Métriques

Consultations de la notice

137