Latent-Based Adversarial Neural Networks for Facial Affect Estimations

Decky Aspandi, Adria Mallol-Ragolta, Bjorn Schuller, Xavier Binefa

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

There is a growing interest in affective computing research nowadays given its crucial role in bridging humans with computers. This progress has recently been accelerated due to the emergence of bigger dataset. One recent advance in this field is the use of adversarial learning to improve model learning through augmented samples. However, the use of latent features, which is feasible through adversarial learning, is not largely explored, yet. This technique may also improve the performance of affective models, as analogously demonstrated in related fields, such as computer vision. To expand this analysis, in this work, we explore the use of latent features through our proposed adversarial-based networks for valence and arousal recognition in the wild. Specifically, our models operate by aggregating several modalities to our discriminator, which is further conditioned to the extracted latent features by the generator. Our experiments on the recently released SEWA dataset suggest the progressive improvements of our results. Finally, we show our competitive results on the Affective Behavior Analysis in-the-Wild (ABAW) challenge dataset.

Original languageEnglish
Title of host publicationProceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020
EditorsVitomir Struc, Francisco Gomez-Fernandez
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages606-610
Number of pages5
ISBN (Electronic)9781728130798
DOIs
StatePublished - Nov 2020
Externally publishedYes
Event15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020 - Buenos Aires, Argentina
Duration: 16 Nov 202020 Nov 2020

Publication series

NameProceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020

Conference

Conference15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020
Country/TerritoryArgentina
CityBuenos Aires
Period16/11/2020/11/20

Keywords

  • Adversarial Networks
  • Affective Computing
  • Latent Representation

Fingerprint

Dive into the research topics of 'Latent-Based Adversarial Neural Networks for Facial Affect Estimations'. Together they form a unique fingerprint.

Cite this