Skip to main navigation Skip to search Skip to main content

Learning Guided Attention Masks for Facial Action Unit Recognition

  • SUNY Buffalo

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

4 Scopus citations

Abstract

Humans have the innate ability to rapidly spot and react to a person's emotional response. For computers to be able to understand expressions in a similar way, the gap between the perception of expressions between the humans and computers needs to be minimized. Inspired by human visual fixations, we propose a guided attention mechanism that facilitates the network to 'look' at the most important features of a face. Rather than imposing hard attention, we learn the attention maps from the intermediate representation for Action Units (AUs). We propose a joint attention learning and AU classification module with minimal increase in the network parameters. We demonstrate the efficiency of our approach on three standard datasets: BP4D, MMSE and DISFA and obtain state of the art and near state of the art results respectively.

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.
Pages465-472
Number of pages8
ISBN (Electronic)9781728130798
DOIs
StatePublished - Nov 2020
Event15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020 - Buenos Aires, Argentina
Duration: Nov 16 2020Nov 20 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
Period11/16/2011/20/20

Keywords

  • affective computing
  • Facial action unit recognition
  • spatial attention

Fingerprint

Dive into the research topics of 'Learning Guided Attention Masks for Facial Action Unit Recognition'. Together they form a unique fingerprint.

Cite this