Skip to main navigation Skip to search Skip to main content

Facial Action Unit Recognition with Micro-Action-Aware Transformer

  • Yichen Yuan
  • , Yifan Cheng
  • , Zhiwen Shao*
  • , Qianwen Dang
  • , Rui Chen
  • , Mingjian Fu
  • , Shengtian Jiang
  • , Chunyu Li
  • , Lizhuang Ma*
  • *Corresponding author for this work
  • China University of Mining and Technology
  • Ministry of Education of the People's Republic of China
  • Shanghai Jiao Tong University

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

Abstract

Facial action unit (AU) recognition is a challenging task, due to the subtlety of each AU and the correlations among AUs in global face. However, the learning of local-global features has not been thoroughly exploited in most of the existing methods. In this paper, we propose a novel micro-action-aware transformer to integrate local and global feature extractions, which effectively captures subtle AU details while maintaining the global relational modeling capacity of transformers. Besides, we jointly train facial AU recognition and facial landmark detection, in which the two correlated tasks contribute to each other and further facilitate the learning of local-global AU-related feature. Extensive experiments demonstrate that our approach achieves comparable performance to the state-of-the-art AU recognition methods on the challenging BP4D and GFT benchmarks, and works well for landmark detection. Particularly, our approach achieves average F1 score results of 63.3% and 55.8% on BP4D and GFT datasets, respectively.

Original languageEnglish
Title of host publicationEmotional Intelligence - Second CSIG Conference, CEI 2024, Proceedings
EditorsXiaohua Huang, Qirong Mao
PublisherSpringer Science and Business Media Deutschland GmbH
Pages71-84
Number of pages14
ISBN (Print)9789819650835
DOIs
StatePublished - 2025
Externally publishedYes
Event2nd CSIG Conference on Emotional Intelligence, CEI 2024 - Nanjing, China
Duration: 6 Dec 20248 Dec 2024

Publication series

NameCommunications in Computer and Information Science
Volume2450 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference2nd CSIG Conference on Emotional Intelligence, CEI 2024
Country/TerritoryChina
CityNanjing
Period6/12/248/12/24

Keywords

  • facial action unit recognition
  • facial landmark detection
  • Micro-action-aware transformer

Fingerprint

Dive into the research topics of 'Facial Action Unit Recognition with Micro-Action-Aware Transformer'. Together they form a unique fingerprint.

Cite this