A Multi-Modal Approach for Driver Gaze Prediction to Remove Identity Bias

Zehui Yu, Xiehe Huang, Xiubao Zhang, Haifeng Shen, Qun Li, Weihong Deng, Jian Tang, Yi Yang, Jieping Ye

Research output: Chapter in Book/Entry/PoemConference contribution

8 Scopus citations

Abstract

Driver gaze prediction is an important task in Advanced Driver Assistance System (ADAS). Although the Convolutional Neural Network (CNN) can greatly improve the recognition ability, there are still several unsolved problems due to the challenge of illumination, pose and camera placement. To solve these difficulties, we propose an effective multi-model fusion method for driver gaze estimation. Rich appearance representations, i.e. holistic and eyes regions, and geometric representations, i.e. landmarks and Delaunay angles, are separately learned to predict the gaze, followed by a score-level fusion system. Moreover, pseudo-3D appearance supervision and identity-adaptive geometric normalization are proposed to further enhance the prediction accuracy. Finally, the proposed method achieves state-of-the-art accuracy of 82.5288% on the test data, which ranks 1st at the EmotiW2020 driver gaze prediction sub-challenge.

Original languageEnglish (US)
Title of host publicationICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction
PublisherAssociation for Computing Machinery, Inc
Pages768-776
Number of pages9
ISBN (Electronic)9781450375818
DOIs
StatePublished - Oct 21 2020
Externally publishedYes
Event22nd ACM International Conference on Multimodal Interaction, ICMI 2020 - Virtual, Online, Netherlands
Duration: Oct 25 2020Oct 29 2020

Publication series

NameICMI 2020 - Proceedings of the 2020 International Conference on Multimodal Interaction

Conference

Conference22nd ACM International Conference on Multimodal Interaction, ICMI 2020
Country/TerritoryNetherlands
CityVirtual, Online
Period10/25/2010/29/20

Keywords

  • appearance representation
  • driver gaze prediction
  • geometric representation
  • identity bias
  • model fusion

ASJC Scopus subject areas

  • Hardware and Architecture
  • Human-Computer Interaction
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'A Multi-Modal Approach for Driver Gaze Prediction to Remove Identity Bias'. Together they form a unique fingerprint.

Cite this