In the Eye of Transformer: Global–Local Correlation for Egocentric Gaze Estimation and Beyond

Bolin Lai, Miao Liu, Fiona Ryan, James M. Rehg

Research output: Contribution to journalArticlepeer-review

Abstract

Predicting human’s gaze from egocentric videos serves as a critical role for human intention understanding in daily activities. In this paper, we present the first transformer-based model to address the challenging problem of egocentric gaze estimation. We observe that the connection between the global scene context and local visual information is vital for localizing the gaze fixation from egocentric video frames. To this end, we design the transformer encoder to embed the global context as one additional visual token and further propose a novel global–local correlation module to explicitly model the correlation of the global token and each local token. We validate our model on two egocentric video datasets – EGTEA Gaze + and Ego4D. Our detailed ablation studies demonstrate the benefits of our method. In addition, our approach exceeds the previous state-of-the-art model by a large margin. We also apply our model to a novel gaze saccade/fixation prediction task and the traditional action recognition problem. The consistent gains suggest the strong generalization capability of our model. We also provide additional visualizations to support our claim that global–local correlation serves a key representation for predicting gaze fixation from egocentric videos. More details can be found in our website (https://bolinlai.github.io/GLC-EgoGazeEst).

Original languageEnglish (US)
Pages (from-to)854-871
Number of pages18
JournalInternational Journal of Computer Vision
Volume132
Issue number3
DOIs
StatePublished - Mar 2024
Externally publishedYes

Keywords

  • Egocentric gaze estimation
  • Global–local correlation
  • Vision transformer

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'In the Eye of Transformer: Global–Local Correlation for Egocentric Gaze Estimation and Beyond'. Together they form a unique fingerprint.

Cite this