In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Bolin, Liu, Miao, Ryan, Fiona, Rehg, James M.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913547752046592
author Lai, Bolin
Liu, Miao
Ryan, Fiona
Rehg, James M.
author_facet Lai, Bolin
Liu, Miao
Ryan, Fiona
Rehg, James M.
contents 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 (GLC) 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 previous state-of-the-arts by a large margin. 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).
format Preprint
id arxiv_https___arxiv_org_abs_2208_04464
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
Lai, Bolin
Liu, Miao
Ryan, Fiona
Rehg, James M.
Computer Vision and Pattern Recognition
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 (GLC) 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 previous state-of-the-arts by a large margin. 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).
title In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2208.04464