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

TL;DR

This paper introduces a transformer-based model with a novel global-local correlation module for egocentric gaze estimation, significantly improving accuracy by explicitly modeling the relationship between scene context and local visual cues.

Contribution

The paper presents the first transformer model for egocentric gaze estimation, incorporating a global-local correlation module to enhance gaze prediction accuracy.

Findings

Outperforms previous state-of-the-art methods on EGTEA Gaze+ and Ego4D datasets.

Demonstrates the effectiveness of global-local correlation in gaze estimation.

Provides detailed ablation studies validating the proposed approach.

Abstract

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).