MGTR: End-to-End Mutual Gaze Detection with Transformer

TL;DR

MGTR introduces an end-to-end transformer-based framework for mutual gaze detection, improving speed and maintaining accuracy by jointly detecting heads and inferring gaze relationships in a single process.

Contribution

The paper presents a novel one-stage transformer-based approach for mutual gaze detection, streamlining the process and enhancing efficiency over traditional two-stage methods.

Findings

Accelerates mutual gaze detection without performance loss

Effectively captures semantic information at multiple levels

Demonstrates superior speed and accuracy on benchmark datasets

Abstract

People's looking at each other or mutual gaze is ubiquitous in our daily interactions, and detecting mutual gaze is of great significance for understanding human social scenes. Current mutual gaze detection methods focus on two-stage methods, whose inference speed is limited by the two-stage pipeline and the performance in the second stage is affected by the first one. In this paper, we propose a novel one-stage mutual gaze detection framework called Mutual Gaze TRansformer or MGTR to perform mutual gaze detection in an end-to-end manner. By designing mutual gaze instance triples, MGTR can detect each human head bounding box and simultaneously infer mutual gaze relationship based on global image information, which streamlines the whole process with simplicity. Experimental results on two mutual gaze datasets show that our method is able to accelerate mutual gaze detection process without losing performance. Ablation study shows that different components of MGTR can capture different levels of semantic information in images. Code is available at https://github.com/Gmbition/MGTR