LAEO-Net++: revisiting people Looking At Each Other in videos

TL;DR

LAEO-Net++ is a deep learning model that detects mutual gaze between people in videos by analyzing spatio-temporal tracks, introducing new datasets, and outperforming previous methods in accuracy.

Contribution

The paper presents LAEO-Net++, a novel CNN architecture that reasons about entire tracks for LAEO detection, along with two new datasets and applications to social relationship inference.

Findings

Achieves state-of-the-art results on TVHID-LAEO dataset.

Successfully determines if two people are LAEO and identifies when it occurs.

Enables inference of social relationships based on LAEO patterns.

Abstract

Capturing the 'mutual gaze' of people is essential for understanding and interpreting the social interactions between them. To this end, this paper addresses the problem of detecting people Looking At Each Other (LAEO) in video sequences. For this purpose, we propose LAEO-Net++, a new deep CNN for determining LAEO in videos. In contrast to previous works, LAEO-Net++ takes spatio-temporal tracks as input and reasons about the whole track. It consists of three branches, one for each character's tracked head and one for their relative position. Moreover, we introduce two new LAEO datasets: UCO-LAEO and AVA-LAEO. A thorough experimental evaluation demonstrates the ability of LAEO-Net++ to successfully determine if two people are LAEO and the temporal window where it happens. Our model achieves state-of-the-art results on the existing TVHID-LAEO video dataset, significantly outperforming previous approaches. Finally, we apply LAEO-Net++ to a social network, where we automatically infer the social relationship between pairs of people based on the frequency and duration that they LAEO, and show that LAEO can be a useful tool for guided search of human interactions in videos. The code is available at https://github.com/AVAuco/laeonetplus.