LAEO-Net: Revisiting People Looking At Each Other in Videos
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 characters 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 16, 2019
- Accession Number
- AD1152052
Entities
People
- Andrew Zisserman
- Manuel J. Marin-Jimenez
- Pablo Medina-suarez
- Vicky Kalogeiton
Organizations
- University of Córdoba
- University of Oxford