Skip to Main content Skip to Navigation
Journal articles

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 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.
Complete list of metadata

https://hal-polytechnique.archives-ouvertes.fr/hal-03110590
Contributor : Vicky Kalogeiton <>
Submitted on : Thursday, January 14, 2021 - 4:44:18 PM
Last modification on : Friday, January 22, 2021 - 3:30:54 AM
Long-term archiving on: : Thursday, April 15, 2021 - 7:17:59 PM

File

vickyPAMI21.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Manuel Marín-Jiménez, Vicky Kalogeiton, Pablo Medina-Suárez, Andrew Zisserman. LAEO-Net++: revisiting people Looking At Each Other in videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2020, pp.1-16. ⟨10.1109/TPAMI.2020.3048482⟩. ⟨hal-03110590⟩

Share

Metrics

Record views

45

Files downloads

82