Passer à la navigation principale Passer à la recherche Passer au contenu principal

Laeo-net: Revisiting people looking at each other in videos

  • Manuel J. Marin-Jimenez
  • , Vicky Kalogeiton
  • , Pablo Medina-Suarez
  • , Andrew Zisserman
  • University of Cordoba
  • University of Oxford

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

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.

langue originaleAnglais
titreProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
EditeurIEEE Computer Society
Pages3472-3480
Nombre de pages9
ISBN (Electronique)9781728132938
Les DOIs
étatPublié - 1 juin 2019
Modification externeOui
Evénement32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, États-Unis
Durée: 16 juin 201920 juin 2019

Série de publications

NomProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (imprimé)1063-6919

Une conférence

Une conférence32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Pays/TerritoireÉtats-Unis
La villeLong Beach
période16/06/1920/06/19

Empreinte digitale

Examiner les sujets de recherche de « Laeo-net: Revisiting people looking at each other in videos ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation