TY - GEN
T1 - Attention flow
T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
AU - Sumer, Omer
AU - Gerjets, Peter
AU - Trautwein, Ulrich
AU - Kasneci, Enkelejda
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - This paper addresses the problem of understanding joint attention in third-person social scene videos. Joint attention is the shared gaze behaviour of two or more individuals on an object or an area of interest and has a wide range of applications such as human-computer interaction, educational assessment, treatment of patients with attention disorders, and many more. Our method, Attention Flow, learns joint attention in an end-to-end fashion by using saliency-augmented attention maps and two novel convolutional attention mechanisms that determine to select relevant features and improve joint attention localization. We compare the effect of saliency maps and attention mechanisms and report quantitative and qualitative results on the detection and localization of joint attention in the VideoCoAtt dataset, which contains complex social scenes.
AB - This paper addresses the problem of understanding joint attention in third-person social scene videos. Joint attention is the shared gaze behaviour of two or more individuals on an object or an area of interest and has a wide range of applications such as human-computer interaction, educational assessment, treatment of patients with attention disorders, and many more. Our method, Attention Flow, learns joint attention in an end-to-end fashion by using saliency-augmented attention maps and two novel convolutional attention mechanisms that determine to select relevant features and improve joint attention localization. We compare the effect of saliency maps and attention mechanisms and report quantitative and qualitative results on the detection and localization of joint attention in the VideoCoAtt dataset, which contains complex social scenes.
UR - http://www.scopus.com/inward/record.url?scp=85085500079&partnerID=8YFLogxK
U2 - 10.1109/WACV45572.2020.9093515
DO - 10.1109/WACV45572.2020.9093515
M3 - Conference contribution
AN - SCOPUS:85085500079
T3 - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
SP - 3316
EP - 3325
BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 1 March 2020 through 5 March 2020
ER -