Attention Flow: End-to-End Joint Attention Estimation

  title={Attention Flow: End-to-End Joint Attention Estimation},
  author={{\"O}mer S{\"u}mer and Peter Gerjets and U. Trautwein and Enkelejda Kasneci},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
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… Expand
1 Citations

Figures and Tables from this paper

Detecting Attended Visual Targets in Video
  • E. Chong, Yongxin Wang, Nataniel Ruiz, J. Rehg
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
  • 3
  • Highly Influenced
  • PDF


Supervising Neural Attention Models for Video Captioning by Human Gaze Data
  • 39
  • PDF
Following Gaze in Video
  • 32
  • PDF
Inferring Shared Attention in Social Scene Videos
  • 18
  • Highly Influential
  • PDF
Social saliency prediction
  • H. Park, J. Shi
  • Mathematics, Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
  • 70
  • PDF
Action Recognition using Visual Attention
  • 504
  • PDF
Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model
  • 290
  • PDF
Attentional Push: A Deep Convolutional Network for Augmenting Image Salience with Shared Attention Modeling in Social Scenes
  • 16
  • PDF
3D Social Saliency from Head-mounted Cameras
  • 85
  • PDF
Residual Attention Network for Image Classification
  • 1,365
  • PDF