Patch-level Gaze Distribution Prediction for Gaze Following

被引:10
|
作者
Miao, Qiaomu [1 ]
Minh Hoai [1 ]
Samaras, Dimitris [1 ]
机构
[1] SUNY Stony Brook, Stony Brook, NY 11794 USA
基金
美国国家科学基金会;
关键词
TRACKING;
D O I
10.1109/WACV56688.2023.00094
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Gaze following aims to predict where a person is looking in a scene, by predicting the target location, or indicating that the target is located outside the image. Recent works detect the gaze target by training a heatmap regression task with a pixel-wise mean-square error (MSE) loss, while formulating the in/out prediction task as a binary classification task. This training formulation puts a strict, pixel-level constraint in higher resolution on the single annotation available in training, and does not consider annotation variance and the correlation between the two subtasks. To address these issues, we introduce the patch distribution prediction (PDP) method. We replace the in/out prediction branch in previous models with the PDP branch, by predicting a patch-level gaze distribution that also considers the outside cases. Experiments show that our model regularizes the MSE loss by predicting better heatmap distributions on images with larger annotation variances, meanwhile bridging the gap between the target prediction and in/out prediction subtasks, showing a significant improvement in performance on both subtasks on public gaze following datasets.
引用
收藏
页码:880 / 889
页数:10
相关论文
共 50 条
  • [11] Following Gaze in Video
    Recasens, Adria
    Vondrick, Carl
    Khosla, Aditya
    Torralba, Antonio
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1444 - 1452
  • [12] Gaze following in newborns
    Farroni, T
    Massaccesi, S
    Pividori, D
    Johnson, MH
    INFANCY, 2004, 5 (01) : 39 - 60
  • [13] Loop closure detection with patch-level local features and visual saliency prediction
    Jin, Sheng
    Dai, Xuyang
    Meng, Qinghao
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 120
  • [14] Gaze Response to Others' Gaze Following in Children With and Without Autism
    Wang, Qiandong
    Hoi, Sio Pan
    Wang, Yuyin
    Lam, Cheuk Man
    Fang, Fang
    Yi, Li
    JOURNAL OF ABNORMAL PSYCHOLOGY, 2020, 129 (03) : 320 - 329
  • [15] Gaze distribution analysis and saliency prediction across age groups
    Krishna, Onkar
    Helo, Andrea
    Raemae, Pia
    Aizawa, Kiyoharu
    PLOS ONE, 2018, 13 (02):
  • [16] Following Eye Gaze Activates a Patch in the Posterior Temporal Cortex That Is not Part of the Human "Face Patch" System
    Marquardt, Kira
    Ramezanpour, Hamidreza
    Dicke, Peter W.
    Thier, Peter
    ENEURO, 2017, 4 (02)
  • [17] Gaze Prediction for Recommender Systems
    Zhao, Qian
    Chang, Shuo
    Harper, F. Maxwell
    Konstan, Joseph A.
    PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, : 131 - 138
  • [18] Gaze Following, Gaze Reading, and Word Learning in Children at Risk for Autism
    Gliga, Teodora
    Elsabbagh, Mayada
    Hudry, Kristelle
    Charman, Tony
    Johnson, Mark H.
    CHILD DEVELOPMENT, 2012, 83 (03) : 926 - 938
  • [19] Neurofuzzy prediction for gaze control
    Cuevas, Erik
    Zaldivar, Daniel
    Rojas, Raul
    CANADIAN JOURNAL OF ELECTRICAL AND COMPUTER ENGINEERING-REVUE CANADIENNE DE GENIE ELECTRIQUE ET INFORMATIQUE, 2009, 34 (1-2): : 15 - 20
  • [20] PATCH-LEVEL REGULARIZER FOR CONVOLUTIONAL NEURAL NETWORK
    Xu, Dejiang
    Lee, Mong Li
    Hsu, Wynne
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3232 - 3236