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
  • [21] A Unified Account of Gaze Following
    Jasso, Hector
    Triesch, Jochen
    Deak, Gedeon
    Lewis, Joshua M.
    IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, 2012, 4 (04) : 257 - 272
  • [22] Patch-Level Unsupervised Planetary Change Detection
    Saha, Sudipan
    Zhu, Xiao Xiang
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [23] EFFECTS OF SPEAKING ORDER AND SPEAKER GAZE LEVEL ON INTERPERSONAL GAZE IN A TRIAD
    LESKO, WA
    SCHNEIDER, FW
    JOURNAL OF SOCIAL PSYCHOLOGY, 1978, 104 (02): : 185 - 195
  • [24] Gaze following:: why (not) learn it?
    Triesch, J
    Teuscher, C
    Deák, GO
    Carlson, E
    DEVELOPMENTAL SCIENCE, 2006, 9 (02) : 125 - 147
  • [25] Gaze following among toddlers
    Kishimoto, Takeshi
    Shizawa, Yasuhiro
    Yasuda, Jun
    Hinobayashi, Toshihiko
    Minami, Tetsuhiro
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2008, 43 (3-4) : 499 - 499
  • [26] Gaze following among toddlers
    Kishimoto, Takeshi
    Shizawa, Yasuhiro
    Yasuda, Jun
    Hinobayashi, Toshihiko
    Minami, Tetsuhiro
    INFANT BEHAVIOR & DEVELOPMENT, 2008, 31 (02): : 280 - 286
  • [27] PREDICTION AND COOPERATION IN GAZE CONTROL
    BROWN, C
    BIOLOGICAL CYBERNETICS, 1990, 63 (01) : 61 - 70
  • [28] PATCH-LEVEL SELECTION AND BREADTH-FIRST PREDICTION STRATEGY FOR REVERSIBLE DATA HIDING
    Wu, Hanzhou
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 2837 - 2841
  • [29] Human-object interaction prediction in videos through gaze following
    Ni, Zhifan
    Mascaro, Esteve Valls
    Ahn, Hyemin
    Lee, Dongheui
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 233
  • [30] SEA SURFACE TEMPERATURE PREDICTION AND RECONSTRUCTION USING PATCH-LEVEL NEURAL NETWORK REPRESENTATIONS
    Ouala, Said
    Herzet, Cedric
    Fablet, Ronan
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 5628 - 5631