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
  • [31] OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction
    Fang, Yini
    Yu, Jingling
    Zhang, Haozheng
    van der Lans, Ralf
    Shi, Bertram
    COMPUTER VISION - ECCV 2024, PT LV, 2025, 15113 : 366 - 382
  • [32] Combining pixel-level and patch-level information for segmentation
    Wang, Tao
    Ji, Zexuan
    Sun, Quansen
    Han, Shoudong
    NEUROCOMPUTING, 2015, 158 : 13 - 25
  • [33] Patch-Level Operation With Adaptive Patch Control for Improving Anomaly Localization
    Lee, Hyunyong
    Kim, Nac-Woo
    Lee, Jun-Gi
    Lee, Byung-Tak
    IEEE ACCESS, 2021, 9 : 90727 - 90737
  • [34] Practical Perception-Based Evaluation of Gaze Prediction for Gaze Contingent Rendering
    Aziz S.
    Lohr D.J.
    Stefanescu R.
    Komogortsev O.
    Proceedings of the ACM on Human-Computer Interaction, 2023, 7 (ETRA)
  • [35] The impact of maternal gaze responsiveness on infants' gaze following and later vocabulary development
    Wildt, Eugenia
    Rohlfing, Katharina J.
    INFANT BEHAVIOR & DEVELOPMENT, 2024, 74
  • [36] Patch-level Augmentation for Object Detection in Aerial Images
    Hong, Sungeun
    Kang, Sungil
    Cho, Donghyeon
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 127 - 134
  • [37] Visual Estimation of Building Condition with Patch-level ConvNets
    Koch, David
    Despotovic, Miroslav
    Sakeena, Muntaha
    Doeller, Mario
    Zeppelzauer, Matthias
    RETECH'18: PROCEEDINGS OF THE 2018 ACM WORKSHOP ON MULTIMEDIA FOR REAL ESTATE TECH, 2018, : 12 - 17
  • [38] Digging Deeper into Egocentric Gaze Prediction
    Tavakoli, Hamed R.
    Rahtu, Esa
    Kannala, Juho
    Borji, Ali
    2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 273 - 282
  • [39] GAZE CONTROLS COOPERATING THROUGH PREDICTION
    BROWN, C
    IMAGE AND VISION COMPUTING, 1990, 8 (01) : 10 - 17
  • [40] Active Contour Integrating Patch-Level and Pixel-Level Features
    Mao, Xinyue
    Chen, Yufei
    Liu, Xianhui
    Zhao, Weidong
    INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2017, PT I, 2017, 10361 : 353 - 365