Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models

被引:0
|
作者
Uppal, Karan [1 ]
Kim, Jaeah [2 ]
Singh, Shashank [3 ]
机构
[1] Indian Inst Technol, Kharagpur, W Bengal, India
[2] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[3] Max Planck Inst Intelligent Syst, Tubingen, Germany
来源
GAZE MEETS MACHINE LEARNING WORKSHOP, VOL 210 | 2022年 / 210卷
基金
美国国家科学基金会;
关键词
Gaze; Eye-Tracking; Deep Learning; Attentional Decoding; VISUAL WORLD PARADIGM; MOUNTED EYE-TRACKING;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Eye-tracking has potential to provide rich behavioral data about human cognition in ecologically valid environments. However, analyzing this rich data is often challenging. Most automated analyses are specific to simplistic artificial visual stimuli with well-separated, static regions of interest, while most analyses in the context of complex visual stimuli, such as most natural scenes, rely on laborious and time-consuming manual annotation. This paper studies using computer vision tools for "attention decoding", the task of assessing the locus of a participant's overt visual attention over time. We provide a publicly available Multiple Object Eye-Tracking (MOET) dataset, consisting of gaze data from participants tracking specific objects, annotated with labels and bounding boxes, in crowded real-world videos, for training and evaluating attention decoding algorithms. We also propose two end-to-end deep learning models for attention decoding and compare these to state-of-the-art heuristic methods.
引用
收藏
页码:219 / 240
页数:22
相关论文
共 50 条
  • [21] End-to-End Dataset Collection System for Sport Activities
    Fresta, Matteo
    Bellotti, Francesco
    Capello, Alessio
    Dabbous, Ali
    Lazzaroni, Luca
    Ansovini, Flavio
    Berta, Riccardo
    ELECTRONICS, 2024, 13 (07)
  • [22] SUPPORTIVE ATTENTION IN END-TO-END MEMORY NETWORKS
    Chien, Jen-Tzung
    Lin, Ting-An
    2018 IEEE 28TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2018,
  • [23] End-to-End Instance Segmentation with Recurrent Attention
    Ren, Mengye
    Zemel, Richard S.
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 293 - 301
  • [24] An End-to-End TextSpotter with Explicit Alignment and Attention
    He, Tong
    Tian, Zhi
    Huang, Weilin
    Shen, Chunhua
    Qiao, Yu
    Sun, Changming
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5020 - 5029
  • [25] TRIGGERED ATTENTION FOR END-TO-END SPEECH RECOGNITION
    Moritz, Niko
    Hori, Takaaki
    Le Roux, Jonathan
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 5666 - 5670
  • [26] End-to-End Human-Gaze-Target Detection with Transformers
    Tu, Danyang
    Min, Xiongkuo
    Duan, Huiyu
    Guo, Guodong
    Zhai, Guangtao
    Shen, Wei
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 2192 - 2200
  • [27] Approaches to end-to-end ecosystem models
    Fulton, Elizabeth A.
    JOURNAL OF MARINE SYSTEMS, 2010, 81 (1-2) : 171 - 183
  • [28] A Benchmark Methodology For End-to-End Delay of Reactive Mobile Networks
    Laner, Markus
    Svoboda, Philipp
    Rupp, Markus
    2013 IFIP WIRELESS DAYS (WD), 2013,
  • [29] End-to-end delay models with priority
    Osterbo, O
    Performance Challenges for Efficient Next Generation Networks, Vols 6A-6C, 2005, 6A-6C : 1049 - 1058
  • [30] KNOWLEDGE DISTILLATION USING OUTPUT ERRORS FOR SELF-ATTENTION END-TO-END MODELS
    Kim, Ho-Gyeong
    Na, Hwidong
    Lee, Hoshik
    Lee, Jihyun
    Kang, Tae Gyoon
    Lee, Min-Joong
    Choi, Young Sang
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6181 - 6185