Attention-Based Segmentation on an Image Pyramid Sequence

被引:0
|
作者
Atsumi, Masayasu [1 ]
机构
[1] Soka Univ, Fac Engn, Dept Informat Syst Sci, Hachioji, Tokyo 1928577, Japan
来源
ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, PROCEEDINGS | 2008年 / 5259卷
关键词
VISUAL-ATTENTION;
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
This paper proposes a, computational model of attention-based segmentation in which a sequence of image pyramids of early visual features is computed for a video sequence and a repetition of selective attention and figure-ground segmentation is performed on the sequence for object perception through successive segment development with mergence of concurrent segments. Attentiou is stochastically selected on a OF multi-level saliency map that is called a visual attention pyramid and segmentation is performed on Markov random fields which are dynamically formed around foci of attention. A set of segments and their spatial relation are stored in a visual working memory and maintained through the repetitive attention and segmentation process. Performances of the model are evaluated for basic functions of the vision system such as visual pop-out, figure-ground reversal and perceptual organization and also for pp real-world scenes which contain objects designed to attract attention.
引用
收藏
页码:625 / 636
页数:12
相关论文
共 50 条
  • [31] Attention-Based Background/Foreground Monocular Depth Prediction Model Using Image Segmentation
    Chiang, Ting-Hui
    Chiang, Meng-Hsiu
    Tsai, Ming-Han
    Chang, Che-Cheng
    APPLIED SCIENCES-BASEL, 2022, 12 (21):
  • [32] An attention-based dense network model for cardiac image segmentation using learning approaches
    Subaramani, Nandhagopal
    Sasikala, E.
    SOFT COMPUTING, 2024, 28 (01) : 765 - 775
  • [33] An attention-based dense network model for cardiac image segmentation using learning approaches
    Nandhagopal Subaramani
    E. Sasikala
    Soft Computing, 2024, 28 : 765 - 775
  • [34] Attention-based sequence classification for affect detection
    Gorrostieta, Cristina
    Brutti, Richard
    Taylor, Kye
    Shapiro, Avi
    Moran, Joseph
    Azarbayejani, Ali
    Kane, John
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 506 - 510
  • [35] Image segmentation of skin lesions based on dense atrous spatial pyramid pooling and attention mechanism
    Yin W.
    Zhou D.
    Fan T.
    Yu Z.
    Li Z.
    Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, 2022, 39 (06): : 1108 - 1116
  • [36] Attention-Based Transformers for Instance Segmentation of Cells in Microstructures
    Prangemeier, Tim
    Reich, Christoph
    Koeppl, Heinz
    2020 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2020, : 700 - 707
  • [37] A New Attention-Based LSTM for Image Captioning
    Fen Xiao
    Wenfeng Xue
    Yanqing Shen
    Xieping Gao
    Neural Processing Letters, 2022, 54 : 3157 - 3171
  • [38] Attention-based Stylisation for Exemplar Image Colourisation
    Blanch, Marc Gorriz
    Khalifeh, Issa
    O'Connor, Noel E.
    Mrak, Marta
    IEEE MMSP 2021: 2021 IEEE 23RD INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2021,
  • [39] Attention-Based Multi-Kernelized and Boundary-Aware Network for image semantic segmentation
    Zhou, Xuanchen
    Wu, Gengshen
    Sun, Xin
    Hu, Pengpeng
    Liu, Yi
    NEUROCOMPUTING, 2024, 597
  • [40] Deep Attention-Based Imbalanced Image Classification
    Wang, Lituan
    Zhang, Lei
    Qi, Xiaofeng
    Yi, Zhang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (08) : 3320 - 3330