State-of-the-Art in Visual Attention Modeling

被引:1510
作者
Borji, Ali [1 ]
Itti, Laurent [1 ,2 ,3 ]
机构
[1] Univ So Calif, Dept Comp Sci, Los Angeles, CA 90089 USA
[2] Univ So Calif, Dept Neurosci, Los Angeles, CA 90089 USA
[3] Univ So Calif, Dept Psychol, Los Angeles, CA 90089 USA
基金
美国国家科学基金会;
关键词
Visual attention; bottom-up attention; top-down attention; saliency; eye movements; regions of interest; gaze control; scene interpretation; visual search; gist; EYE-MOVEMENTS; SELECTIVE ATTENTION; SPATIOTEMPORAL SALIENCY; DISCRIMINANT SALIENCY; NEUROBIOLOGICAL MODEL; PATTERN-RECOGNITION; BAYESIAN-INFERENCE; NEURAL MECHANISMS; CONTEXT-FREE; SCENE;
D O I
10.1109/TPAMI.2012.89
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.
引用
收藏
页码:185 / 207
页数:23
相关论文
共 216 条
[1]
[Anonymous], 2008, BRIT MACHINE VISION
[2]
[Anonymous], THESIS
[3]
[Anonymous], THESIS
[4]
[Anonymous], IEEE INT S IND EL
[5]
[Anonymous], P IEEE C COMP VIS PA
[6]
[Anonymous], P 8 IEEE INT C DEV L
[7]
[Anonymous], 2010, P IEEE C COMP VIS PA
[8]
[Anonymous], 2009, P IEEE C COMP VIS PA
[9]
[Anonymous], 1988, Signal Detection Theory and Psychophysics
[10]
[Anonymous], 2008, NIPS