کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
4033615 1263362 2015 18 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
On computational modeling of visual saliency: Examining what’s right, and what’s left
موضوعات مرتبط
علوم زیستی و بیوفناوری علم عصب شناسی سیستم های حسی
پیش نمایش صفحه اول مقاله
On computational modeling of visual saliency: Examining what’s right, and what’s left
چکیده انگلیسی


• We review prior work in computational modeling of visual saliency.
• We demonstrate problems with prevailing methods for model evaluation.
• We present an alternative vantage point for model evaluation grounded in visual psychophysics.
• We identify promising avenues for future research in saliency modeling.

In the past decade, a large number of computational models of visual saliency have been proposed. Recently a number of comprehensive benchmark studies have been presented, with the goal of assessing the performance landscape of saliency models under varying conditions. This has been accomplished by considering fixation data, annotated image regions, and stimulus patterns inspired by psychophysics. In this paper, we present a high-level examination of challenges in computational modeling of visual saliency, with a heavy emphasis on human vision and neural computation. This includes careful assessment of different metrics for performance of visual saliency models, and identification of remaining difficulties in assessing model performance. We also consider the importance of a number of issues relevant to all saliency models including scale-space, the impact of border effects, and spatial or central bias. Additionally, we consider the biological plausibility of models in stepping away from exemplar input patterns towards a set of more general theoretical principles consistent with behavioral experiments. As a whole, this presentation establishes important obstacles that remain in visual saliency modeling, in addition to identifying a number of important avenues for further investigation.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Vision Research - Volume 116, Part B, November 2015, Pages 95–112
نویسندگان
, , , , ,