NIMBLE: a kernel density model of saccade-based visual memory.

NIMBLE: a kernel density model of saccade-based visual memory.
复制标题

DOI:
10.1167/8.14.17
复制
发表时间:
2008-11-12
期刊:
影响因子:
1.8
通讯作者:
Cottrell GW
Cottrell GW
中科院分区:
医学4区
文献类型:
--
作者:
Barrington L;Marks TK;Hsiao JH;Cottrell GW

文献摘要

参考文献

被引文献

相似文献

我们提出了扫视视觉记忆的自然输入记忆(NIM)模型的贝叶斯版本。我们的模型称为 NIMBLE(带有贝叶斯似然估计的 NIM),它使用一种认知上合理的图像采样技术,提供图像块的注视点表示。我们将这些记忆的图像片段视为图像类分布的样本,并使用核密度估计对这些片段的记忆进行建模。使用这些模型,我们得出新图像片段的类条件概率,并结合各个片段概率对图像进行分类。我们的模型贝叶斯公式可以轻松扩展以处理多类问题。我们通过展示人脸识别记忆任务的人类性能水平以及多类别人脸和物体识别的高精度来验证我们的模型。我们还使用 NIMBLE 来检查随着从图像中获取更多注视而产生的信念变化。使用从人类受试者收集的注视数据,我们直接将 NIMBLE 的记忆组件的性能与人类的表现进行比较,证明使用人类注视位置使 NIMBLE 只需一次注视即可识别熟悉的面孔。
We present a Bayesian version of Natural Input Memory (NIM) model of saccadic visual memory. Our model, which we call NIMBLE (NIM with Bayesian Likelihood Estimation), uses a cognitively plausible image sampling technique that provides a foveated representation of image patches. We conceive of these memorized image fragments as samples from image class distributions and model the memory of these fragments using kernel density estimation. Using these models, we derive class-conditional probabilities of new image fragments and combine individual fragment probabilities to classify images. Our Bayesian formulation of the model extends easily to handle multi-class problems. We validate our model by demonstrating human levels of performance on a face recognition memory task and high accuracy on multi-category face and object identification. We also use NIMBLE to examine the change in beliefs as more fixations are taken from an image. Using fixation data collected from human subjects, we directly compare the performance of NIMBLE’s memory component to human performance, demonstrating that using human fixation locations allows NIMBLE to recognize familiar faces with only a single fixation.
DOI: 10.1023/b:visi.0000029664.99615.94
发表时间: 2004-11-01
影响因子: 19.5
作者:
Lowe, DG
通讯作者: Lowe, DG
DOI: 10.1016/0042-6989(71)90213-6
发表时间: 1971-01-01
期刊: VISION RESEARCH
影响因子: 1.8
作者:
NOTON, D;STARK, L
通讯作者: STARK, L
DOI: 10.1167/7.3.6
发表时间: 2007-01-01
期刊: JOURNAL OF VISION
影响因子: 1.8
作者:
Renninger, Laura Walker;Verghese, Preeti;Coughlan, James
通讯作者: Coughlan, James
DOI: 10.3758/bf03195300
发表时间: 2005-01-01
期刊: MEMORY & COGNITION
影响因子: 2.4
作者:
Henderson, JM;Williams, CC;Falk, RJ
通讯作者: Falk, RJ
DOI: 10.1016/s0262-8856(97)00070-x
发表时间: 1998-04-27
影响因子: 4.7
作者:
Phillips, PJ;Wechsler, H;Rauss, PJ
通讯作者: Rauss, PJ