.png){kind=icon}
返回
Shape from Contour: Computation and Representation
.png){kind=icon}
OA
AI
DOI：10.1146/annurev-vision-091517-034110.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The human visual system reliably extracts shape information from complex natural scenes in spite of noise and fragmentation caused by clutter and occlusions. A fast, feedforward sweep through ventral stream involving mechanisms tuned for orientation, curvature, and local Gestalt principles produces partial shape representations sufficient for simpler discriminative tasks. More complete shape representations may involve recurrent processes that integrate local and global cues. While feedforward discriminative deep neural network models currently produce the best predictions of object selectivity in higher areas of the object pathway, a generative model may be required to account for all aspects of shape perception. Research suggests that a successful model will account for our acute sensitivity to four key perceptual dimensions of shape: topology, symmetry, composition, and deformation.
Keyword:
shape
form
object
contour
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
A
IF:
5.5
论文数:
0
被引数:
1
机构
引用论文
分享收藏Characterization of Campylobacter upsaliensis fur and its localization in a highly conserved region of the Campylobacter genome.png)
Gene
GeneIF0
PREAI
分享收藏Response of Alfalfa Cultivars to Salinity during Germination and Post‐Germination GrowthCrop Science
Crop ScienceIF0
PREAI
分享收藏Highly enantioselective direct vinylogous Michael addition of γ-substituted deconjugated butenolides to maleimides catalyzed by chiral squaramidesRSC Advances
RSC AdvancesIF0
PREAI
分享收藏分享收藏
查看更多内容