Combining Statistical and Symbolic Reasoning for Active Scene Categorization

2011 ◽  
pp. 262-275 ◽  
Author(s):  
Thomas Reineking ◽  
Niclas Schult ◽  
Joana Hois
Keyword(s):  
Scene Categorization ◽  
Symbolic Reasoning

scholarly journals Statistics of natural scene structures and scene categorization

2012 ◽  
Vol 13 (S1) ◽  
Author(s):  
Xin Chen ◽  
Weibing Wan ◽  
Zhiyong Yong
Keyword(s):  
Natural Scene ◽  
Scene Categorization

scholarly journals Flexible time course of spatial frequency use during scene categorization

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sandro L. Wiesmann ◽  
Laurent Caplette ◽  
Verena Willenbockel ◽  
Frédéric Gosselin ◽  
Melissa L.-H. Võ
Keyword(s):  
Time Course ◽  
Task Characteristics ◽  
Scene Categorization ◽  
Fine Grained ◽  
Spatial Frequencies ◽  
Outdoor Scenes ◽  
Indoor Scenes ◽  
Fine Pattern ◽  
Late Stages ◽  
Basic Level

AbstractHuman observers can quickly and accurately categorize scenes. This remarkable ability is related to the usage of information at different spatial frequencies (SFs) following a coarse-to-fine pattern: Low SFs, conveying coarse layout information, are thought to be used earlier than high SFs, representing more fine-grained information. Alternatives to this pattern have rarely been considered. Here, we probed all possible SF usage strategies randomly with high resolution in both the SF and time dimensions at two categorization levels. We show that correct basic-level categorizations of indoor scenes are linked to the sampling of relatively high SFs, whereas correct outdoor scene categorizations are predicted by an early use of high SFs and a later use of low SFs (fine-to-coarse pattern of SF usage). Superordinate-level categorizations (indoor vs. outdoor scenes) rely on lower SFs early on, followed by a shift to higher SFs and a subsequent shift back to lower SFs in late stages. In summary, our results show no consistent pattern of SF usage across tasks and only partially replicate the diagnostic SFs found in previous studies. We therefore propose that SF sampling strategies of observers differ with varying stimulus and task characteristics, thus favouring the notion of flexible SF usage.

Region Contextual Visual Words for scene categorization

2011 ◽  
Vol 38 (9) ◽  
pp. 11591-11597 ◽  
Author(s):  
Shuoyan Liu ◽  
De Xu ◽  
Songhe Feng
Keyword(s):  
Scene Categorization ◽  
Visual Words

scholarly journals Scene Categorization Model Using Deep Visually Sensitive Features

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 45230-45239 ◽  
Author(s):  
Jing Shi ◽  
Hong Zhu ◽  
Shunyuan Yu ◽  
Wenhuan Wu ◽  
Hua Shi
Keyword(s):  
Scene Categorization ◽  
Categorization Model

scholarly journals Visual, Functional, and Semantic Contributions to Scene Categorization

2017 ◽  
Vol 17 (10) ◽  
pp. 552 ◽  
Author(s):  
Michelle Greene ◽  
Bruce Hansen
Keyword(s):  
Scene Categorization

scholarly journals Effect of adaptation suggests role of low-level processes in rapid scene categorization

2010 ◽  
Vol 6 (6) ◽  
pp. 800-800
Author(s):  
D. Kaping ◽  
T. Tzvetanov ◽  
S. Treue
Keyword(s):  
Scene Categorization ◽  
Low Level

scholarly journals Decoding the informative value of early and late visual evoked potentials in scene categorization

2016 ◽  
Vol 16 (12) ◽  
pp. 259
Author(s):  
Bruce Hansen ◽  
Michelle Greene ◽  
Catherine Walsh ◽  
Rachel Goldberg ◽  
Yanchang Zhang
Keyword(s):  
Evoked Potentials ◽  
Visual Evoked Potentials ◽  
Scene Categorization ◽  
Visual Evoked
Sign in / Sign up

Export Citation Format

Share Document