On visual understanding

2021 ◽  
Author(s):  
Yunhe Pan
Keyword(s):  
Visual Understanding

Deep semantic segmentation for visual understanding on construction sites

2021 ◽  
Author(s):  
Zifeng Wang ◽  
Yuyang Zhang ◽  
Khalid M. Mosalam ◽  
Yuqing Gao ◽  
Shao‐Lun Huang
Keyword(s):  
Semantic Segmentation ◽  
Construction Sites ◽  
Visual Understanding

Introduction to ‘Show Me the Data! Improving Evidence Presentation for Publication’ and ‘Show Us Your Data: Connect the Dots, Improve Science’

2018 ◽  
Vol 14 (2) ◽  
pp. 421-421
Author(s):  
Liisa Välikangas
Keyword(s):  
Empirical Data ◽  
Potential Importance ◽  
Visual Understanding

Henrich R. Greve, joined here by Sheen S. Levine, calls for presenting empirical data in more graphical forms than currently is the standard in management journals. This would benefit the advancement of science in many ways: showing the potential importance of the phenomenon under study to allowing a visual understanding of its relationships, thus connecting the reader to the evidence beyond the statistics shown. Do we have here a beast or a star? Without following the recommendations to start graphing as put forward by Greve and Levine, the reader would never know.

scholarly journals Examining Infant Relation Categorization Through Deep Neural Networks

2021 ◽  
Author(s):  
Guy Davidson ◽  
Brenden M. Lake
Keyword(s):  
Neural Networks ◽  
Spatial Cognition ◽  
Deep Neural Networks ◽  
Relational Learning ◽  
Spatial Relations ◽  
Computational Experiments ◽  
Visual Understanding

Categorizing spatial relations is central to the development of visual understanding and spatial cognition, with roots in the first few months of life. Quinn (2003) reviews two findings in infant relation categorization: categorizing one object as above/below another precedes categorizing an object as between other objects, and categorizing relations over specific objects predates abstract relations over varying objects. We model these phenomena with deep neural networks, including contemporary architectures specialized for relational learning and vision models pretrained on baby headcam footage (Sullivan et al., 2020). Across two computational experiments, we can account for most of the developmental findings, suggesting these models are useful for studying the computational mechanisms of infant categorization.

scholarly journals Computational modeling of human reasoning processes for interpretable visual knowledge: a case study with radiographers

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Yu Li ◽  
Hongfei Cao ◽  
Carla M. Allen ◽  
Xin Wang ◽  
Sanda Erdelez ◽  
...  
Keyword(s):  
Visual Attention ◽  
Computational Method ◽  
Human Cognition ◽  
Visual Knowledge ◽  
Spatial Features ◽  
Temporal Features ◽  
Visual Tasks ◽  
Visual Understanding ◽  
Reasoning Patterns ◽  
Expertise Level

AbstractVisual reasoning is critical in many complex visual tasks in medicine such as radiology or pathology. It is challenging to explicitly explain reasoning processes due to the dynamic nature of real-time human cognition. A deeper understanding of such reasoning processes is necessary for improving diagnostic accuracy and computational tools. Most computational analysis methods for visual attention utilize black-box algorithms which lack explainability and are therefore limited in understanding the visual reasoning processes. In this paper, we propose a computational method to quantify and dissect visual reasoning. The method characterizes spatial and temporal features and identifies common and contrast visual reasoning patterns to extract significant gaze activities. The visual reasoning patterns are explainable and can be compared among different groups to discover strategy differences. Experiments with radiographers of varied levels of expertise on 10 levels of visual tasks were conducted. Our empirical observations show that the method can capture the temporal and spatial features of human visual attention and distinguish expertise level. The extracted patterns are further examined and interpreted to showcase key differences between expertise levels in the visual reasoning processes. By revealing task-related reasoning processes, this method demonstrates potential for explaining human visual understanding.

Visual understanding of the hidden-order transition inURu2Si2by high-resolution x-ray Compton scattering

2015 ◽  
Vol 92 (12) ◽  
Author(s):  
Akihisa Koizumi ◽  
Yasunori Kubo ◽  
Gaku Motoyama ◽  
Tomoo Yamamura ◽  
Masayoshi Itou ◽  
...  
Keyword(s):  
High Resolution ◽  
Compton Scattering ◽  
Order Transition ◽  
X Ray ◽  
Hidden Order ◽  
Visual Understanding

Understanding depot antipsychotics: an illustrated guide to kinetics

CNS Spectrums ◽  
2013 ◽  
Vol 18 (s1) ◽  
pp. 55-68 ◽  
Author(s):  
Jonathan M. Meyer
Keyword(s):  
Patient Population ◽  
Oral Medications ◽  
High Prevalence ◽  
Visual Understanding ◽  
Long Acting ◽  
Depot Antipsychotics ◽  
Typical Antipsychotics

Long-acting injectable (LAI) antipsychotics can have considerable advantages over oral medications for the management of patients with schizophrenia. Despite the high prevalence of treatment nonadherence with oral pharmacotherapy, LAI antipsychotics are significantly underutilized in this patient population. The availability of newer LAI antipsychotic preparations combined with a resurgent interest in the use of typical antipsychotics has rekindled awareness of the value of LAI medications. This article is intended to provide a visual understanding of the various kinetic profiles of LAI antipsychotics to facilitate initiation and greater use of these agents.

Sign in / Sign up

Export Citation Format

Share Document