Are Categorical Spatial Relations Encoded by Shifting Visual Attention between Objects? [PDF]
PLoS One, 2016 Perceiving not just values, but relations between values, is critical to human cognition. We tested the predictions of a proposed mechanism for processing categorical spatial relations between two objects—the shift account of relation processing—which ...
Yuan L, Uttal D, Franconeri S.
europepmc +2 more sources
The relationship between spatial ability self-efficacy and visualization performance: psychometric evidence [PDF]
Frontiers in PsychologyIntroductionThis study adopts a holistic perspective on spatial ability by integrating preservice teachers’ self-efficacy perceptions with performance-based approaches.
Okan Kuzu, Hanife Taşdelen
doaj +2 more sources
Development of a spatial skills test for 4th grade primary school students: validity and reliability study [PDF]
Frontiers in PsychologyAlthough several instruments have been developed to assess spatial skills, most were designed for older students, emphasize specific components of spatial ability, or have not been specifically designed to reflect the developmental characteristics and ...
Elif Aydın-Çolak +2 more
doaj +2 more sources
Spatial Relations Using High Level Concepts
ISPRS International Journal of Geo-Information, 2012 Existing models of spatial relations do not consider that different concepts exist on different levels in a hierarchy and in turn that the spatial relations in a given scene are a function of the specific concepts considered.
Michela Bertolotto +2 more
doaj +3 more sources
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations [PDF]
International Conference Geographic Information Science, 2023 This research focuses on assessing the ability of large language models (LLMs) in representing geometries and their spatial relations. We utilize LLMs including GPT-2 and BERT to encode the well-known text (WKT) format of geometries and then feed their ...
Yu Ji, Song Gao
semanticscholar +1 more source
On the Importance of Spatial Relations for Few-shot Action Recognition [PDF]
ACM Multimedia, 2023 Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer knowledge from
Yilun Zhang +6 more
semanticscholar +1 more source
The scientific and philosophical presentation of the concept “space” and its explication in Erzya-Mordvin and Finnish languages [PDF]
Финно-угорский мир, 2022 Introduction. The article discusses the concept of “space” from the point of view of scientific, philosophical and linguistic concepts, describes the historical genesis of this phenomenon, starting from ancient philosophy and mythology to the present ...
Natalya M. Mosina, Olga V. Rubtsova
doaj +1 more source
Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling
AAAI Conference on Artificial Intelligence, 2023 Modeling multi-variate time-series (MVTS) data is a long-standing research subject and has found wide applications. Recently, there is a surge of interest in modeling spatial relations between variables as graphs, i.e., first learning one static graph ...
Yuchen Fang +7 more
semanticscholar +1 more source
The Dorsal Visual Pathway Represents Object-Centered Spatial Relations for Object Recognition
Journal of Neuroscience, 2021 Although there is mounting evidence that input from the dorsal visual pathway is crucial for object processes in the ventral pathway, the specific functional contributions of dorsal cortex to these processes remain poorly understood.
V. Ayzenberg, M. Behrmann
semanticscholar +1 more source
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D [PDF]
Neural Information Processing Systems, 2020 Understanding spatial relations (e.g., "laptop on table") in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, which is critical for learning ...
Ankit Goyal +3 more
semanticscholar +1 more source