Exploring diagram-based visual problem representation and relational abstraction
Chayanika D. Nath, Shyamanta Moni Hazarika · Spatial Cognition and Computation · 2024
For visual information processing, the derivation of meaningful low-level spatio-temporal information is challenging. In line with human visualisation and perception in spatial problem-solving, we believe explicit representations hold promise for efficient low-level abstractions. An approach for mapping spatial objects and relations, exploring diagrams’ representation power for problem visualisation, is presented. Combined, qualitative spatio-temporal reasoning and diagrammatic reasoning directly influence information visualisation and abstraction over the physical substrate of a problem. The framework preserves objects’ low-level spatio-temporal information over time, facilitating the interpretation of unique relationships. A 78% average activity recognition accuracy on the CAVIAR and Mind’s Eye datasets demonstrates the effectiveness of the suggested abstraction approach.