A Multi-Attribute Latent Space for Visual Analysis of Watches

2026-06-26

AI Summary

This study addresses the limitations of conventional watch e-commerce platforms, which rely solely on metadata filtering and lack support for visual similarity search and style exploration. To overcome this, the authors propose an interactive visualization approach that integrates heterogeneous attributes—including dial color (represented via a CIELAB palette), dial structure (encoded using gradient image descriptors), and watch type (predicted by a Vision Transformer)—into a unified probabilistic target. They innovatively embed a multi-attribute neighborhood graph into the UMAP framework and introduce a category-aware layout mechanism that preserves global semantic structure while revealing local visual proximities. The resulting system enables users to efficiently explore and compare watch styles, with qualitative evaluations from both domain experts and novices confirming its effectiveness, while also highlighting limitations in scalability, image-based retrieval, and cross-domain applicability.

Abstract

We present a design rationale, embedding model, and interactive visual-analysis system for exploring large wristwatch collections through heterogeneous visual and semantic attributes. The system addresses a common limitation of catalog and e-commerce interfaces: users can filter by metadata, but they receive little support for open-ended exploration of visual similarity, stylistic alternatives, and mixed aesthetic-functional criteria. We therefore represent watches with separate attribute graphs for dial color and dial design, while using watch type as an explicit semantic organizer. Dials are segmented with a U-Net, watch types are predicted with a Vision Transformer, colors are represented through a shared CIELAB reference palette, and dial structure is described with a gradient-based image descriptor. We extend UMAP by combining attribute-specific neighborhood graphs in a unified probabilistic objective and by adding a class-aware layout term that separates global type structure from local visual neighborhoods. The resulting map is exposed in an interactive interface with spatial navigation, metadata filtering, detail inspection, and search-by-example insertion. We evaluate the approach through parameter analysis, runtime measurements, and a qualitative pilot study with watch experts and novices. The results suggest that the system supports discovery and comparison, while also revealing limitations in scalability assessment, search-by-example validation, and the need for broader domain studies. We explicitly discuss these limitations and derive design implications for multi-attribute latent-space visualization across heterogeneous visual collections.

Problem

• visual similarity
• stylistic alternatives
• multi-attribute exploration
• aesthetic-functional criteria
• heterogeneous visual collections

Innovation

• multi-attribute latent space
• heterogeneous visual collections
• class-aware UMAP
• interactive visual analysis
• semantic-visual embedding