LeSSS: Learned Shared Semantic Spaces for Relating Multi-Modal Representations of 3D Shapes

• Published in: Computer graphics forum Vol. 34; no. 5; pp. 141 - 151
• Main Authors: Herzog, Robert, Mewes, Daniel, Wand, Michael, Guibas, Leonidas, Seidel, Hans-Peter
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.08.2015
• Subjects: 3D-shape descriptors; Analysis; and object representations; Artificial Intelligence [I.2.10]: Vision and Scene Understanding; Categories and Subject Descriptors (according to ACM CCS); collaborative filtering; Computer Graphics [I.3.5]: Computational Geometry and Object Modeling-Curve; Computer Graphics [I.3.5]: Computational Geometry and Object Modeling—Curve, surface, solid, and object representations; Correlation; Image processing systems; Labels; multi-modal learning; object recognition; object retrieval; Representations; semantic correspondences; Semantics; Shape Image Processing and Computer Vision [I.4.8]: Scene Analysis-Object recognition; Similarity; solid; Studies; surface; Texts; Three dimensional; Topological manifolds
• ISSN: 0167-7055; 1467-8659; 1467-8659
• DOI: 10.1111/cgf.12703

In this paper, we propose a new method for structuring multi‐modal representations of shapes according to semantic relations. We learn a metric that links semantically similar objects represented in different modalities. First, 3D‐shapes are associated with textual labels by learning how textual attributes are related to the observed geometry. Correlations between similar labels are captured by simultaneously embedding labels and shape descriptors into a common latent space in which an inner product corresponds to similarity. The mapping is learned robustly by optimizing a rank‐based loss function under a sparseness prior for the spectrum of the matrix of all classifiers. Second, we extend this framework towards relating multi‐modal representations of the geometric objects. The key idea is that weak cues from shared human labels are sufficient to obtain a consistent embedding of related objects even though their representations are not directly comparable. We evaluate our method against common base‐line approaches, investigate the influence of different geometric descriptors, and demonstrate a prototypical multi‐modal browser that relates 3D‐objects with text, photographs, and 2D line sketches.