NDLI: LeSSS: learned shared semantic spaces for relating multi-modal representations of 3D shapes

Please wait, while we are loading the content...

Stable topological signatures for points on 3D shapes

Reforming shapes for material-aware fabrication

Hierarchical multiview rigid registration

Tight relaxation of quadratic matching

Fast and exact (Poisson) solvers on symmetric geometries

Dynamic SfM: detecting scene changes from image pairs

Perfect Laplacians for polygon meshes

Homotopic morphing of planar curves

Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks

Texture mapping real-world objects with hydrographics

Sparse non-rigid registration of 3D shapes

Continuous matching via vector field flow

Quaternion Julia set shape optimization

An image degradation model for depth-augmented image editing

Perfect matching quad layouts for manifold meshes

A one-dimensional homologically persistent skeleton of an unstructured point cloud in any metric space

Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces

Robust articulated-ICP for real-time hand tracking

LeSSS: learned shared semantic spaces for relating multi-modal representations of 3D shapes

Unconditionally stable shock filters for image and geometry processing

Can bi-cubic surfaces be class A?

Example based repetitive structure synthesis

LeSSS: learned shared semantic spaces for relating multi-modal representations of 3D shapes

Content Provider	ACM Digital Library
Author	Mewes, Daniel Wand, Michael Herzog, Robert Seidel, Hans-Peter Guibas, Leonidas
Abstract	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.
Starting Page	141
Ending Page	151
Page Count	11
ISSN	01677055 14678659
DOI	10.1111/cgf.12703
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-07-06
Publisher Place	Goslar
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	3d-shape descriptors Collaborative filtering Multi-modal learning Object recognition Object retrieval Semantic correspondences
Content Type	Text
Resource Type	Article
Subject	Computer Graphics and Computer-Aided Design Computer Networks and Communications

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes

Relating shapes via geometric symmetries and regularities

Shape2Vec: semantic-based descriptors for 3D shapes, sketches and images

Stable region correspondences between non-isometric shapes

Relative scale estimation and 3D registration of multi-modal geometry using Growing Least Squares

3D Media and the Semantic Web

Exploration of continuous variability in collections of 3D shapes

Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks

Partial 3D Shape Retrieval by Reeb Pattern Unfolding

LeSSS: learned shared semantic spaces for relating multi-modal representations of 3D shapes

Similar Documents

Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes

Relating shapes via geometric symmetries and regularities

Shape2Vec: semantic-based descriptors for 3D shapes, sketches and images

Stable region correspondences between non-isometric shapes

Relative scale estimation and 3D registration of multi-modal geometry using Growing Least Squares

3D Media and the Semantic Web

Exploration of continuous variability in collections of 3D shapes

Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks

Partial 3D Shape Retrieval by Reeb Pattern Unfolding

LeSSS: learned shared semantic spaces for relating multi-modal representations of 3D shapes