ShapeGlot: Learning Language for Shape Differentiation

In this work we explore how fine-grained differences between the shapes of common objects are expressed in language, grounded on images and 3D models of the objects. We first build a large scale, carefully controlled dataset of human utterances that each refers to a 2D rendering of a 3D CAD model so...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-05
Hauptverfasser:	Achlioptas, Panos, Fan, Judy, Hawkins, Robert X D, Goodman, Noah D, Guibas, Leonidas J
Format:	Artikel
Sprache:	eng
Schlagworte:	Differentiation Furniture Learning Three dimensional models Training Two dimensional models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!