Frame Semantics in Text-to-Scene Generation
نویسندگان
چکیده
3D graphics scenes are difficult to create, requiring users to learn and utilize a series of complex menus, dialog boxes, and often tedious direct manipulation techniques. By giving up some amount of control afforded by such interfaces we have found that users can use natural language to quickly and easily create a wide variety of 3D scenes. Natural language offers an interface that is intuitive and immediately accessible by anyone, without requiring any special skill or training. The WordsEye system (http://www.wordseye.com) has been used by several thousand users on the web to create over 10,000 scenes. The system relies on a large database of 3D models and poses to depict entities and actions. We describe how the current version of the system incorporates the type of lexical and real-world knowledge needed to depict scenes from language.
منابع مشابه
VigNet: Grounding Language in Graphics using Frame Semantics
This paper introduces Vignette Semantics, a lexical semantic theory based on Frame Semantics that represents conceptual and graphical relations. We also describe a lexical resource that implements this theory, VigNet, and its application in text-to-scene generation.
متن کاملApplication of Frame Semantics to Teaching Seeing and Hearing Vocabulary to Iranian EFL Learners
A term in one language rarely has an absolute synonymous meaning in the same language; besides, it rarely has an equivalent meaning in an L2. English synonyms of seeing and hearing are particularly grammatically and semantically different. Frame semantics is a good tool for discovering differences between synonymous words in L2 and differences between supposed L1 and L2 equivalents. Vocabulary ...
متن کاملTranslation and Hybridity in Scenes and Frames Semantics
The present study is a theoretical attempt to illustrate how Fillmore's Scenes and Frames Semantics (SFS) could be employed as a framework to portray the process of understanding and translating hybrid texts. It first reviews the origin of SFS; then it maps SFS onto Nida’s linguistic model of translation process and the Interpretive Theory of Translation; it examines in the next section, withi...
متن کاملScene Text Area Detection from Video
Text detection from videos is a well known research area. Especially the detection of static superimposed text such as captions has been researched successfully, but makes many assumptions that question the applicability of those algorithms for moving scene text. In this dissertation, I propose a scene text area detection approach that includes a simple key frame extraction, feature extraction,...
متن کاملUnderstanding Descriptions of Visual Scenes Using Graph Grammars
Teaching computers to understand the meaning of natural language text has long been an important goal for Artificial Intelligence. The focus of my work is on the interpretation of descriptions of visual scenes such as ‘A man is sitting on a chair and using the computer’. One application of this research is the automatic generation of 3D scenes (Coyne and Sproat 2001), such as the one in Figure ...
متن کاملNatural scene text localization using edge color signature
Localizing text regions in images taken from natural scenes is one of the challenging problems dueto variations in font, size, color and orientation of text. In this paper, we introduce a new concept socalled Edge Color Signature for localizing text regions in an image. This method is able to localizeboth Farsi and English texts. In the proposed method rst a pyramid using diff...
متن کامل