Corpus ID: 59828464

BISHOP|BLENDER: Spatially Grounded Language Understanding in 3D Modelling Software

@inproceedings{Gorniak2009BISHOPBLENDERSG,
  title={BISHOP|BLENDER: Spatially Grounded Language Understanding in 3D Modelling Software},
  author={Peter Gorniak},
  year={2009}
}
We present BISHOP|BLENDER, an augmentation of the 3D modelling application Blender (Blender Foundation , 2003). In the BISHOP project (Gorniak and Roy, 2004) we investigated how people describe objects in visual scenes using spatial language, and built a visually grounded language understanding system that performed well in understanding visually referring expressions. One application of this work is in applications that share a virtual world with the user, such as 3D modelling applications… Expand
A natural-language-based 3D-CG system with shape estimation for unknown words
TLDR
This work has improved their system for creating three dimensional computer graphics so that it can understand a wider variety of words and sentences than the previous system, and compared the performance of six different methods for the shape estimation. Expand

References

SHOWING 1-9 OF 9 REFERENCES
Grounded Semantic Composition for Visual Scenes
TLDR
The implementation of word level visually-grounded semantics and their embedding in a compositional parsing framework is described and how visual context influences the semantics of utterances is revealed. Expand
Augmenting user interfaces with adaptive speech commands
TLDR
A system that augments any unmodified Java application with an adaptive speech interface that learns to associate spoken words and utterances with interface actions such as button clicks so that selected interface functions migrate from keyboard and mouse to speech. Expand
Word learning as Bayesian inference.
The authors present a Bayesian framework for understanding how adults and children learn the meanings of words. The theory explains how learners can generalize meaningfully from just one or a fewExpand
Grounded compositional semantics for visual scenes
  • Journal of Artificial Intelligence Research, 21:429–470.
  • 2004
Grounded compositional semantics for visual scenes
  • Journal of Artificial Intelligence Research
  • 2004
Mitsubishi Electric Research Lab- oratories Sphinx 4 Java Speech Rec- ognizer
  • Mitsubishi Electric Research Lab- oratories Sphinx 4 Java Speech Rec- ognizer
  • 2004
Blender 3 D graphics creation suite Sphinx 4 Java Speech Recognizer
  • 2003
Blender 3D graphics creation suite
  • Blender 3D graphics creation suite
  • 2003