@inproceedings{5537f8dbb00a450796b5df25ca3297c6,
title = "A visual language model for estimating object pose and structure in a generative visual domain",
abstract = "We present a generative domain of visual objects by analogy to the generative nature of human language. Just as small inventories of phonemes and words combine in a grammatical fashion to yield myriad valid words and utterances, a small inventory of physical parts combine in a grammatical fashion to yield myriad valid assemblies. We apply the notion of a language model from speech recognition to this visual domain to similarly improve the performance of the recognition process over what would be possible by only applying recognizers to the components. Unlike the context-free models for human language, our visual language models are context sensitive and formulated as stochastic constraint-satisfaction problems. And unlike the situation for human language where all components are observable, our methods deal with occlusion, successfully recovering object structure despite unobservable components. We demonstrate our system with an integrated robotic system for disassembling structures that performs whole-scene reconstruction consistent with a language model in the presence of noisy feature detectors.",
author = "Siddharth Narayanaswamy and Andrei Barbu and Siskind, {Jeffrey Mark}",
year = "2011",
month = aug,
day = "15",
doi = "10.1109/ICRA.2011.5980161",
language = "English",
isbn = "978-1-61284-386-5",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "4854--4860",
booktitle = "2011 IEEE International Conference on Robotics and Automation",
address = "United States",
note = "2011 IEEE International Conference on Robotics and Automation, ICRA 2011 ; Conference date: 09-05-2011 Through 13-05-2011",
}