Rapid Inference on a Novel AND/OR Graph for Object Detection, Segmentation and Parsing
Abstract
In this paper we formulate a novel AND/OR graph representation capable of describing the different configurations of deformable articulated objects such as horses. The representation makes use of the summarization principle so that lower level nodes in the graph only pass on summary statistics to the higher level nodes. The probability distributions are invariant to position, orientation, and scale. We develop a novel inference algorithm that combined a bottom-up process for proposing configurations for horses together with a top-down process for refining and validating these proposals. The strategy of surround suppression is applied to ensure that the inference time is polynomial in the size of input data. The algorithm was applied to the tasks of detecting, segmenting and parsing horses. We demonstrate that the algorithm is fast and comparable with the state of the art approaches.
Cite
Text
Chen et al. "Rapid Inference on a Novel AND/OR Graph for Object Detection, Segmentation and Parsing." Neural Information Processing Systems, 2007.Markdown
[Chen et al. "Rapid Inference on a Novel AND/OR Graph for Object Detection, Segmentation and Parsing." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/chen2007neurips-rapid/)BibTeX
@inproceedings{chen2007neurips-rapid,
title = {{Rapid Inference on a Novel AND/OR Graph for Object Detection, Segmentation and Parsing}},
author = {Chen, Yuanhao and Zhu, Long and Lin, Chenxi and Zhang, Hongjiang and Yuille, Alan L.},
booktitle = {Neural Information Processing Systems},
year = {2007},
pages = {289-296},
url = {https://mlanthology.org/neurips/2007/chen2007neurips-rapid/}
}