Title | ||
---|---|---|
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 de- scribing 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 suppres- sion 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. |
Year | DOI | Venue |
---|---|---|
2007 | null | Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference |
Keywords | Field | DocType |
top down processing,probability distribution,graph representation,bottom up | Automatic summarization,Object detection,Pattern recognition,Polynomial,Inference,Segmentation,Computer science,Probability distribution,Artificial intelligence,Parsing,Graph (abstract data type),Machine learning | Conference |
Volume | Issue | ISSN |
null | null | null |
Citations | PageRank | References |
36 | 1.98 | 16 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuanhao Chen | 1 | 325 | 30.63 |
Long Zhu | 2 | 522 | 64.76 |
Chenxi Lin | 3 | 537 | 29.26 |
Alan L. Yuille | 4 | 10339 | 1902.01 |
Hong-Jiang ZHANG | 5 | 17378 | 1393.22 |