Recursive Compositional Models for Vision: Description and Review of Recent Work
- Authors
- Zhu, Long (Leo); Chen, Yuanhao; Yuille, Alan
- Issue Date
- 9월-2011
- Publisher
- SPRINGER
- Keywords
- Computer vision; Image processing; Machine learning; Object detection; Image parsing
- Citation
- JOURNAL OF MATHEMATICAL IMAGING AND VISION, v.41, no.1-2, pp.122 - 146
- Indexed
- SCIE
SCOPUS
- Journal Title
- JOURNAL OF MATHEMATICAL IMAGING AND VISION
- Volume
- 41
- Number
- 1-2
- Start Page
- 122
- End Page
- 146
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/111687
- DOI
- 10.1007/s10851-011-0282-2
- ISSN
- 0924-9907
- Abstract
- This paper describes and reviews a class of hierarchical probabilistic models of images and objects. Visual structures are represented in a hierarchical form where complex structures are composed of more elementary structures following a design principle of recursive composition. Probabilities are defined over these structures which exploit properties of the hierarchy-e.g. long range spatial relationships can be represented by local potentials at the upper levels of the hierarchy. The compositional nature of this representation enables efficient learning and inference algorithms. In particular, parts can be shared between different object models. Overall the architecture of Recursive Compositional Models (RCMs) provides a balance between statistical and computational complexity. The goal of this paper is to describe the basic ideas and common themes of RCMs, to illustrate their success on a range of vision tasks, and to gives pointers to the literature. In particular, we show that RCMs generally give state of the art results when applied to a range of different vision tasks and evaluated on the leading benchmarked datasets.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Brain and Cognitive Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.