Part and appearance sharing: Recursive compositional models for multi-view multi-object detection
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object subparts). We represent the set of objects by a family of RCMs where each RCM is a probability distribution defined over a...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
| Online Access: | http://hdl.handle.net/1721.1/71892 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1811082866394660864 |
|---|---|
| author | Zhu, Long Chen, Yuanhao Torralba, Antonio Freeman, William T. Yuille, Alan |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhu, Long Chen, Yuanhao Torralba, Antonio Freeman, William T. Yuille, Alan |
| author_sort | Zhu, Long |
| collection | MIT |
| description | We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object subparts). We represent the set of objects by a family of RCMs where each RCM is a probability distribution defined over a hierarchical graph which corresponds to a specific object and viewpoint. An RCM is constructed from a hierarchy of subparts/subgraphs which are learnt from training data. Part-sharing is used so that different RCMs are encouraged to share subparts/subgraphs which yields a compact representation for the set of objects and which enables efficient inference and learning from a limited number of training samples. In addition, we use appearance-sharing so that RCMs for the same object, but different viewpoints, share similar appearance cues which also helps efficient learning. RCMs lead to a multi-view multi-object detection system. We illustrate RCMs on four public datasets and achieve state-of-the-art performance. |
| first_indexed | 2024-09-23T12:10:56Z |
| format | Article |
| id | mit-1721.1/71892 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:10:56Z |
| publishDate | 2012 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/718922022-10-01T08:37:50Z Part and appearance sharing: Recursive compositional models for multi-view multi-object detection Zhu, Long Chen, Yuanhao Torralba, Antonio Freeman, William T. Yuille, Alan Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Freeman, William T. Zhu, Long Torralba, Antonio Freeman, William T. We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object subparts). We represent the set of objects by a family of RCMs where each RCM is a probability distribution defined over a hierarchical graph which corresponds to a specific object and viewpoint. An RCM is constructed from a hierarchy of subparts/subgraphs which are learnt from training data. Part-sharing is used so that different RCMs are encouraged to share subparts/subgraphs which yields a compact representation for the set of objects and which enables efficient inference and learning from a limited number of training samples. In addition, we use appearance-sharing so that RCMs for the same object, but different viewpoints, share similar appearance cues which also helps efficient learning. RCMs lead to a multi-view multi-object detection system. We illustrate RCMs on four public datasets and achieve state-of-the-art performance. United States. National Geospatial-Intelligence Agency (NEGI-1582-04-0004) United States. Army Research Office. Multidisciplinary University Research Initiative (Grant Number N00014-06-1-0734) United States. Air Force Office of Scientific Research (FA9550- 08-1-0489) National Science Foundation (U.S.). (IIS-0917141) 2012-07-30T17:39:49Z 2012-07-30T17:39:49Z 2010-08 2010-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-6984-0 1063-6919 http://hdl.handle.net/1721.1/71892 Detection, Multi- et al. “Part and Appearance Sharing: Recursive Compositional Models for Multi-view.” IEEE, 2010. 1919–1926. © Copyright 2010 IEEE https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/ 10.1109/CVPR.2010.5539865 2010 IEEE Conference on Computer Vision and Pattern Recognition Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers (IEEE) IEEE |
| spellingShingle | Zhu, Long Chen, Yuanhao Torralba, Antonio Freeman, William T. Yuille, Alan Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title | Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title_full | Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title_fullStr | Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title_full_unstemmed | Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title_short | Part and appearance sharing: Recursive compositional models for multi-view multi-object detection |
| title_sort | part and appearance sharing recursive compositional models for multi view multi object detection |
| url | http://hdl.handle.net/1721.1/71892 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT zhulong partandappearancesharingrecursivecompositionalmodelsformultiviewmultiobjectdetection AT chenyuanhao partandappearancesharingrecursivecompositionalmodelsformultiviewmultiobjectdetection AT torralbaantonio partandappearancesharingrecursivecompositionalmodelsformultiviewmultiobjectdetection AT freemanwilliamt partandappearancesharingrecursivecompositionalmodelsformultiviewmultiobjectdetection AT yuillealan partandappearancesharingrecursivecompositionalmodelsformultiviewmultiobjectdetection |