Nonparametric scene parsing: Label transfer via dense scene alignment
In this paper we propose a novel nonparametric approach for object recognition and scene parsing using dense scene alignment. Given an input image, we retrieve its best matches from a large database with annotated images using our modified, coarse-to-fine SIFT flow algorithm that aligns the structur...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/59843 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1811088103787462656 |
|---|---|
| author | Torralba, Antonio Liu, Ce Yuen, Jenny |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Torralba, Antonio Liu, Ce Yuen, Jenny |
| author_sort | Torralba, Antonio |
| collection | MIT |
| description | In this paper we propose a novel nonparametric approach for object recognition and scene parsing using dense scene alignment. Given an input image, we retrieve its best matches from a large database with annotated images using our modified, coarse-to-fine SIFT flow algorithm that aligns the structures within two images. Based on the dense scene correspondence obtained from the SIFT flow, our system warps the existing annotations, and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on a challenging database. Compared to existing object recognition approaches that require training for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure. |
| first_indexed | 2024-09-23T13:56:20Z |
| format | Article |
| id | mit-1721.1/59843 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:56:20Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/598432022-10-01T18:07:13Z Nonparametric scene parsing: Label transfer via dense scene alignment Torralba, Antonio Liu, Ce Yuen, Jenny Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Torralba, Antonio Torralba, Antonio Liu, Ce Yuen, Jenny In this paper we propose a novel nonparametric approach for object recognition and scene parsing using dense scene alignment. Given an input image, we retrieve its best matches from a large database with annotated images using our modified, coarse-to-fine SIFT flow algorithm that aligns the structures within two images. Based on the dense scene correspondence obtained from the SIFT flow, our system warps the existing annotations, and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on a challenging database. Compared to existing object recognition approaches that require training for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure. Royal Dutch/Shell Group United States. National Geospatial-Intelligence Agency (NEGI-1582-04-0004) United States. Office of Naval Research (MURI Grant N00014-06-1-0734) National Science Foundation (U.S.) ((NSF Career award (IIS 0747120)) National Defense Science and Engineering Graduate Fellowship 2010-11-05T19:32:14Z 2010-11-05T19:32:14Z 2009-08 2009-06 Article http://purl.org/eprint/type/JournalArticle 978-1-4244-3992-8 1063-6919 INSPEC Accession Number: 10836097 http://hdl.handle.net/1721.1/59843 Ce Liu, J. Yuen, and A. Torralba. “Nonparametric scene parsing: Label transfer via dense scene alignment.” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 2009. 1972-1979. © 2009 Institute of Electrical and Electronics Engineers. https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPRW.2009.5206536 IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 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 |
| spellingShingle | Torralba, Antonio Liu, Ce Yuen, Jenny Nonparametric scene parsing: Label transfer via dense scene alignment |
| title | Nonparametric scene parsing: Label transfer via dense scene alignment |
| title_full | Nonparametric scene parsing: Label transfer via dense scene alignment |
| title_fullStr | Nonparametric scene parsing: Label transfer via dense scene alignment |
| title_full_unstemmed | Nonparametric scene parsing: Label transfer via dense scene alignment |
| title_short | Nonparametric scene parsing: Label transfer via dense scene alignment |
| title_sort | nonparametric scene parsing label transfer via dense scene alignment |
| url | http://hdl.handle.net/1721.1/59843 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT torralbaantonio nonparametricsceneparsinglabeltransferviadensescenealignment AT liuce nonparametricsceneparsinglabeltransferviadensescenealignment AT yuenjenny nonparametricsceneparsinglabeltransferviadensescenealignment |