{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T14:59:28Z","timestamp":1761058768616},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1109\/iccv.2007.4408877","type":"proceedings-article","created":{"date-parts":[[2008,1,4]],"date-time":"2008-01-04T20:34:53Z","timestamp":1199478893000},"page":"1-8","source":"Crossref","is-referenced-by-count":12,"title":["Learning Structured Appearance Models from Captioned Images of Cluttered Scenes"],"prefix":"10.1109","author":[{"given":"Michael","family":"Jamieson","sequence":"first","affiliation":[]},{"given":"Afsaneh","family":"Fazly","sequence":"additional","affiliation":[]},{"given":"Sven","family":"Dickinson","sequence":"additional","affiliation":[]},{"given":"Suzanne","family":"Stevenson","sequence":"additional","affiliation":[]},{"given":"Sven","family":"Wachsmuth","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.325"},{"key":"ref11","article-title":"PCA-SIFT: A more distinctive representation for local image descriptors","author":"ke","year":"0","journal-title":"CVPR-04 3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref13","article-title":"Video data mining using configurations of viewpoint invariant regions","author":"sivic","year":"0","journal-title":"CVPRW '04"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1119212.1119216"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315239"},{"key":"ref6","article-title":"Weakly supervised learning of part-based spatial models for visual object recognition","author":"crandall","year":"0","journal-title":"ECCV'06"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVL.1998.694480"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315274"},{"key":"ref7","article-title":"Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary","author":"duygulu","year":"0","journal-title":"ECCV '02"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315253"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937654"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.142"}],"event":{"name":"2007 IEEE 11th International Conference on Computer Vision","start":{"date-parts":[[2007,10,14]]},"location":"Rio de Janeiro, Brazil","end":{"date-parts":[[2007,10,21]]}},"container-title":["2007 IEEE 11th International Conference on Computer Vision"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4408818\/4408819\/04408877.pdf?arnumber=4408877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T21:20:00Z","timestamp":1489699200000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4408877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/iccv.2007.4408877","relation":{},"subject":[],"published":{"date-parts":[[2007]]}}}