{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:31:27Z","timestamp":1730230287360,"version":"3.28.0"},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,3]]},"DOI":"10.1109\/icassp.2012.6288151","type":"proceedings-article","created":{"date-parts":[[2012,9,7]],"date-time":"2012-09-07T19:58:06Z","timestamp":1347047886000},"page":"1393-1396","source":"Crossref","is-referenced-by-count":2,"title":["From video to text: Semantic driving scene understanding using a coarse-to-fine method"],"prefix":"10.1109","author":[{"given":"Huiyuan","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.232"},{"key":"2","article-title":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","author":"li","year":"0","journal-title":"IEEE European Conference on Computer Vision 2009"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609410"},{"key":"1","first-page":"44","article-title":"Segmentation and recognition using structure from motion point clouds","volume":"1","author":"brostow","year":"2008","journal-title":"IEEE Eur Conf Comput Vis"},{"key":"7","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume":"18","author":"lafferty","year":"2001","journal-title":"IEEE International Conference on Machine Learning"},{"key":"6","first-page":"1","article-title":"Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation","author":"shotton","year":"2006","journal-title":"IEEE Eur Conf Comput Vis"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"4","article-title":"What, where and how many? Combining object detectors and crfs","author":"ladicky","year":"0","journal-title":"European Conference on Computer Vision 2010"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"8","first-page":"335","article-title":"Finding pictures of objects in large collections of images","author":"forsyth","year":"1996","journal-title":"IEEE Eur Conf Comput Vis"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"}],"event":{"name":"ICASSP 2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing","start":{"date-parts":[[2012,3,25]]},"location":"Kyoto, Japan","end":{"date-parts":[[2012,3,30]]}},"container-title":["2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6268628\/6287775\/06288151.pdf?arnumber=6288151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T21:34:23Z","timestamp":1490132063000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6288151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/icassp.2012.6288151","relation":{},"subject":[],"published":{"date-parts":[[2012,3]]}}}