{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:57:22Z","timestamp":1730296642053,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1109\/siu.2014.6830631","type":"proceedings-article","created":{"date-parts":[[2014,6,20]],"date-time":"2014-06-20T21:51:45Z","timestamp":1403301105000},"page":"1922-1925","source":"Crossref","is-referenced-by-count":1,"title":["Data-driven image captioning with meta-class based retrieval"],"prefix":"10.1109","author":[{"given":"Mert","family":"Kilickaya","sequence":"first","affiliation":[]},{"given":"Erkut","family":"Erdem","sequence":"additional","affiliation":[]},{"given":"Aykut","family":"Erdem","sequence":"additional","affiliation":[]},{"given":"Nazli Ikizler","family":"Cinbis","sequence":"additional","affiliation":[]},{"given":"Ruket","family":"Cakici","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"22","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"17","article-title":"Building the gist of a scene: The role of global image features in recognition","volume":"155","author":"oliva","year":"2006","journal-title":"Visual Perception Progress in Brain Research"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.101"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"15","article-title":"Efficient object category recognition using classemes","author":"torresani","year":"2010","journal-title":"ECCV"},{"key":"16","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"CVPR"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"14","article-title":"Object Bank: A high-level image representation for scene classification & semantic feature sparsification","author":"li","year":"2010","journal-title":"NIPS"},{"journal-title":"The PASCAL Visual Object Classes Challange 2008","year":"2008","author":"everingham","key":"11"},{"key":"12","article-title":"Meta-class features for large-scale object categorization on a budget","author":"bergamo","year":"2012","journal-title":"CVPR"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"3","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"ECCV"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"2","article-title":"Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary","author":"duygulu","year":"2002","journal-title":"ECCV"},{"key":"1","article-title":"Image-to-word transformation based on dividing and vector quantizing images with words","author":"mori","year":"1999","journal-title":"WMISR"},{"key":"10","article-title":"Collecting image annotations using Amazon's mechanical turk","author":"rashtchian","year":"2010","journal-title":"NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"7","article-title":"Corpusguided sentence generation of natural images","author":"yang","year":"2011","journal-title":"EMNLP"},{"key":"6","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"CoNLL"},{"key":"5","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"NIPS"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"9","article-title":"Choosing linguistics over vision to describe images","author":"gupta","year":"2012","journal-title":"AAAI"},{"key":"8","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"EACL"}],"event":{"name":"2014 22nd Signal Processing and Communications Applications Conference (SIU)","start":{"date-parts":[[2014,4,23]]},"location":"Trabzon, Turkey","end":{"date-parts":[[2014,4,25]]}},"container-title":["2014 22nd Signal Processing and Communications Applications Conference (SIU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6820096\/6830164\/06830631.pdf?arnumber=6830631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T13:16:20Z","timestamp":1490274980000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6830631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/siu.2014.6830631","relation":{},"subject":[],"published":{"date-parts":[[2014,4]]}}}