{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T11:48:20Z","timestamp":1763466500864,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,3]]},"DOI":"10.1109\/icassp.2012.6288367","type":"proceedings-article","created":{"date-parts":[[2012,9,7]],"date-time":"2012-09-07T15:58:06Z","timestamp":1347033486000},"page":"2273-2276","source":"Crossref","is-referenced-by-count":11,"title":["Multimodal city-verification on flickr videos using acoustic and textual features"],"prefix":"10.1109","author":[{"given":"Howard","family":"Lei","sequence":"first","affiliation":[]},{"given":"Jaeyoung","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Gerald","family":"Friedland","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/3DPVT.2006.80"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383150"},{"key":"18","article-title":"SRILM - An Extensible Language Modeling Toolkit","author":"stolcke","year":"0","journal-title":"Proc Intl Conf Spoken Language Processing Denver Colorado 2002"},{"key":"15","article-title":"Working Notes for the Placing Task at MediaEval 2011","author":"rae","year":"0","journal-title":"Proc of MediaEval 2011"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"year":"0","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/2072508.2072513"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946968"},{"key":"12","first-page":"249","article-title":"LNKnet: Neural Network, Machine Learning, and Statistical Software for Pattern Classification","volume":"6","author":"lippmann","year":"1993","journal-title":"Lincoln Laboratory Journal"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415219"},{"journal-title":"Amazon Mechanical Turk","year":"0","key":"1"},{"key":"10","first-page":"737","article-title":"Video Genetics: A Case Study from YouTube","volume":"1","author":"kender","year":"2005","journal-title":"ICASSP"},{"journal-title":"HMM Toolkit (HTK)","year":"0","key":"7"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"5","article-title":"Comparison of Parametric Representations of MonosyllabicWord Recognition in Continuously Spoken Sentences","author":"davis","year":"0","journal-title":"Proc 1980 ICASSP"},{"key":"4","article-title":"The 2011 ICSI Video Location Estimation System","author":"choi","year":"0","journal-title":"Proc of MediaEval Workshop 2011"},{"key":"9","article-title":"Making Large Scale SVM Learning Practical","author":"joachims","year":"1999","journal-title":"Advances in Kernel Methods - Support Vector Learning"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408995"}],"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\/06288367.pdf?arnumber=6288367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T17:58:02Z","timestamp":1490119082000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6288367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2012.6288367","relation":{},"subject":[],"published":{"date-parts":[[2012,3]]}}}