{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T08:46:23Z","timestamp":1769589983619,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,11,3]],"date-time":"2014-11-03T00:00:00Z","timestamp":1414972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Dutch national program COMMIT"},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center","award":["D11PC20067"],"award-info":[{"award-number":["D11PC20067"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,11,3]]},"DOI":"10.1145\/2647868.2654913","type":"proceedings-article","created":{"date-parts":[[2014,10,31]],"date-time":"2014-10-31T19:32:56Z","timestamp":1414783976000},"page":"17-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["VideoStory"],"prefix":"10.1145","author":[{"given":"Amirhossein","family":"Habibian","sequence":"first","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Thomas","family":"Mensink","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Cees G.M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2014,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"e_1_3_2_1_2_1","volume-title":"TRECVID","author":"Aly R.","year":"2013","unstructured":"R. Aly The AXES submissions at trecvid 2013 . In TRECVID , 2013 . R. Aly et al. The AXES submissions at trecvid 2013. In TRECVID, 2013."},{"key":"e_1_3_2_1_3_1","volume-title":"IJCAI","author":"Banerjee S.","year":"2003","unstructured":"S. Banerjee and T. Pedersen . Extended gloss overlaps as a measure of semantic relatedness . In IJCAI , 2003 . S. Banerjee and T. Pedersen. Extended gloss overlaps as a measure of semantic relatedness. In IJCAI, 2003."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1886063.1886114"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502155"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433456"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","volume-title":"NAACL","author":"Dodge J.","year":"2012","unstructured":"J. Dodge Detecting visual text . In NAACL , 2012 . J. Dodge et al. Detecting visual text. In NAACL, 2012."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"e_1_3_2_1_11_1","volume-title":"Recommendations for recognizing video events by concept vocabularies. CVIU, 124","author":"Habibian A.","year":"2014","unstructured":"A. Habibian and C. Snoek . Recommendations for recognizing video events by concept vocabularies. CVIU, 124 , 2014 . A. Habibian and C. Snoek. Recommendations for recognizing video events by concept vocabularies. CVIU, 124, 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_31"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"e_1_3_2_1_16_1","volume-title":"TRECVID","author":"Jiang Y.-G.","year":"2010","unstructured":"Y.-G. Jiang , X. Zeng , G. Ye , S. Bhattacharya , D. Ellis , M. Shah , and S.-F. Chang . Columbia-ucf trecvid2010 multimedia event detection: Combining multiple modalities, contextual concepts, and temporal matching . In TRECVID , 2010 . Y.-G. Jiang, X. Zeng, G. Ye, S. Bhattacharya, D. Ellis, M. Shah, and S.-F. Chang. Columbia-ucf trecvid2010 multimedia event detection: Combining multiple modalities, contextual concepts, and temporal matching. In TRECVID, 2010."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1178677.1178712"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075150"},{"key":"e_1_3_2_1_19_1","volume-title":"NIPS","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. Hinton . Imagenet classification with deep convolutional neural networks . In NIPS , 2012 . A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012."},{"key":"e_1_3_2_1_20_1","volume-title":"ACL","author":"Kuznetsova P.","year":"2013","unstructured":"P. Kuznetsova , V. Ordonez , A. Berg , T. Berg , and Y. Choi . Generalizing image captions for image-text parallel corpus . In ACL , 2013 . P. Kuznetsova, V. Ordonez, A. Berg, T. Berg, and Y. Choi. Generalizing image captions for image-text parallel corpus. In ACL, 2013."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6475038"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393414"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502119"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461466.2461507"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2536798"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2168948"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354988"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101288"},{"key":"e_1_3_2_1_29_1","volume-title":"TRECVID 2013-an overview of the goals, tasks, data, evaluation mechanisms and metrics. In TRECVID","author":"Over P.","year":"2013","unstructured":"P. Over , J. Fiscus , G. Sanders , TRECVID 2013-an overview of the goals, tasks, data, evaluation mechanisms and metrics. In TRECVID , 2013 . P. Over, J. Fiscus, G. Sanders, et al. TRECVID 2013-an overview of the goals, tasks, data, evaluation mechanisms and metrics. In TRECVID, 2013."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"e_1_3_2_1_33_1","volume-title":"LREC","author":"Strassel S.","year":"2012","unstructured":"S. Strassel : Heterogeneous audio visual internet collection . In LREC , 2012 . S. Strassel et al. Creating havic: Heterogeneous audio visual internet collection. In LREC, 2012."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248114"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.08.002"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.154"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010008"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.127"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2283696.2283856"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_52"}],"event":{"name":"MM '14: 2014 ACM Multimedia Conference","location":"Orlando Florida USA","acronym":"MM '14","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 22nd ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2647868.2654913","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2647868.2654913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:56:09Z","timestamp":1750229769000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2647868.2654913"}},"subtitle":["A New Multimedia Embedding for Few-Example Recognition and Translation of Events"],"short-title":[],"issued":{"date-parts":[[2014,11,3]]},"references-count":41,"alternative-id":["10.1145\/2647868.2654913","10.1145\/2647868"],"URL":"https:\/\/doi.org\/10.1145\/2647868.2654913","relation":{},"subject":[],"published":{"date-parts":[[2014,11,3]]},"assertion":[{"value":"2014-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}