{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:27:27Z","timestamp":1750307247775,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,6,5]],"date-time":"2012-06-05T00:00:00Z","timestamp":1338854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,6,5]]},"DOI":"10.1145\/2324796.2324805","type":"proceedings-article","created":{"date-parts":[[2012,7,3]],"date-time":"2012-07-03T11:53:15Z","timestamp":1341316395000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["SUPER"],"prefix":"10.1145","author":[{"given":"Yu-Gang","family":"Jiang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2012,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"TRECVID multimedia event detection track. http:\/\/www.nist.gov\/itl\/iad\/mig\/med.cfm\/.  TRECVID multimedia event detection track. http:\/\/www.nist.gov\/itl\/iad\/mig\/med.cfm\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282352"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"e_1_3_2_1_5_1","volume-title":"Chang. Columbia-UCF TRECVID2010 multimedia event detection: Combining multiple modalities, contextual concepts, and temporal matching. In Proc. of NIST TRECVID Workshop","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 Proc. of NIST TRECVID Workshop , 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 Proc. of NIST TRECVID Workshop, 2010."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888212.1888257"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034776"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000027790.02288.f2"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70822"},{"key":"e_1_3_2_1_15_1","volume-title":"BBN VISER TRECVID 2011 multimedia event detection system. In Proc. of NIST TRECVID Workshop","author":"Natarajan P.","year":"2011","unstructured":"P. Natarajan and et al . BBN VISER TRECVID 2011 multimedia event detection system. In Proc. of NIST TRECVID Workshop , 2011 . P. Natarajan and et al. BBN VISER TRECVID 2011 multimedia event detection system. In Proc. of NIST TRECVID Workshop, 2011."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.264"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_38"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888089.1888101"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. of IEEE Conference on Computer Vision and Pattern Recognition","author":"Schindler K.","year":"2008","unstructured":"K. Schindler and L. van Gool . Action snippets : How many frames does human action recognition require ? In Proc. of IEEE Conference on Computer Vision and Pattern Recognition , 2008 . K. Schindler and L. van Gool. Action snippets: How many frames does human action recognition require? In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2008."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587503"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2331"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052027"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of British Machine Vision Conference","author":"Yu T.-H.","year":"2010","unstructured":"T.-H. Yu , T.-K. Kim , and R. Cipolla . Real-time action recognition by sptiotemoral semantic and structural forests . In Proc. of British Machine Vision Conference , 2010 . T.-H. Yu, T.-K. Kim, and R. Cipolla. Real-time action recognition by sptiotemoral semantic and structural forests. In Proc. of British Machine Vision Conference, 2010."}],"event":{"name":"ICMR '12: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Hong Kong China","acronym":"ICMR '12"},"container-title":["Proceedings of the 2nd ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2324796.2324805","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2324796.2324805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:52:09Z","timestamp":1750243929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2324796.2324805"}},"subtitle":["towards real-time event recognition in internet videos"],"short-title":[],"issued":{"date-parts":[[2012,6,5]]},"references-count":27,"alternative-id":["10.1145\/2324796.2324805","10.1145\/2324796"],"URL":"https:\/\/doi.org\/10.1145\/2324796.2324805","relation":{},"subject":[],"published":{"date-parts":[[2012,6,5]]},"assertion":[{"value":"2012-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}