{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:49:03Z","timestamp":1763459343807,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,22]],"date-time":"2016-06-22T00:00:00Z","timestamp":1466553600000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1251276"],"award-info":[{"award-number":["1251276"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC52-07NA27344"],"award-info":[{"award-number":["DE-AC52-07NA27344"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,22]]},"DOI":"10.1145\/2671188.2749396","type":"proceedings-article","created":{"date-parts":[[2015,6,22]],"date-time":"2015-06-22T11:37:08Z","timestamp":1434973028000},"page":"611-614","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Audio-Based Multimedia Event Detection with DNNs and Sparse Sampling"],"prefix":"10.1145","author":[{"given":"Khalid","family":"Ashraf","sequence":"first","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Elizalde","sequence":"additional","affiliation":[{"name":"International Computer Science Institute, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Forrest","family":"Iandola","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Moskewicz","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"Bernd","sequence":"additional","affiliation":[{"name":"International Computer Science Institute, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerald","family":"Friedland","sequence":"additional","affiliation":[{"name":"International Computer Science Institute, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"J. Bernd D. Borth B. Elizalde G. Friedland H. Gallagher L. Gottlieb A. Janin S. Karabashlieva J. Takahashi and J. Won. The YLI-MED corpus: Characteristics procedures and plans (ICSI Technical Report TR-15-001). arXiv:1503.04250 2015."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of TRECVID 2012","author":"Cheng H.","year":"2012","unstructured":"H. Cheng, J. Liu, S. Ali, O. Javed, Q. Yu, A. Tamrakar, A. Divakaran, H. S. Sawhney, R. Manmatha, J. Allan, A. Hauptmann, M. Shah, S. Bhattacharya, A. Dehghan, G. Friedland, B. M. Elizalde, T. Darrell, M. Witbrock, and J. Curtis. SRI-Sarnoff AURORA system at TRECVID 2012: Multimedia event detection and recounting. In Proceedings of TRECVID 2012. NIST, USA, 2012."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2013.27"},{"key":"e_1_3_2_1_4_1","volume-title":"SLAM@INTERSPEECH","author":"Elizalde B.","year":"2014","unstructured":"B. Elizalde, M. Ravanelli, and G. Friedland. Audio-concept features and hidden Markov models for multimedia event detection. In SLAM@INTERSPEECH, 2014."},{"key":"e_1_3_2_1_5_1","volume-title":"Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093","author":"Jia Y.","year":"2014","unstructured":"Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014."},{"key":"e_1_3_2_1_6_1","volume-title":"TRECVID 2013. In Proceedings of TRECVID 2013. NIST, USA","author":"Lan Z.","year":"2013","unstructured":"Z. Lan, L. Jiang, S.-I. Yu, C. Gao, S. Rawat, Y. Cai, S. Xu, H. Shen, X. Li, Y. Wang, W. Sze, Y. Yan, Z. Ma, N. Ballas, D. Meng, W. Tong, Y. Yang, S. Burger, F. Metze, R. Singh, B. Raj, R. Stern, T. Mitamura, E. Nyberg, and A. Hauptmann Informedia @ TRECVID 2013. In Proceedings of TRECVID 2013. NIST, USA, 2013."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890234"},{"key":"e_1_3_2_1_8_1","volume-title":"BBN VISER TRECVID 2012 multimedia event detection and multimedia event recounting systems. In Proceedings of TRECVID 2012. NIST, USA","author":"Natarajan P.","year":"2012","unstructured":"P. Natarajan, P. Natarajan, S. Wu, X. Zhuang, A. Vazquez Reina, S. N. Vitaladevuni, K. Tsourides, C. Andersen, R. Prasad, G. Ye, D. Liu, S.-F. Chang, I. Saleemi, M. Shahand, Y. Ng, B. White, L. Davis, A. Gupta, and I. Haritaoglu. BBN VISER TRECVID 2012 multimedia event detection and multimedia event recounting systems. In Proceedings of TRECVID 2012. NIST, USA, 2012."},{"key":"e_1_3_2_1_9_1","volume-title":"TRECVID 2013 - an overview of the goals, tasks, data, evaluation mechanisms and metrics. In Proceedings of TRECVID 2013. NIST, USA","author":"Over P.","year":"2013","unstructured":"P. Over, G. Awad, M. Michel, J. Fiscus, G. Sanders, W. Kraaij, A. F. Smeaton, and G. Qu\u00e9not. TRECVID 2013 - an overview of the goals, tasks, data, evaluation mechanisms and metrics. In Proceedings of TRECVID 2013. NIST, USA, 2013."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1887176.1887235"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-557"}],"event":{"name":"ICMR '15: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Shanghai China","acronym":"ICMR '15"},"container-title":["Proceedings of the 5th ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749396","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2671188.2749396","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2671188.2749396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:43:38Z","timestamp":1763459018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2671188.2749396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,22]]},"references-count":11,"alternative-id":["10.1145\/2671188.2749396","10.1145\/2671188"],"URL":"https:\/\/doi.org\/10.1145\/2671188.2749396","relation":{},"subject":[],"published":{"date-parts":[[2015,6,22]]},"assertion":[{"value":"2015-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}