{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T04:01:42Z","timestamp":1746504102590,"version":"3.40.4"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319131672"},{"type":"electronic","value":"9783319131689"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-13168-9_12","type":"book-chapter","created":{"date-parts":[[2014,10,20]],"date-time":"2014-10-20T06:40:02Z","timestamp":1413787202000},"page":"113-122","source":"Crossref","is-referenced-by-count":4,"title":["Semantic Concept Annotation of Consumer Videos at Frame-Level Using Audio"],"prefix":"10.1007","author":[{"given":"Junwei","family":"Liang","sequence":"first","affiliation":[]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Xixi","family":"He","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jieping","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"12_CR1","unstructured":"Snoek, C., Worring, M.: Concept-based Video Retrieval. Foundations and Trends in Information Retrieval (2009)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chang, S.F., Ellis, D., Jiang, W., Lee, K., Yanagawa, A., Loui, A.C., Luo, J.: Large-Scale Multimodal Semantic Concept Detection for Consumer Video. In: International Workshop on Multimedia Information Retrieval (MIR) (2007)","DOI":"10.1145\/1290082.1290118"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Naphade, M.R., Smith, J.R., Tesic, J., Chang, S.F., Hsu, W., Kennedy, L., Hauptmann, A., Curtis, J.: Large-Scale Concept Ontology for Multimedia. IEEE Journal MultiMedia\u00a013(3) (2006)","DOI":"10.1109\/MMUL.2006.63"},{"key":"12_CR4","unstructured":"Over, P., Awad, G., Michel, M., Fiscus, J., Sanders, G., Kraaij, W., Smeaton, A.F., Qu\u00e9enot, G.: TRECVID 2013 \u2013 An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics. In: Proceedings of TRECVID. NIST, USA (2013), http:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv13.papers\/tv13overview.pdf"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Lee, K., Ellis, D.P.W.: Audio-Based Semantic Concept Classificationfor Consumer Video. IEEE Transactions on Audio, Speech, and Language Processing\u00a018(6) (2010)","DOI":"10.1109\/TASL.2009.2034776"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Atrey, P.K., Kankanhalli, M.S., Jain, R.: Information Assimilation Framework for Event Detection in Multimedia Surveillance Systems. In: Multimedia Systems, pp. 239\u2013253 (2006)","DOI":"10.1007\/s00530-006-0063-8"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Kolekar, M.H., Sengupta, S.: Semantic concept extraction from sports video for highlight generation. In: International Conference on Mobile Multimedia Communications (MobiMedia) (2006)","DOI":"10.1145\/1374296.1374324"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Luo, H., Fan, J.: Building Concept Ontology for Medical Video Annotation. In: ACM Multimedia (2006)","DOI":"10.1145\/1180639.1180659"},{"key":"12_CR9","unstructured":"ICEM 2014 Huawei Accurate and Fast Mobile Video Annotation Challenge, http:\/\/www.icme2014.org\/huawei-accurate-and-fast-mobile-video-annotation-challenge"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Wold, E., Blum, T., Keislar, D., Wheaten, J.: Content-based Classification, Search, and Retrieval of Audio. IEEE Multimedia\u00a03(3) (1996)","DOI":"10.1109\/93.556537"},{"key":"12_CR11","unstructured":"Saunders, J.: Real-time Discrimination of Broadcast Speech\/Music. In: ICASSP (1996)"},{"key":"12_CR12","unstructured":"Scheirer, E., Slaney, M.: Construction and Evaluation of a Robust Multifeature Speech\/Music Discriminator. In: ICASSP (1997)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Williams, G., Ellis, D.P.W.: Speech\/Music Discrimination Based on Posterior Probability Features. In: Eurospeech (1999)","DOI":"10.21437\/Eurospeech.1999-176x"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Ma, L., Milner, B., Smith, D.: Acoustic Environment Classification. ACM Transactions on Speech and Language Processing\u00a03(2) (2006)","DOI":"10.1145\/1149290.1149292"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Eronen, A., Peltonen, V., Tuomi, J., Klapuri, A., Fagerlund, S., Sorsa, T., Lorho, G., Huopaniemi, J.: Audio-based Context Recognition. IEEE Trans. on Audio, Speech, and Language Processing\u00a014(1) (2006)","DOI":"10.1109\/TSA.2005.854103"},{"key":"12_CR16","unstructured":"Brown, L., et al.: IBM Research and Columbia University TRECVID-2013 Multimedia Event Detection (MED), Multimedia Event Recounting (MER), Surveillance Event Detection (SED), and Semantic Indexing (SIN) Systems. In: TRECVID Workshop (2013)"},{"key":"12_CR17","unstructured":"Jin, Q., Schulam, F., Rawat, S., Burger, S., Ding, D., Metze, F.: Categorizing Consumer Videos Using Audio. In: Interspeech (2012)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Xue, X.B., Zhou, Z.H.: Distributional Features for Text Categorization. IEEE Transactions on Knowledge and Data Engineering\u00a021(3) (2008)","DOI":"10.1109\/TKDE.2008.166"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR 2007 (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Snoek, C., Worring, M., Koelma, D., Smeulders, A.: Bootstrapping Visual Categorization With Relevant Negatives. IEEE Transactions on Multimedia\u00a015(4) (2013)","DOI":"10.1109\/TMM.2013.2238523"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Maji, S., Berg, A., Malik, J.: Classification using international kernel support vector machines is efficient. In: CVPR 2008 (2008)","DOI":"10.1109\/CVPR.2008.4587630"},{"issue":"1","key":"12_CR22","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TMM.2011.2174782","volume":"14","author":"Z.-J. Zha","year":"2012","unstructured":"Zha, Z.-J., Wang, M., Zheng, Y.-T., Yang, Y., Hong, R., Chua, T.-S.: Interactive Video Indexing with Statistical Active Learning. IEEE Transactions on Multimedia\u00a014(1), 17\u201327 (2012)","journal-title":"IEEE Transactions on Multimedia"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2014"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-13168-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T06:39:47Z","timestamp":1746427187000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-13168-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319131672","9783319131689"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-13168-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}