{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:17:45Z","timestamp":1784391465569,"version":"3.55.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319105987","type":"print"},{"value":"9783319105994","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10599-4_35","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T03:37:13Z","timestamp":1407987433000},"page":"540-555","source":"Crossref","is-referenced-by-count":320,"title":["Category-Specific Video Summarization"],"prefix":"10.1007","author":[{"given":"Danila","family":"Potapov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthijs","family":"Douze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaid","family":"Harchaoui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhou, F., Liu, W., De la Torre, F., Liu, Y.: Unsupervised summarization of rushes videos. In: ACM Multimedia (2010)","DOI":"10.1145\/1873951.1874069"},{"issue":"1","key":"35_CR2","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","volume":"32","author":"S. Avila de","year":"2011","unstructured":"de Avila, S., Lopes, A., et al.: VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recognition Letters\u00a032(1), 56\u201368 (2011)","journal-title":"Pattern Recognition Letters"},{"key":"35_CR3","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"issue":"4","key":"35_CR4","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1109\/TMM.2012.2185041","volume":"14","author":"M. Wang","year":"2012","unstructured":"Wang, M., Hong, R., Li, G., Zha, Z.J., Yan, S., Chua, T.S.: Event driven web video summarization by tag localization and key-shot identification. Transactions on Multimedia\u00a014(4), 975\u2013985 (2012)","journal-title":"Transactions on Multimedia"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Khosla, A., Hamid, R., Lin, C.J., Sundaresan, N.: Large-scale video summarization using web-image priors. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.348"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Lu, Z., Grauman, K.: Story-driven summarization for egocentric video. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.350"},{"issue":"1","key":"35_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/1198302.1198305","volume":"3","author":"B.T. Truong","year":"2007","unstructured":"Truong, B.T., Venkatesh, S.: Video abstraction: A systematic review and classification. ACM Transactions on Multimedia Computing, Communications, and Applications\u00a03(1), 3 (2007)","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Over, P., Smeaton, A.F., Awad, G.: The Trecvid 2008 BBC rushes summarization evaluation. In: 2nd ACM TRECVID Video Summarization Workshop (2008)","DOI":"10.1145\/1463563.1463564"},{"key":"35_CR9","unstructured":"Ma, Y.F., Hua, X.S., Lu, L., Zhang, H.J.: A generic framework of user attention model and its application in video summarization. Transactions on Multimedia (2005)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Li, K., Oh, S., Perera, A.G.A., Fu, Y.: A videography analysis framework for video retrieval and summarization. In: BMVC (2012)","DOI":"10.5244\/C.26.126"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Ngo, C.W., Ma, Y.F., Zhang, H.J.: Video summarization and scene detection by graph modeling. Circuits and Systems for Video Technology 15(2) (2005)","DOI":"10.1109\/TCSVT.2004.841694"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Divakaran, A., Peker, K., Radhakrishnan, R., Xiong, Z., Cabasson, R.: Video summarization using Mpeg-7 motion activity and audio descriptors. In: Video Mining, vol.\u00a06. Springer (2003)","DOI":"10.1007\/978-1-4757-6928-9_4"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Xie, L., Xu, P., Chang, S.F., Divakaran, A., Sun, H.: Structure analysis of soccer video with domain knowledge and hidden markov models. Pattern Recognition Letters\u00a025(7) (2004)","DOI":"10.1016\/j.patrec.2004.01.005"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Rui, Y., Gupta, A., Acero, A.: Automatically extracting highlights for TV baseball programs. In: ACM Multimedia (2000)","DOI":"10.1145\/354384.354443"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Sundaram, H., Xie, L., Chang, S.F.: A utility framework for the automatic generation of audio-visual skims. In: ACM Multimedia (2002)","DOI":"10.1145\/641007.641042"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xing, E.P.: Quasi real-time summarization for consumer videos. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.322"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Cong, Y., Yuan, J., Luo, J.: Towards scalable summarization of consumer videos via sparse dictionary selection. Transactions on Multimedia (2012)","DOI":"10.1109\/TMM.2011.2166951"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Kim, G., Sigal, L., Xing, E.P.: Joint summarization of large-scale collections of web images and videos for storyline reconstruction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.538"},{"key":"35_CR19","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: ACL Workshop on Text Summarization Branches, pp. 74\u201381 (2004)"},{"issue":"3","key":"35_CR20","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1145\/1073204.1073232","volume":"24","author":"D. Hoiem","year":"2005","unstructured":"Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. ACM Transactions on Graphics\u00a024(3), 577\u2013584 (2005)","journal-title":"ACM Transactions on Graphics"},{"key":"35_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/978-3-642-15555-0_26","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J. Tighe","year":"2010","unstructured":"Tighe, J., Lazebnik, S.: SuperParsing: Scalable nonparametric image parsing with superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol.\u00a06315, pp. 352\u2013365. Springer, Heidelberg (2010)"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Lezama, J., Alahari, K., Sivic, J., Laptev, I.: Track to the future: Spatio-temporal video segmentation with long-range motion cues. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.6044588"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Massoudi, A., Lefebvre, F., Demarty, C.H., Oisel, L., Chupeau, B.: A video fingerprint based on visual digest and local fingerprints. In: ICIP (2006)","DOI":"10.1109\/ICIP.2006.312834"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Chasanis, V., Kalogeratos, A., Likas, A.: Movie segmentation into scenes and chapters using locally weighted bag of visual words. In: CIVR (2009)","DOI":"10.1145\/1646396.1646439"},{"key":"35_CR26","unstructured":"Kay, S.M.: Fundamentals of Statistical signal processing, vol. 2: Detection theory. Prentice Hall PTR (1998)"},{"key":"35_CR27","unstructured":"Harchaoui, Z., Bach, F., Moulines, E.: Kernel change-point analysis. In: NIPS (2008)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Harchaoui, Z., Capp\u00e9, O.: Retrospective mutiple change-point estimation with kernels. In: IEEE Workshop on Statistical Signal Processing, pp. 768\u2013772 (2007)","DOI":"10.1109\/SSP.2007.4301363"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer (2009)","DOI":"10.1007\/978-0-387-84858-7"},{"key":"35_CR30","unstructured":"Arlot, S., Celisse, A., Harchaoui, Z.: Kernel change-point detection. arXiv:1202.3878 (2012)"},{"key":"35_CR31","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1145\/964965.808600","volume":"18","author":"F.C. Crow","year":"1984","unstructured":"Crow, F.C.: Summed-area tables for texture mapping. ACM SIGGRAPH Computer Graphics\u00a018, 207\u2013212 (1984)","journal-title":"ACM SIGGRAPH Computer Graphics"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Action and Event Recognition with Fisher Vectors on a Compact Feature Set. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.228"},{"key":"35_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1007\/978-3-642-33709-3_49","volume-title":"Computer Vision \u2013 ECCV 2012","author":"L. Cao","year":"2012","unstructured":"Cao, L., Mu, Y., Natsev, A., Chang, S.-F., Hua, G., Smith, J.R.: Scene aligned pooling for complex video recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol.\u00a07573, pp. 688\u2013701. Springer, Heidelberg (2012)"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization with actoms. PAMI (2013)","DOI":"10.1109\/TPAMI.2013.65"},{"key":"35_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F. Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 143\u2013156. Springer, Heidelberg (2010)"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. IJCV (2013)","DOI":"10.1007\/s11263-012-0594-8"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to information retrieval, Cambridge, vol.\u00a01 (2008)","DOI":"10.1017\/CBO9780511809071"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10599-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T09:31:34Z","timestamp":1575279094000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10599-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105987","9783319105994"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}