{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:12:39Z","timestamp":1744200759449,"version":"3.37.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319681290"},{"type":"electronic","value":"9783319681306"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-68130-6_5","type":"book-chapter","created":{"date-parts":[[2017,10,10]],"date-time":"2017-10-10T00:53:35Z","timestamp":1507596815000},"page":"56-67","source":"Crossref","is-referenced-by-count":1,"title":["A Video Library System Using Scene Detection and Automatic Tagging"],"prefix":"10.1007","author":[{"given":"Lorenzo","family":"Baraldi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Costantino","family":"Grana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,11]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Apostolidis, E., Mezaris, V.: Fast shot segmentation combining global and local visual descriptors. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6583\u20136587 (2014)","DOI":"10.1109\/ICASSP.2014.6854873"},{"issue":"4","key":"5_CR2","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s00371-016-1320-2","volume":"33","author":"F Balducci","year":"2017","unstructured":"Balducci, F., Grana, C., Cucchiara, R.: Affective level design for a role-playing videogame evaluated by a brain-computer interface and machine learning methods. Vis. Comput. 33(4), 413\u2013427 (2017)","journal-title":"Vis. Comput."},{"key":"5_CR3","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.cviu.2015.05.009","volume":"140","author":"L Ballan","year":"2015","unstructured":"Ballan, L., Bertini, M., Serra, G., Del Bimbo, A.: A data-driven approach for tag refinement and localization in web videos. Comput. Vis. Image Underst. 140, 58\u201367 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"5_CR4","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: A deep siamese network for scene detection in broadcast videos. In: Proceedings of the 23rd Annual ACM Conference on Multimedia Conference (MM 2015), pp. 1199\u20131202 (2015). http:\/\/doi.acm.org\/10.1145\/2733373.2806316"},{"key":"5_CR5","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: Scene-driven retrieval in edited videos using aesthetic and semantic deep features. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval (ICMR 2016), pp. 23\u201329 (2016). http:\/\/doi.acm.org\/10.1145\/2911996.2912012"},{"issue":"5","key":"5_CR6","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1109\/TMM.2016.2644872","volume":"19","author":"L Baraldi","year":"2017","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: Recognizing and presenting the storytelling video structure with deep multimodal networks. IEEE Trans. Multimed. 19(5), 955\u2013968 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Bolelli, F., Borghi, G., Grana, C.: Historical handwritten text images word spotting through sliding window HOG features. In: 19th International Conference on Image Analysis and Processing (2017)","DOI":"10.1007\/978-3-319-68560-1_65"},{"issue":"1","key":"5_CR8","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/TMM.2008.2008924","volume":"11","author":"VT Chasanis","year":"2009","unstructured":"Chasanis, V.T., Likas, C., Galatsanos, N.P.: Scene detection in videos using shot clustering and sequence alignment. IEEE Trans. Multimed. 11(1), 89\u2013100 (2009)","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"5_CR9","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/76.767124","volume":"9","author":"A Hanjalic","year":"1999","unstructured":"Hanjalic, A., Lagendijk, R.L., Biemond, J.: Automated high-level movie segmentation for advanced video-retrieval systems. IEEE Trans. Circ. Syst. Video Technol. 9(4), 580\u2013588 (1999)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"5_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"1","key":"5_CR11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1126004.1126005","volume":"2","author":"MS Lew","year":"2006","unstructured":"Lew, M.S., Sebe, N., Djeraba, C., Jain, R.: Content-based multimedia information retrieval: state of the art and challenges. ACM Trans. Multimed. Comput. Commun. Appl. (TOMCCAP) 2(1), 1\u201319 (2006)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMCCAP)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Lin, D., Fidler, S., Kong, C., Urtasun, R.: Visual semantic search: retrieving videos via complex textual queries. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2657\u20132664, June 2014","DOI":"10.1109\/CVPR.2014.340"},{"issue":"4","key":"5_CR13","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1109\/TMM.2013.2238522","volume":"15","author":"C Liu","year":"2013","unstructured":"Liu, C., Wang, D., Zhu, J., Zhang, B.: Learning a contextual\/multi-thread model for movie\/TV scene segmentation. IEEE Trans. Multimed. 15(4), 884\u2013897 (2013)","journal-title":"IEEE Trans. Multimed."},{"key":"5_CR14","unstructured":"Logan, B., et al.: Mel frequency cepstral coefficients for music modeling. In: ISMIR (2000)"},{"key":"5_CR15","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"issue":"6","key":"5_CR16","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1109\/TMM.2005.858392","volume":"7","author":"Z Rasheed","year":"2005","unstructured":"Rasheed, Z., Shah, M.: Detection and representation of scenes in videos. IEEE Trans. Multimed. 7(6), 1097\u20131105 (2005)","journal-title":"IEEE Trans. Multimed."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Sharif Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806\u2013813 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"issue":"8","key":"5_CR18","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1109\/TCSVT.2011.2138830","volume":"21","author":"P Sidiropoulos","year":"2011","unstructured":"Sidiropoulos, P., Mezaris, V., Kompatsiaris, I., Meinedo, H., Bugalho, M., Trancoso, I.: Temporal video segmentation to scenes using high-level audiovisual features. IEEE Trans. Circ. Syst. Video Technol. 21(8), 1163\u20131177 (2011)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"5_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint (2014). arXiv:1409.1556"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video google: a text retrieval approach to object matching in videos. In: IEEE International Conference on Computer Vision, pp. 1470\u20131477. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"5","key":"5_CR21","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1109\/TMM.2007.900156","volume":"9","author":"CG Snoek","year":"2007","unstructured":"Snoek, C.G., Huurnink, B., Hollink, L., De Rijke, M., Schreiber, G., Worring, M.: Adding semantics to detectors for video retrieval. IEEE Trans. Multimed. 9(5), 975\u2013986 (2007)","journal-title":"IEEE Trans. Multimed."},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Yeung, M.M., Yeo, B.L., Wolf, W.H., Liu, B.: Video browsing using clustering and scene transitions on compressed sequences. In: IS&T\/SPIE\u2019s Symposium on Electronic Imaging: Science & Technology, pp. 399\u2013413 (1995)","DOI":"10.1117\/12.206067"}],"container-title":["Communications in Computer and Information Science","Digital Libraries and Archives"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68130-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T07:32:42Z","timestamp":1570174362000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-68130-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319681290","9783319681306"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68130-6_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]}}}