{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:30:09Z","timestamp":1743064209214,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466033"},{"type":"electronic","value":"9783319466040"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46604-0_43","type":"book-chapter","created":{"date-parts":[[2016,9,17]],"date-time":"2016-09-17T03:31:55Z","timestamp":1474083115000},"page":"605-620","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Label-Based Automatic Alignment of Video with Narrative Sentences"],"prefix":"10.1007","author":[{"given":"Pelin","family":"Dogan","sequence":"first","affiliation":[]},{"given":"Markus","family":"Gross","sequence":"additional","affiliation":[]},{"given":"Jean-Charles","family":"Bazin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,18]]},"reference":[{"key":"43_CR1","unstructured":"Agirre, E., Diab, M., Cer, D., Gonzalez-Agirre, A.: Semeval-2012 task 6: a pilot on semantic textual similarity. In: Joint Conference on Lexical and Computational Semantics, pp. 385\u2013393 (2012)"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Apostolidis, E., Mezaris, V.: Fast shot segmentation combining global and local visual descriptors. In: ICASSP (2014)","DOI":"10.1109\/ICASSP.2014.6854873"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Lajugie, R., Grave, E., Bach, F., Laptev, I., Ponce, J., Schmid, C.: Weakly-supervised alignment of video with text. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.507"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"43_CR5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"EW Dijkstra","year":"1959","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs. Numer. Math. 1, 269 (1959)","journal-title":"Numer. Math."},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"43_CR7","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1016\/S0031-3203(98)00168-X","volume":"32","author":"MS Drew","year":"1999","unstructured":"Drew, M.S., Wei, J., Li, Z.N.: Illumination-invariant image retrieval and video segmentation. Pattern Recogn. 32, 1369 (1999)","journal-title":"Pattern Recogn."},{"key":"43_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision\u2013ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010)"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Srinivasan, P., Shi, J., Davis, L.S.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"43_CR10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF01261224","volume":"1","author":"A Hampapur","year":"1995","unstructured":"Hampapur, A., Jain, R., Weymouth, T.E.: Production model based digital video segmentation. Multimedia Tools Appl. 1, 9 (1995)","journal-title":"Multimedia Tools Appl."},{"key":"43_CR11","unstructured":"Han, L., Kashyap, A., Finin, T., Mayfield, J., Weese, J.: UMBC ebiquity-core: semantic textual similarity systems. In: Proceedings of the Second Joint Conference on Lexical and Computational Semantics (2013)"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: ACM International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"43_CR13","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.: BabyTalk: understanding and generating simple image descriptions. PAMI 35, 2891 (2013)","journal-title":"PAMI"},{"key":"43_CR14","unstructured":"Lankinen, J., K\u00e4m\u00e4r\u00e4inen, J.K.: Video shot boundary detection using visual bag-of-words. In: VISAPP (2013)"},{"key":"43_CR15","unstructured":"Lee, J.C.M., Ip, D.M.C.: A robust approach for camera break detection in color video sequence. In: MVA (1995)"},{"key":"43_CR16","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv preprint \n                      arXiv:1301.3781"},{"key":"43_CR17","unstructured":"Nagasaka, A., Tanaka, Y.: Automatic video indexing and full-video search for object appearances (1992)"},{"key":"43_CR18","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.L.: Im2Text: describing images using 1 million captioned photographs. In: NIPS (2011)"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Pedersen, T., Patwardhan, S., Michelizzi, J.: WordNet::Similarity - Measuring the Relatedness of Concepts. In: Proceedings of Demonstration Papers at HLT-NAACL (2004)","DOI":"10.3115\/1614025.1614037"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Qu, Z., Liu, Y., Ren, L., Chen, Y., Zheng, R.: A method of shot detection based on color and edge features. In: Proceedings of IEEE Symposium on Web Society (SWS) (2009)","DOI":"10.1109\/SWS.2009.5271731"},{"key":"43_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/978-3-319-11752-2_15","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2014","unstructured":"Rohrbach, A., Rohrbach, M., Qiu, W., Friedrich, A., Pinkal, M., Schiele, B.: Coherent multi-sentence video description with variable level of detail. In: Jiang, X., Hornegger, J., Koch, R. (eds.) GCPR 2014. LNCS, vol. 8753, pp. 184\u2013195. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-11752-2_15"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"43_CR25","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","volume":"26","author":"H Sakoe","year":"1978","unstructured":"Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Sig. Process. 26, 43 (1978)","journal-title":"IEEE Trans. Acoust. Speech Sig. Process."},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Sankar, P., Jawahar, C., Zisserman, A.: Subtitle-free movie to script alignment. In: BMVC (2009)","DOI":"10.5244\/C.23.121"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., B\u00e4uml, M., Stiefelhagen, R.: Story-based video retrieval in TV series using plot synopses. In: Proceedings of International Conference on Multimedia Retrieval (2014)","DOI":"10.1145\/2578726.2578727"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Bauml, M., Stiefelhagen, R.: Book2Movie: aligning video scenes with book chapters. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298792"},{"key":"43_CR29","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"J Xiao","year":"2014","unstructured":"Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: SUN database: exploring a large collection of scene categories. IJCV 119, 3 (2014)","journal-title":"IJCV"},{"key":"43_CR30","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"},{"key":"43_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., Fidler, S.: Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46604-0_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T00:54:11Z","timestamp":1602291251000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46604-0_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466033","9783319466040"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46604-0_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"18 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}