{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:17:44Z","timestamp":1784391464950,"version":"3.55.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464770","type":"print"},{"value":"9783319464787","type":"electronic"}],"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\/978-3-319-46478-7_47","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:48:37Z","timestamp":1473932917000},"page":"766-782","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":491,"title":["Video Summarization with Long Short-Term Memory"],"prefix":"10.1007","author":[{"given":"Ke","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Lun","family":"Chao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"issue":"4","key":"47_CR1","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1016\/S0031-3203(96)00109-4","volume":"30","author":"HJ Zhang","year":"1997","unstructured":"Zhang, H.J., Wu, J., Zhong, D., Smoliar, S.W.: An integrated system for content-based video retrieval and browsing. Pattern Recogn. 30(4), 643\u2013658 (1997)","journal-title":"Pattern Recogn."},{"key":"47_CR2","unstructured":"Gong, B., Chao, W.L., Grauman, K., Sha, F.: Diverse sequential subset selection for supervised video summarization. In: NIPS (2014)"},{"issue":"2","key":"47_CR3","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s00799-005-0129-9","volume":"6","author":"P Mundur","year":"2006","unstructured":"Mundur, P., Rao, Y., Yesha, Y.: Keyframe-based video summarization using delaunay clustering. Int. J. Digit. Libr. 6(2), 219\u2013232 (2006)","journal-title":"Int. J. Digit. Libr."},{"issue":"12","key":"47_CR4","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.1109\/TPAMI.2010.31","volume":"32","author":"D Liu","year":"2010","unstructured":"Liu, D., Hua, G., Chen, T.: A hierarchical visual model for video object summarization. IEEE Trans. Pattern Anal. Mach. Intell. 32(12), 2178\u20132190 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"47_CR5","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"key":"47_CR6","unstructured":"Ngo, C.W., Ma, Y.F., Zhang, H.: Automatic video summarization by graph modeling. In: ICCV (2003)"},{"key":"47_CR7","doi-asserted-by":"crossref","unstructured":"Lagani\u00e8re, R., Bacco, R., Hocevar, A., Lambert, P., Pa\u00efs, G., Ionescu, B.E.: Video summarization from spatio-temporal features. In: ACM TRECVid Video Summarization Workshop (2008)","DOI":"10.1145\/1463563.1463590"},{"issue":"1\u20132","key":"47_CR8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/A:1013241718521","volume":"16","author":"J Nam","year":"2002","unstructured":"Nam, J., Tewfik, A.H.: Event-driven video abstraction and visualization. Multimedia Tools Appl. 16(1\u20132), 55\u201377 (2002)","journal-title":"Multimedia Tools Appl."},{"key":"47_CR9","doi-asserted-by":"crossref","unstructured":"Lu, Z., Grauman, K.: Story-driven summarization for egocentric video. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.350"},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Hong, R., Tang, J., Tan, H.K., Yan, S., Ngo, C., Chua, T.S.: Event driven summarization for web videos. In: SIGMM Workshop (2009)","DOI":"10.1145\/1631144.1631154"},{"key":"47_CR11","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":"47_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/3-540-47979-1_27","volume-title":"Computer Vision \u2014 ECCV 2002","author":"T Liu","year":"2002","unstructured":"Liu, T., Kender, J.R.: Optimization algorithms for the selection of key frame sequences of variable length. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 403\u2013417. Springer, Heidelberg (2002). doi: 10.1007\/3-540-47979-1_27"},{"key":"47_CR13","unstructured":"Kang, H.W., Matsushita, Y., Tang, X., Chen, X.Q.: Space-time video montage. In: CVPR (2006)"},{"key":"47_CR14","doi-asserted-by":"crossref","unstructured":"Ma, Y.F., Lu, L., Zhang, H.J., Li, M.: A user attention model for video summarization. In: ACM Multimedia (2002)","DOI":"10.1145\/641007.641116"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Gygli, M., Grabner, H., Van Gool, L.: Video summarization by learning submodular mixtures of objectives. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"47_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.l., Sha, F., Grauman, K.: Summary transfer: exemplar-based subset selection for video summarization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.120"},{"key":"47_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-319-10584-0_33","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Gygli","year":"2014","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Gool, L.: Creating summaries from user videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 505\u2013520. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10584-0_33"},{"key":"47_CR18","unstructured":"Chao, W.L., Gong, B., Grauman, K., Sha, F.: Large-margin determinantal point processes. In: UAI (2015)"},{"key":"47_CR19","doi-asserted-by":"crossref","unstructured":"Deng, L., Hinton, G., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: ICASSP, pp. 8599\u20138603 (2013)","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"47_CR20","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: ICASSP, pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"47_CR21","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: ICML, pp. 1764\u20131772 (2014)"},{"key":"47_CR22","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, pp. 2625\u20132634 (2015)","DOI":"10.21236\/ADA623249"},{"key":"47_CR23","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: ICCV, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"47_CR24","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: ICCV, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"47_CR25","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: CVPR (2014)","DOI":"10.3115\/v1\/N15-1173"},{"key":"47_CR26","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"2-3","key":"47_CR27","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1561\/2200000044","volume":"5","author":"Alex Kulesza","year":"2012","unstructured":"Kulesza, A., Taskar, B.: Determinantal point processes for machine learning. Found. Trends Mach. Learn. 5(2\u20133) (2012)","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"issue":"1","key":"47_CR28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","volume":"32","author":"SEF de Avila","year":"2011","unstructured":"de Avila, S.E.F., Lopes, A.P.B., da Luz, A., de Ara\u00fajo, A.A.: VSUMM: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recogn. Lett. 32(1), 56\u201368 (2011)","journal-title":"Pattern Recogn. Lett."},{"issue":"1","key":"47_CR29","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s11042-009-0307-7","volume":"46","author":"M Furini","year":"2010","unstructured":"Furini, M., Geraci, F., Montangero, M., Pellegrini, M.: STIMO: STIll and MOving video storyboard for the web scenario. Multimedia Tools Appl. 46(1), 47\u201369 (2010)","journal-title":"Multimedia Tools Appl."},{"key":"47_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Merialdo, B.: Multi-video summarization based on video-MMR. In: WIAMIS Workshop (2010)","DOI":"10.1109\/CBMI.2010.5529899"},{"key":"47_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-319-10599-4_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"D Potapov","year":"2014","unstructured":"Potapov, D., Douze, M., Harchaoui, Z., Schmid, C.: Category-specific video summarization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 540\u2013555. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10599-4_35"},{"key":"47_CR32","doi-asserted-by":"crossref","unstructured":"Morere, O., Goh, H., Veillard, A., Chandrasekhar, V., Lin, J.: Co-regularized deep representations for video summarization. In: ICIP, pp. 3165\u20133169 (2015)","DOI":"10.1109\/ICIP.2015.7351387"},{"key":"47_CR33","doi-asserted-by":"crossref","unstructured":"Kim, G., Xing, E.P.: Reconstructing storyline graphs for image recommendation from web community photos. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.496"},{"key":"47_CR34","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":"47_CR35","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TVSUM: summarizing web videos using titles. In: CVPR (2015)"},{"key":"47_CR36","doi-asserted-by":"crossref","unstructured":"Chu, W.S., Song, Y., Jaimes, A.: Video co-summarization: video summarization by visual co-occurrence. In: CVPR. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"47_CR37","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, B., Lin, S., Wipf, D., Guo, M., Guo, B.: Unsupervised extraction of video highlights via robust recurrent auto-encoders. In: ICCV, pp. 4633\u20134641 (2015)","DOI":"10.1109\/ICCV.2015.526"},{"key":"47_CR38","unstructured":"Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"47_CR39","unstructured":"Jin, J., Fu, K., Cui, R., Sha, F., Zhang, C.: Aligning where to see and what to tell: image caption with region-based attention and scene factorization, arXiv preprint (2015). arXiv:1506.06272"},{"issue":"10","key":"47_CR40","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451\u20132471 (2000)","journal-title":"Neural Comput."},{"issue":"8","key":"47_CR41","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"47_CR42","unstructured":"Zaremba, W., Sutskever, I.: Learning to execute. arXiv preprint (2014). arXiv:1410.4615"},{"key":"47_CR43","unstructured":"Wolf, W.: Key frame selection by motion analysis. In: ICASSP (1996)"},{"key":"47_CR44","doi-asserted-by":"crossref","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM networks. In: IJCNN, pp. 2047\u20132052 (2005)","DOI":"10.1109\/IJCNN.2005.1556215"},{"key":"47_CR45","doi-asserted-by":"crossref","unstructured":"Kulesza, A., Taskar, B.: Learning determinantal point processes. In: UAI (2011)","DOI":"10.1561\/9781601986290"},{"issue":"5","key":"47_CR46","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1137\/130929205","volume":"44","author":"N Buchbinder","year":"2015","unstructured":"Buchbinder, N., Feldman, M., Seffi, J., Schwartz, R.: A tight linear time (1\/2)-approximation for unconstrained submodular maximization. SIAM J. Comput. 44(5), 1384\u20131402 (2015)","journal-title":"SIAM J. Comput."},{"key":"47_CR47","unstructured":"Open video project. http:\/\/www.open-video.org\/"},{"key":"47_CR48","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"47_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-642-15561-1_16","volume-title":"Computer Vision \u2013 ECCV 2010","author":"K Saenko","year":"2010","unstructured":"Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213\u2013226. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15561-1_16"},{"key":"47_CR50","doi-asserted-by":"crossref","unstructured":"Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066\u20132073 (2012)","DOI":"10.1109\/CVPR.2012.6247911"},{"key":"47_CR51","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML, pp. 647\u2013655 (2014)"},{"key":"47_CR52","doi-asserted-by":"crossref","unstructured":"Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10306"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46478-7_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:02:17Z","timestamp":1749582137000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46478-7_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464770","9783319464787"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46478-7_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"16 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"}]}}