{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:47Z","timestamp":1777567547466,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012366","type":"print"},{"value":"9783030012373","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01237-3_10","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:42:18Z","timestamp":1538836938000},"page":"156-174","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["How Local Is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization"],"prefix":"10.1007","author":[{"given":"Yandong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1265-4656","authenticated-orcid":false,"given":"Liqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7858-5438","authenticated-orcid":false,"given":"Tianbao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3915-5977","authenticated-orcid":false,"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"10_CR1","unstructured":"Gong, B., Chao, W., Grauman, K., Sha, F.: Diverse sequential subset selection for supervised video summarization. In: Advances in Neural Information Processing Systems (NIPS), pp. 2069\u20132077 (2014)"},{"issue":"2","key":"10_CR2","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.jvcir.2007.04.002","volume":"19","author":"AG Money","year":"2008","unstructured":"Money, A.G., Agius, H.: Video summarisation: a conceptual framework and survey of the state of the art. J. Vis. Commun. Image Represent. 19(2), 121\u2013143 (2008)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10_CR3","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: The First SIGMM Workshop on Social Media, pp. 43\u201348. ACM (2009)","DOI":"10.1145\/1631144.1631154"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Khosla, A., Hamid, R., Lin, C.J., Sundaresan, N.: Large-scale video summarization using web-image priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2698\u20132705 (2013)","DOI":"10.1109\/CVPR.2013.348"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Ngo, C.W., Ma, Y.F., Zhang, H.J.: Automatic video summarization by graph modeling. In: IEEE The Ninth International Conference on Computer Vision (ICCV), pp. 104\u2013109 (2003)","DOI":"10.1109\/ICCV.2003.1238320"},{"key":"10_CR6","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, Part IV. LNCS, vol. 2353, pp. 403\u2013417. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-47979-1_27"},{"issue":"4","key":"10_CR7","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 Recognit. 30(4), 643\u2013658 (1997)","journal-title":"Pattern Recognit."},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1346\u20131353. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247820"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Lu, Z., Grauman, K.: Story-driven summarization for egocentric video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2714\u20132721 (2013)","DOI":"10.1109\/CVPR.2013.350"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Gygli, M., Grabner, H., Van Gool, L.: Video summarization by learning submodular mixtures of objectives. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3090\u20133098 (2015)","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.L., Sha, F., Grauman, K.: Summary transfer: exemplar-based subset selection for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1059\u20131067 (2016)","DOI":"10.1109\/CVPR.2016.120"},{"key":"10_CR12","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., Van Gool, L.: Creating summaries from user videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 505\u2013520. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33"},{"key":"10_CR13","unstructured":"Chao, W., Gong, B., Grauman, K., Sha, F.: Large-margin determinantal point processes. In: Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence (UAI), pp. 191\u2013200 (2015)"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Kang, H.W., Chen, X.Q.: Space-time video montage. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, pp. 1331\u20131338. IEEE (2006)","DOI":"10.1109\/CVPR.2006.284"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Ma, Y.F., Lu, L., Zhang, H.J., Li, M.: A user attention model for video summarization. In: The tenth ACM International Conference on Multimedia, pp. 533\u2013542. ACM (2002)","DOI":"10.1145\/641007.641116"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Xu, J., Mukherjee, L., Li, Y., Warner, J., Rehg, J.M., Singh, V.: Gaze-enabled egocentric video summarization via constrained submodular maximization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2235\u20132244 (2015)","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"10_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46484-8_1","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Sharghi","year":"2016","unstructured":"Sharghi, A., Gong, B., Shah, M.: Query-focused extractive video summarization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 3\u201319. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_1"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Sharghi, A., Laurel, J.S., Gong, B.: Query-focused video summarization: dataset, evaluation, and a memory network based approach. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2127\u20132136. IEEE (2017)","DOI":"10.1109\/CVPR.2017.229"},{"key":"10_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1007\/978-3-319-46478-7_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Chao, W.-L., Sha, F., Grauman, K.: Video summarization with long short-term memory. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VII. LNCS, vol. 9911, pp. 766\u2013782. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_47"},{"key":"10_CR20","unstructured":"Kulesza, A., Taskar, B.: Learning determinantal point processes. In: Proceedings of 27th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 419\u2013427 (2011)"},{"key":"10_CR21","unstructured":"Chao, W.L., Gong, B., Grauman, K., Sha, F.: Large-margin determinantal point processes. In: UAI (2015)"},{"key":"10_CR22","unstructured":"Affandi, R.H., Fox, E.B., Adams, R.P., Taskar, B.: Learning the parameters of determinantal point process kernels. In: ICML, pp. 1224\u20131232 (2014)"},{"key":"10_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Series B 39, 1\u201338 (1977)","journal-title":"J. R. Stat. Soc. Series B"},{"issue":"4","key":"10_CR24","first-page":"10","volume":"53","author":"LR Welch","year":"2003","unstructured":"Welch, L.R.: Hidden markov models and the Baum-Welch algorithm. IEEE Inf. Theory Soc. Newsl. 53(4), 10\u201313 (2003)","journal-title":"IEEE Inf. Theory Soc. Newsl."},{"key":"10_CR25","volume-title":"Reinforcement learning: An introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction, vol. 1. MIT press, Cambridge (1998)"},{"issue":"9","key":"10_CR26","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1109\/TPAMI.2014.2385695","volume":"37","author":"J Kwon","year":"2015","unstructured":"Kwon, J., Lee, K.M.: A unified framework for event summarization and rare event detection from multiple views. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1737\u20131750 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR27","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4225\u20134232 (2014)","DOI":"10.1109\/CVPR.2014.538"},{"key":"10_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-319-10602-1_19","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Xiong","year":"2014","unstructured":"Xiong, B., Grauman, K.: Detecting snap points in egocentric video with a web photo prior. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 282\u2013298. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_19"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Chu, W.S., Song, Y., Jaimes, A.: Video co-summarization: video summarization by visual co-occurrence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3584\u20133592 (2015)","DOI":"10.1109\/CVPR.2015.7298981"},{"issue":"12","key":"10_CR30","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."},{"issue":"1","key":"10_CR31","first-page":"65","volume":"47","author":"AG del Molino","year":"2017","unstructured":"del Molino, A.G., Tan, C., Lim, J.H., Tan, A.H.: Summarization of egocentric videos: a comprehensive survey. IEEE Trans. Hum.-Mach. Syst. 47(1), 65\u201376 (2017)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Yao, T., Mei, T., Rui, Y.: Highlight detection with pairwise deep ranking for first-person video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 982\u2013990 (2016)","DOI":"10.1109\/CVPR.2016.112"},{"key":"10_CR33","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR35","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Proceedings of the ACL 2004 Workshop on Text summarization Branches Out, vol. 8, Barcelona, Spain (2004)"},{"key":"10_CR36","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: The ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. vol. 29, pp. 65\u201372 (2005)"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"3\u20134","key":"10_CR38","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. arXiv preprint arXiv:1612.00563 (2016)","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2-3","key":"10_CR40","doi-asserted-by":"publisher","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\u00ae Mach. Learn. 5(2\u20133), 123\u2013286 (2012)","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Affandi, R.H., Kulesza, A., Fox, E.B.: Markov determinantal point processes. arXiv preprint arXiv:1210.4850 (2012)","DOI":"10.1561\/9781601986290"},{"key":"10_CR42","volume-title":"Reinforcement Learning","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Song, Y., Vallmitjana, J., Stent, A., Jaimes, A.: TVSUM: summarizing web videos using titles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5179\u20135187 (2015)","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"10_CR44","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Jia Deng, Wei Dong, R.S.L.J.L.K.L., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Annual Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"10_CR46","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11263-014-0794-5","volume":"114","author":"YJ Lee","year":"2015","unstructured":"Lee, Y.J., Grauman, K.: Predicting important objects for egocentric video summarization. Int. J. Comput. Vis. 114(1), 38\u201355 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Sharghi, A., Gong, B., Shah, M.: Query-focused extractive video summarization. In: European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR49","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, Part VI. LNCS, vol. 8694, pp. 540\u2013555. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Li, Y., Merialdo, B.: Multi-video summarization based on video-MMR. In: 2010 11th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), pp. 1\u20134. IEEE (2010)","DOI":"10.1109\/CBMI.2010.5529899"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xing, E.P.: Quasi real-time summarization for consumer videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2513\u20132520 (2014)","DOI":"10.1109\/CVPR.2014.322"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01237-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:48:44Z","timestamp":1775242124000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01237-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012366","9783030012373"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01237-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}