{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:54Z","timestamp":1742914134991,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030687984"},{"type":"electronic","value":"9783030687991"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-68799-1_6","type":"book-chapter","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T08:03:53Z","timestamp":1614845033000},"page":"75-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Coarse to Fine: Hierarchical Structure-Aware Video Summarization"],"prefix":"10.1007","author":[{"given":"Wenxu","family":"Li","sequence":"first","affiliation":[]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Xiaozhou","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xiaoxuan","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Jiawan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bettadapura, V., Pantofaru, C., Essa, I.: Leveraging contextual cues for generating basketball highlights. In: Proceedings of the 24th ACM international conference on Multimedia, pp. 908\u2013917. ACM (2016)","DOI":"10.1145\/2964284.2964286"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Carlos Niebles, J., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1914\u20131923 (2016)","DOI":"10.1109\/CVPR.2016.211"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: Proceedings of the Empirical Methods in Natural Language Processing, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"6_CR5","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"},{"key":"6_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Chen, K., Sun, C., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3628\u20133636 (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"6_CR8","unstructured":"Gong, B., Chao, W.L., Grauman, K., Sha, F.: Diverse sequential subset selection for supervised video summarization. In: Proceedings of Advances in Neural Information Processing Systems, pp. 2069\u20132077 (2014)"},{"key":"6_CR9","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. LNCS, vol. 8695, pp. 505\u2013520. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33"},{"key":"6_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":"6_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Cui, K., Peng, B., Xu, C.: Comprehensive video understanding: video summarization with content-based video recommender design. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1\u20138 (2019)","DOI":"10.1109\/ICCVW.2019.00195"},{"key":"6_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations, pp. 1\u201315 (2014)"},{"issue":"2\u20133","key":"6_CR13","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1561\/2200000044","volume":"5","author":"A Kulesza","year":"2012","unstructured":"Kulesza, A., Taskar, B., et al.: Determinantal point processes for machine learning. Found. Trends in Mach. Learn. 5(2\u20133), 123\u2013286 (2012)","journal-title":"Found. Trends in Mach. Learn."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kwon, H., Shim, W., Cho, M.: Temporal u-nets for video summarization with scene and action recognition. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1\u20134 (2019)","DOI":"10.1109\/ICCVW.2019.00192"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: Bsn: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Mathe, S., Pirinen, A., Sminchisescu, C.: Reinforcement learning for visual object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2894\u20132902 (2016)","DOI":"10.1109\/CVPR.2016.316"},{"issue":"5","key":"6_CR17","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TMM.2018.2876046","volume":"21","author":"M Merler","year":"2018","unstructured":"Merler, M., et al.: Automatic curation of sports highlights using multimodal excitement features. IEEE Trans. Multimedia 21(5), 1147\u20131160 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"6_CR18","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. In: Neural Information Processing Systems Deep Learning Workshop, pp. 1\u20139 (2013)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Otani, M., Nakashima, Y., Rahtu, E., Heikkila, J.: Rethinking the evaluation of video summaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7596\u20137604 (2019)","DOI":"10.1109\/CVPR.2019.00778"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Jeon, S., Sohn, K.: Video summarization by learning relationships between action and scene. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1\u20138 (2019)","DOI":"10.1109\/ICCVW.2019.00193"},{"key":"6_CR21","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp. 8026\u20138037 (2019)"},{"key":"6_CR22","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, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 290\u2013298 (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Ringer, C., Nicolaou, M.A.: Deep unsupervised multi-view detection of video game stream highlights. In: Proceedings of the 13th International Conference on the Foundations of Digital Games, pp. 1\u20136. ACM (2018)","DOI":"10.1145\/3235765.3235781"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Rochan, M., Wang, Y.: Video summarization by learning from unpaired data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7902\u20137911 (2019)","DOI":"10.1109\/CVPR.2019.00809"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Seong, H., Hyun, J., Kim, E.: Video multitask transformer network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1\u20139 (2019)","DOI":"10.1109\/ICCVW.2019.00194"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"6_CR28","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)"},{"key":"6_CR29","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recogn. Challenge 1(2), 2 (2014)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3093\u20133102 (2016)","DOI":"10.1109\/CVPR.2016.337"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Yun, S., Choi, J., Yoo, Y., Yun, K., Young Choi, J.: Action-decision networks for visual tracking with deep reinforcement learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2711\u20132720 (2017)","DOI":"10.1109\/CVPR.2017.148"},{"key":"6_CR32","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":"6_CR33","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. LNCS, vol. 9911, pp. 766\u2013782. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_47"},{"issue":"11","key":"6_CR34","doi-asserted-by":"publisher","first-page":"5469","DOI":"10.1109\/TIP.2016.2601493","volume":"25","author":"S Zhang","year":"2016","unstructured":"Zhang, S., Zhu, Y., Roy-Chowdhury, A.K.: Context-aware surveillance video summarization. IEEE Trans. Image Proces. 25(11), 5469\u20135478 (2016)","journal-title":"IEEE Trans. Image Proces."},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, X., Lu, X.: Hsa-rnn: hierarchical structure-adaptive rnn for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7405\u20137414 (2018)","DOI":"10.1109\/CVPR.2018.00773"},{"key":"6_CR36","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"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, K., Qiao, Y., Xiang, T.: Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Thirty-Second AAAI Conference on Artificial Intelligence, pp. 7582\u20137589 (2018)","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"6_CR39","unstructured":"Zhou, K., Xiang, T., Cavallaro, A.: Video summarisation by classification with deep reinforcement learning. In: Proceedings of the British Machine Vision Conference, pp. 1\u201313 (2018)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68799-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T00:07:07Z","timestamp":1671494827000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68799-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687984","9783030687991"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68799-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}