{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T01:18:58Z","timestamp":1779326338681,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,1,7]]},"DOI":"10.1145\/3512388.3512427","type":"proceedings-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T02:28:13Z","timestamp":1648520893000},"page":"268-274","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["SHTVS: Shot-level based Hierarchical Transformer for Video Summarization"],"prefix":"10.1145","author":[{"given":"Yubo","family":"An","sequence":"first","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,3,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889265"},{"key":"e_1_3_2_1_2_1","first-page":"347","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Rochan M.","unstructured":"Rochan , M. , Ye , L. , and Wang , Y . 2018. Video summarization using fully convolutional sequence networks . In Proceedings of the European Conference on Computer Vision (ECCV) , pp. 347 - 363 . Rochan, M., Ye, L., and Wang, Y. 2018. Video summarization using fully convolutional sequence networks. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 347-363."},{"key":"e_1_3_2_1_3_1","first-page":"54","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV)","author":"Fajtl H. S.","unstructured":"J. Fajtl , H. S. Sokeh , V. Argyriou , D. Monekosso , and P. Remagnino . 2018. Summarizing videos with attention . In Proceedings of the Asian Conference on Computer Vision (ACCV) , pp. 39\u2013 54 . J. Fajtl, H. S. Sokeh, V. Argyriou, D. Monekosso, and P. Remagnino. 2018. Summarizing videos with attention. In Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 39\u201354."},{"key":"e_1_3_2_1_4_1","first-page":"782","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Zhang W.-L.","unstructured":"K. Zhang , W.-L. Chao , F. Sha , and K. Grauman . 2016. Video summarization with long short-term memory . In Proceedings of the European Conference on Computer Vision (ECCV) , pp. 766\u2013 782 . K. Zhang, W.-L. Chao, F. Sha, and K. Grauman. 2016. Video summarization with long short-term memory. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 766\u2013782."},{"key":"e_1_3_2_1_5_1","first-page":"7589","volume-title":"Proceedings of the Association for the Advance of Artificial Intelligence (AAAI)","author":"Zhou Y.","unstructured":"K. Zhou , Y. Qiao , and T. Xiang . 2018. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward . In Proceedings of the Association for the Advance of Artificial Intelligence (AAAI) , pp. 7582\u2013 7589 . K. Zhou, Y. Qiao, and T. Xiang. 2018. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In Proceedings of the Association for the Advance of Artificial Intelligence (AAAI), pp. 7582\u20137589."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_8_1","first-page":"5998","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani A.","unstructured":"Vaswani , A. , Shazeer , N. , Parmar , N. , Uszkoreit , J. , Jones , L. , Gomez , A. N. , 2017. Attention is all you need. Advances in neural information processing systems , pp. 5998 - 6008 . Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., 2017. Attention is all you need. Advances in neural information processing systems, pp. 5998-6008."},{"key":"e_1_3_2_1_9_1","first-page":"555","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Potapov M.","unstructured":"D. Potapov , M. Douze , Z. Harchaoui , and C. Schmid . 2014. Category-specific video summarization . In Proceedings of the European Conference on Computer Vision (ECCV) , pp. 540\u2013 555 . D. Potapov, M. Douze, Z. Harchaoui, and C. Schmid. 2014. Category-specific video summarization. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 540\u2013555."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889265"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108312"},{"key":"e_1_3_2_1_17_1","first-page":"1059","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","author":"Zhang K.","unstructured":"Zhang , K. , Chao , W. L. , Sha , F. and Grauman , K . 2016. Summary transfer: Exemplar-based subset selection for video summarization . In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) , pp. 1059 - 1067 . Zhang, K., Chao, W. L., Sha, F. and Grauman, K. 2016. Summary transfer: Exemplar-based subset selection for video summarization. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 1059-1067."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695887"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.013"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959451"},{"key":"e_1_3_2_1_21_1","first-page":"223","volume-title":"Proceedings of the Association for the Advance of Artificial Intelligence (AAAI)","author":"Wei B.","unstructured":"H. Wei , B. Ni , Y. Yan , H. Yu , X. Yang , and C. Yao . 2018. Video summarization via semantic attended networks . In Proceedings of the Association for the Advance of Artificial Intelligence (AAAI) , pp. 216\u2013 223 . H. Wei, B. Ni, Y. Yan, H. Yu, X. Yang, and C. Yao. 2018. Video summarization via semantic attended networks. In Proceedings of the Association for the Advance of Artificial Intelligence (AAAI), pp. 216\u2013223."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2860797"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066349"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.12.016"}],"event":{"name":"ICIGP 2022: 2022 the 5th International Conference on Image and Graphics Processing","location":"Beijing China","acronym":"ICIGP 2022"},"container-title":["2022 the 5th International Conference on Image and Graphics Processing (ICIGP)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3512388.3512427","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3512388.3512427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:43Z","timestamp":1750191103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3512388.3512427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,7]]},"references-count":24,"alternative-id":["10.1145\/3512388.3512427","10.1145\/3512388"],"URL":"https:\/\/doi.org\/10.1145\/3512388.3512427","relation":{},"subject":[],"published":{"date-parts":[[2022,1,7]]},"assertion":[{"value":"2022-03-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}