{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:52:24Z","timestamp":1783529544797,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Medical Research Council (MRC) Fellowship","award":["MR\/S003916\/1"],"award-info":[{"award-number":["MR\/S003916\/1"]}]},{"name":"Combatting cRiminals In The CLoud","award":["EP\/M020576\/1"],"award-info":[{"award-number":["EP\/M020576\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414064","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"4023-4031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Query Twice"],"prefix":"10.1145","author":[{"given":"Junyan","family":"Wang","sequence":"first","affiliation":[{"name":"Meituan-Dianping Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Bai","sequence":"additional","affiliation":[{"name":"Newcastle University, Newcastle upon Tyne, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Long","sequence":"additional","affiliation":[{"name":"Durham University, Durham, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingzhang","family":"Hu","sequence":"additional","affiliation":[{"name":"Newcastle University, Newcastle upon Tyne, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Chai","sequence":"additional","affiliation":[{"name":"Meituan-Dianping Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"Newcastle University, Newcastle upon Tyne, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolin","family":"Wei","sequence":"additional","affiliation":[{"name":"Meituan-Dianping Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_2_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 ( 2014 ). Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"key":"e_1_3_2_2_7_1","unstructured":"Boqing Gong Wei-Lun Chao Kristen Grauman and Fei Sha. 2014. Diverse sequential subset selection for supervised video summarization. In Advances in Neural Information Processing Systems. 2069--2077.  Boqing Gong Wei-Lun Chao Kristen Grauman and Fei Sha. 2014. Diverse sequential subset selection for supervised video summarization. In Advances in Neural Information Processing Systems. 2069--2077."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351056"},{"key":"e_1_3_2_2_12_1","volume-title":"Video summarization with attention-based encoder-decoder networks","author":"Ji Zhong","year":"2019","unstructured":"Zhong Ji , Kailin Xiong , Yanwei Pang , and Xuelong Li. 2019. Video summarization with attention-based encoder-decoder networks . IEEE Transactions on Circuits and Systems for Video Technology ( 2019 ). Zhong Ji, Kailin Xiong, Yanwei Pang, and Xuelong Li. 2019. Video summarization with attention-based encoder-decoder networks. IEEE Transactions on Circuits and Systems for Video Technology (2019)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018537"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/33.3.239"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Alex Kulesza Ben Taskar etal 2012. Determinantal point processes for machine learning. Foundations and Trends\u00ae in Machine Learning 5 2--3 (2012) 123--286.  Alex Kulesza Ben Taskar et al. 2012. Determinantal point processes for machine learning. Foundations and Trends\u00ae in Machine Learning 5 2--3 (2012) 123--286.","DOI":"10.1561\/2200000044"},{"key":"e_1_3_2_2_16_1","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1346--1353","author":"Lee Yong Jae","year":"2012","unstructured":"Yong Jae Lee , Joydeep Ghosh , and Kristen Grauman . 2012 . Discovering important people and objects for egocentric video summarization . In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1346--1353 . Yong Jae Lee, Joydeep Ghosh, and Kristen Grauman. 2012. Discovering important people and objects for egocentric video summarization. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1346--1353."},{"key":"e_1_3_2_2_17_1","volume-title":"Meta Learning for Task-Driven Video Summarization","author":"Li Xuelong","year":"2019","unstructured":"Xuelong Li , Hongli Li , and Yongsheng Dong . 2019. Meta Learning for Task-Driven Video Summarization . IEEE Transactions on Industrial Electronics ( 2019 ). Xuelong Li, Hongli Li, and Yongsheng Dong. 2019. Meta Learning for Task-Driven Video Summarization. IEEE Transactions on Industrial Electronics (2019)."},{"key":"e_1_3_2_2_18_1","volume-title":"Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. In The 33rd AAAI Conference on Artificial Intelligence","volume":"8","author":"Li Xiangpeng","year":"2019","unstructured":"Xiangpeng Li , Jingkuan Song , Lianli Gao , Xianglong Liu , Wenbing Huang , Xiangnan He , and Chuang Gan . 2019 . Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. In The 33rd AAAI Conference on Artificial Intelligence , Vol. 8 . Xiangpeng Li, Jingkuan Song, Lianli Gao, Xianglong Liu, Wenbing Huang, Xiangnan He, and Chuang Gan. 2019. Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering. In The 33rd AAAI Conference on Artificial Intelligence, Vol. 8."},{"key":"e_1_3_2_2_19_1","volume-title":"A hierarchical visual model for video object summarization","author":"Liu David","year":"2010","unstructured":"David Liu , Gang Hua , and Tsuhan Chen . 2010. A hierarchical visual model for video object summarization . IEEE transactions on pattern analysis and machine intelligence 32, 12 ( 2010 ), 2178--2190. David Liu, Gang Hua, and Tsuhan Chen. 2010. A hierarchical visual model for video object summarization. IEEE transactions on pattern analysis and machine intelligence 32, 12 (2010), 2178--2190."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"e_1_3_2_2_22_1","volume-title":"On first-order metalearning algorithms. arXiv preprint arXiv:1803.02999","author":"Nichol Alex","year":"2018","unstructured":"Alex Nichol , Joshua Achiam , and John Schulman . 2018. On first-order metalearning algorithms. arXiv preprint arXiv:1803.02999 ( 2018 ). Alex Nichol, Joshua Achiam, and John Schulman. 2018. On first-order metalearning algorithms. arXiv preprint arXiv:1803.02999 (2018)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00778"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187","author":"Song Yale","year":"2015","unstructured":"Yale Song , Jordi Vallmitjana , Amanda Stent , and Alejandro Jaimes . 2015 . Tvsum: Summarizing web videos using titles . In Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187 . Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015. Tvsum: Summarizing web videos using titles. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_2_27_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. BMVA British Mach. Vis. Conf. 275","author":"Wang Junyan","year":"2019","unstructured":"Junyan Wang , Bingzhang Hu , Yang Long , and Yu Guan . 2019 . Order Matters: Shuffling Sequence Generation for Video Prediction . In Proc. BMVA British Mach. Vis. Conf. 275 .1--275.14. Junyan Wang, Bingzhang Hu, Yang Long, and Yu Guan. 2019. Order Matters: Shuffling Sequence Generation for Video Prediction. In Proc. BMVA British Mach. Vis. Conf. 275.1--275.14."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655013"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_37"},{"key":"e_1_3_2_2_32_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Wei Huawei","year":"2018","unstructured":"Huawei Wei , Bingbing Ni , Yichao Yan , Huanyu Yu , Xiaokang Yang , and Chen Yao . 2018 . Video summarization via semantic attended networks . In Thirty-Second AAAI Conference on Artificial Intelligence. Huawei Wei, Bingbing Ni, Yichao Yan, Huanyu Yu, Xiaokang Yang, and Chen Yao. 2018. Video summarization via semantic attended networks. In Thirty-Second AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"e_1_3_2_2_34_1","volume-title":"Breaking the softmax bottleneck: A high-rank RNN language model. arXiv preprint arXiv:1711.03953","author":"Yang Zhilin","year":"2017","unstructured":"Zhilin Yang , Zihang Dai , Ruslan Salakhutdinov , and William W Cohen . 2017. Breaking the softmax bottleneck: A high-rank RNN language model. arXiv preprint arXiv:1711.03953 ( 2017 ). Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, and William W Cohen. 2017. Breaking the softmax bottleneck: A high-rank RNN language model. arXiv preprint arXiv:1711.03953 (2017)."},{"key":"e_1_3_2_2_35_1","volume-title":"Ping Li, Li Zhou, and Jiashi Feng.","author":"Yuan Li","year":"2019","unstructured":"Li Yuan , Francis EH Tay , Ping Li, Li Zhou, and Jiashi Feng. 2019 . Cycle-SUM: Cycleconsistent Adversarial LSTM Networks for Unsupervised Video Summarization . arXiv preprint arXiv:1904.08265 (2019). Li Yuan, Francis EH Tay, Ping Li, Li Zhou, and Jiashi Feng. 2019. Cycle-SUM: Cycleconsistent Adversarial LSTM Networks for Unsupervised Video Summarization. arXiv preprint arXiv:1904.08265 (2019)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00983"},{"key":"e_1_3_2_2_42_1","volume-title":"CRC standard probability and statistics tables and formulae","author":"Zwillinger Daniel","unstructured":"Daniel Zwillinger and Stephen Kokoska . 1999. CRC standard probability and statistics tables and formulae . Crc Press . Daniel Zwillinger and Stephen Kokoska. 1999. CRC standard probability and statistics tables and formulae. Crc Press."}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414064","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:24Z","timestamp":1750197684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414064"}},"subtitle":["Dual Mixture Attention Meta Learning for Video Summarization"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":42,"alternative-id":["10.1145\/3394171.3414064","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414064","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}