{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:37:02Z","timestamp":1769920622937,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":83,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"IBM-Illinois C3SR"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1801652"],"award-info":[{"award-number":["1801652"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462959","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:52Z","timestamp":1626057712000},"page":"1389-1399","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization"],"prefix":"10.1145","author":[{"given":"Safa","family":"Messaoud","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismini","family":"Lourentzou","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Assma","family":"Boughoula","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mona","family":"Zehni","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengxiang","family":"Zhai","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander G.","family":"Schwing","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Yaser Sheikh, Jessica Hodgins, and Ariel Shamir.","author":"Arev Ido","year":"2014","unstructured":"Ido Arev, Hyun Soo Park, Yaser Sheikh, Jessica Hodgins, and Ariel Shamir. 2014. Automatic editing of footage from multiple social cameras. TOG."},{"key":"e_1_3_2_2_2_1","unstructured":"Irwan Bello Hieu Pham Quoc V. Le Mohammad Norouzi and Samy Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. In Procs. ICLR."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Dimitrios Besiris Andrew Makedonas George Economou and Spiros Fotopoulos. 2009. Combining graph connectivity & dominant set clustering for video summarization. Multimedia Tools Appl. (2009).","DOI":"10.1007\/s11042-009-0277-9"},{"key":"e_1_3_2_2_4_1","unstructured":"J. Boyan and A. W. Moore. 2000. Learning evaluation functions to improve optimization by local search. JMLR(2000)."},{"key":"e_1_3_2_2_5_1","unstructured":"R. Bunel M. Hausknecht J. Devlin R. Singh and P. Kohli. 2018. Leveraging grammar and reinforcement learning for neural program synthesis. In Procs. ICLR(2018)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Sijia Cai Wangmeng Zuo Larry S. Davis and Lei Zhang. 2018. Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior. In Procs. ECCV.","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"e_1_3_2_2_7_1","unstructured":"Wen-Sheng Chu Yale Song and Alejandro Jaimes. 2015. Video co-summarization: Video summarization by visual co-occurrence. In Procs. CVPR."},{"key":"e_1_3_2_2_8_1","volume-title":"Towards scalable summarization of consumer videos via sparse dictionary selection","author":"Cong Yang","year":"2011","unstructured":"Yang Cong, Junsong Yuan, and Jiebo Luo. 2011. Towards scalable summarization of consumer videos via sparse dictionary selection. IEEE TMM(2011)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239253"},{"key":"e_1_3_2_2_10_1","volume-title":"Antonio da Luz Jr., and Arnaldo de Albuquerque Araujo.","author":"Fontes de Avila Sandra Eliza","year":"2011","unstructured":"Sandra Eliza Fontes de Avila, Ana Paula Brand\u00e3o Lopes, Antonio da Luz Jr., and Arnaldo de Albuquerque Araujo. 2011. VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recognition Letters(2011)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Tamires Tessarolli de Souza Barbieri and Rudinei Goularte. 2020. Content selection criteria for news multi-video summarization based on human strategies.IJDL(2020).","DOI":"10.1145\/3428658.3430964"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Fadi Dornaika and I Kamal Aldine. 2015. Decremental sparse modeling representative selection for prototype selection. Pattern Recognition(2015).","DOI":"10.1016\/j.patcog.2015.05.018"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Ehsan Elhamifar Guillermo Sapiro and Rene Vidal. 2012. See all by looking at a few: Sparse modeling for finding representative objects. In Procs. CVPR.","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Litong Feng Ziyin Li Zhanghui Kuang and Wei Zhang. 2018. Extractive Video Summarizer with Memory Augmented Neural Networks. InProcs. ACM Multimedia.","DOI":"10.1145\/3240508.3240651"},{"key":"e_1_3_2_2_15_1","unstructured":"Tsu-Jui Fu Shao-Heng Tai and Hwann-Tzong Chen. 2019. Attentive and Adversarial Learning for Video Summarization. In Procs. WACV."},{"key":"e_1_3_2_2_16_1","unstructured":"Boqing Gong Wei-Lun Chao Kristen Grauman and Fei Sha. 2014. Diverse Sequential Subset Selection for Supervised Video Summarization. In Procs. NeurIPS."},{"key":"e_1_3_2_2_17_1","unstructured":"Genliang Guan Zhiyong Wang Shaohui Mei Max Ott Mingyi He and David Da-gan Feng. 2014. A top-down approach for video summarization. TOMM(2014)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Michael Gygli Helmut Grabner Hayko Riemenschneider and Luc Van Gool. 2014. Creating summaries from user videos. In Procs. ECCV.","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_2_19_1","unstructured":"D. He Y. Xia T. Qin L. Wang N. Yu T.-Y. Liu and W.-Y. Ma. 2016. Dual learning for machine translation. In Procs. NeurIPS."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1631144.1631154"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.90"},{"key":"e_1_3_2_2_22_1","unstructured":"Zhong Ji Yaru Ma Yanwei Pang and Xuelong Li. 2019. Query-aware sparse coding for web multi-video summarization. Information Sciences(2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"e_1_3_2_2_24_1","unstructured":"Zhong Ji Yuanyuan Zhang Yanwei Pang and Xuelong Li. 2018. Hypergraph Dominant Set Based Multi-Video Summarization. Signal Processing(2018)."},{"key":"e_1_3_2_2_25_1","unstructured":"Zhong Ji Yuanyuan Zhang Yanwei Pang Xuelong Li and Jing Pan. 2019. Multi-Video Summarization with Query-Dependent Weighted Archetypal Analysis. Neurocomputing(2019)."},{"key":"e_1_3_2_2_26_1","volume-title":"Yoshitaka Ushiku, and Tatsuya Harada.","author":"Kanehira Atsushi","year":"2018","unstructured":"Atsushi Kanehira, Luc Van Gool, Yoshitaka Ushiku, and Tatsuya Harada. 2018.Viewpoint-aware Video Summarization. In Procs. CVPR."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Maurice G Kendall. 1945. The treatment of ties in ranking problems. Biometrika(1945).","DOI":"10.2307\/2332303"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Gunhee Kim Leonid Sigal and Eric P Xing. 2014. Joint summarization of large-scale collections of web images and videos for storyline reconstruction. In Procs. CVPR.","DOI":"10.1109\/CVPR.2014.538"},{"key":"e_1_3_2_2_29_1","volume-title":"Roy-Chowdhury","author":"Lan Shuyue","year":"2018","unstructured":"Shuyue Lan, Rameswar Panda, Qi Zhu, and Amit K. Roy-Chowdhury. 2018. FFNet:Video Fast-Forwarding via Reinforcement Learning. In Procs. CVPR."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"J. Li W. Monroe A. Ritter M. Galley J. Gao and D. Jurafsky. 2016. Deep reinforcement learning for dialogue generation. In Procs. EMNLP(2016).","DOI":"10.18653\/v1\/D16-1127"},{"key":"e_1_3_2_2_31_1","unstructured":"Yingbo Li and Bernard Merialdo. 2010. Multi-video summarization based on AV-MMR. In CBMI."},{"key":"e_1_3_2_2_32_1","unstructured":"Yingbo Li and Bernard Merialdo. 2010. Multi-video summarization based on video-mmr. In WIAMIS."},{"key":"e_1_3_2_2_33_1","unstructured":"Yingbo Li and Bernard Merialdo. 2012. Video summarization based on balanced AV-MMR. In Procs. ICMM."},{"key":"e_1_3_2_2_34_1","unstructured":"Yingbo Li and Bernard Merialdo. 2016. Multimedia maximal marginal relevance for multi-video summarization. Multimedia Tools and Applications(2016)."},{"key":"e_1_3_2_2_35_1","unstructured":"Yingbo Li Bernard Merialdo Mickael Rouvier and Georges Linares. 2011. Static and dynamic video summaries. In Procs. ICM."},{"key":"e_1_3_2_2_36_1","unstructured":"C. Liang M. Norouzi J. Berant Q. Le and N. Lao. 2017. Memory augmented policy optimization for program synthesis with generalization. In Procs. NeurIPS(2017)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Y. Liu Y. Li F. Yang S. Chen and Y. F. Wang. 2019. Learning Hierarchical Self-Attention for Video Summarization. In Procs. ICIP.","DOI":"10.1109\/ICIP.2019.8803639"},{"key":"e_1_3_2_2_38_1","volume-title":"MVS: A multi-view video synopsis framework. SPIC(2016).","author":"Mahapatra Ansuman","year":"2016","unstructured":"Ansuman Mahapatra, Pankaj K Sa, Banshidhar Majhi, and Sudarshan Padhy. 2016. MVS: A multi-view video synopsis framework. SPIC(2016)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Behrooz Mahasseni Michael Lam and Sinisa Todorovic. 2017. Unsupervised video summarization with adversarial lstm networks. In Procs. CVPR.","DOI":"10.1109\/CVPR.2017.318"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Safa Messaoud Maghav Kumar and Alexander G Schwing. 2020. Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning?. In Procs. CVPR.","DOI":"10.1109\/CVPR42600.2020.00761"},{"key":"e_1_3_2_2_41_1","unstructured":"Liqiang Nie Richang Hong Luming Zhang Yingjie Xia Dacheng Tao and NicuSebe. 2015. Perceptual attributes optimization for multi-video summarization. Trans. on Cybernetics(2015)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Mayu Otani Yuta Nakashima Esa Rahtu and Janne Heikkila. 2019. Rethinking the Evaluation of Video Summaries. In Procs. CVPR.","DOI":"10.1109\/CVPR.2019.00778"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Shun-Hsing Ou Chia-Han Lee V Srinivasa Somayazulu Yen-Kuang Chen and Shao-Yi Chien. 2014. On-line multi-view video summarization for wireless video sensor network. STSP(2014).","DOI":"10.1109\/JSTSP.2014.2331916"},{"key":"e_1_3_2_2_44_1","unstructured":"Shun-Hsing Ou Yu-Chen Lu Jui-Pin Wang Shao-Yi Chien Shou-De Lin Mi-Yen Yeti Chia-Han Lee Phillip B Gibbons V Srinivasa Somayazulu and Yen-Kuang Chen. 2014. Communication-efficient multi-view key frame extraction in distributed video sensors. In Procs. VCIP."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Gang Pan Yaoxian Zheng Rufei Zhang Zhenjun Han Di Sun and Xingming Qu. 2019. A bottom-up summarization algorithm for videos in the wild. EURASIP Journal on Advances in Signal Processing(2019).","DOI":"10.1186\/s13634-019-0611-y"},{"key":"e_1_3_2_2_46_1","volume-title":"Niluthpol Chowdhury Mithun, and Amit K. Roy-Chowdhury","author":"Panda Rameswar","year":"2017","unstructured":"Rameswar Panda, Niluthpol Chowdhury Mithun, and Amit K. Roy-Chowdhury. 2017. Diversity-Aware Multi-Video Summarization. Trans. Image Processing(2017)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Rameswar Panda and Amit K Roy-Chowdhury. 2017. Collaborative summarization of topic-related videos. In Procs. CVPR.","DOI":"10.1109\/CVPR.2017.455"},{"key":"e_1_3_2_2_48_1","unstructured":"Romain Paulus Caiming Xiong and Richard Socher. 2018. A Deep Reinforced Model for Abstractive Summarization. In Procs. ICLR."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Jeffrey Pennington Richard Socher and Christopher Manning. 2014. Glove:Global vectors for word representation. In Procs. EMNLP.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Bryan A Plummer Matthew Brown and Svetlana Lazebnik. 2017. Enhancing video summarization via vision-language embedding. In Procs. ICCV.","DOI":"10.1109\/CVPR.2017.118"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Danila Potapov Matthijs Douze Za\u00efd Harchaoui and Cordelia Schmid. 2014. Category-Specific Video Summarization. In Procs. ECCV.","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Yael Pritch Alex Rav-Acha Avital Gutman and Shmuel Peleg. 2007. Webcam synopsis: Peeking around the world. In Procs. ICCV.","DOI":"10.1109\/ICCV.2007.4408934"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Mrigank Rochan and Yang Wang. 2019. Video Summarization by Learning From Unpaired Data. In Procs. CVPR.","DOI":"10.1109\/CVPR.2019.00809"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Mrigank Rochan Linwei Ye and Yang Wang. 2018. Video Summarization Using Fully Convolutional Sequence Networks. InProcs. ECCV.","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"e_1_3_2_2_55_1","volume-title":"Rajiv Ratn Shah, and Roger Zimmermann","author":"Sahrawat Dhruva","year":"2019","unstructured":"Dhruva Sahrawat, Mohit Agarwal, Sanchit Sinha, Aditya Adhikary, Mansi Agarwal, Rajiv Ratn Shah, and Roger Zimmermann. 2019. Video Summarization using Global Attention with Memory Network and LSTM. In Procs. BigMM."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4304"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Aidean Sharghi Ali Borji Chengtao Li Tianbao Yang and Boqing Gong. 2018. Improving sequential determinantal point processes for supervised video summarization. In Procs. ECCV.","DOI":"10.1007\/978-3-030-01219-9_32"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Aidean Sharghi Boqing Gong and Mubarak Shah. 2016. Query-Focused Extractive Video Summarization. In Procs. ECCV.","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"crossref","unstructured":"Aidean Sharghi Jacob S Laurel and Boqing Gong. 2017. Query-focused video summarization: Dataset evaluation and a memory network based approach. InProcs. CVPR.","DOI":"10.1109\/CVPR.2017.229"},{"key":"e_1_3_2_2_60_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Procs. ICLR."},{"key":"e_1_3_2_2_61_1","volume-title":"Tvsum: Summarizing web videos using titles. In Procs. CVPR.","author":"Song Yale","year":"2015","unstructured":"Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015. Tvsum: Summarizing web videos using titles. In Procs. CVPR."},{"key":"e_1_3_2_2_62_1","volume-title":"Seitz","author":"Sun Min","year":"2014","unstructured":"Min Sun, Ali Farhadi, and Steven M. Seitz. 2014. Ranking Domain-Specific Highlights by Analyzing Edited Videos. In Procs. ECCV."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"crossref","unstructured":"Arun Balajee Vasudevan Michael Gygli Anna Volokitin and Luc Van Gool. 2017. Query-adaptive Video Summarization via Quality-aware Relevance Estimation. In Procs. MM.","DOI":"10.1145\/3123266.3123297"},{"key":"e_1_3_2_2_64_1","volume-title":"Order Matters: Sequence to sequence for sets. In Procs. ICLR.","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Samy Bengio, and Manjunath Kudlur. 2016. Order Matters: Sequence to sequence for sets. In Procs. ICLR."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"crossref","unstructured":"Feng Wang and Bernard M\u00e9rialdo. 2009. Multi-document video summarization. In Procs. ICME.","DOI":"10.1109\/ICME.2009.5202747"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"crossref","unstructured":"Meng Wang Richang Hong Guangda Li Zheng-Jun Zha Shuicheng Yan and Tat-Seng Chua. 2012. Event Driven Web Video Summarization by Tag Localization and Key-Shot Identification. TMM(2012).","DOI":"10.1109\/TMM.2012.2185041"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"crossref","unstructured":"Huawei Wei Bingbing Ni Yichao Yan Huanyu Yu Xiaokang Yang and Chen Yao. 2018. Video Summarization via Semantic Attended Networks. In Procs. AAAI.","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"crossref","unstructured":"Ronald J. Williams. 1992. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning(1992).","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"e_1_3_2_2_69_1","volume-title":"Procs. CVPR Egocentric Vision Workshop.","author":"Yeung Serena","year":"2014","unstructured":"Serena Yeung, Alireza Fathi, and Li Fei-Fei. 2014. Videoset: Video summary evaluation through text. In Procs. CVPR Egocentric Vision Workshop."},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"crossref","unstructured":"Jinhui Yuan Huiyi Wang Lan Xiao Wujie Zheng Jianmin Li Fuzong Lin and Bo Zhang. 2007. A formal study of shot boundary detection. Trans. Circuits Syst. Video Techn.(2007).","DOI":"10.1109\/TCSVT.2006.888023"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"crossref","unstructured":"Ke Zhang Wei-Lun Chao Fei Sha and Kristen Grauman. 2016. Video summarization with long short-term memory. In Procs. ECCV.","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"crossref","unstructured":"Luming Zhang Yue Gao Richang Hong Yuxing Hu Rongrong Ji and Qionghai Dai. 2014. Probabilistic skimlets fusion for summarizing multiple consumer landmark videos. TM.","DOI":"10.1109\/TMM.2014.2370257"},{"key":"e_1_3_2_2_73_1","unstructured":"Luming Zhang Yingjie Xia Kuang Mao He Ma and Zhenyu Shan. 2014. An effective video summarization framework toward handheld devices. TIE(2014)."},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"crossref","unstructured":"Yujia Zhang Michael Kampffmeyer Xiaoguang Zhao and Min Tan. 2019. Deep Reinforcement Learning for Query-Conditioned Video Summarization. Applied Sciences(2019).","DOI":"10.3390\/app9040750"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321408.3322622"},{"key":"e_1_3_2_2_76_1","volume-title":"Xing","author":"Zhang Yujia","year":"2018","unstructured":"Yujia Zhang, Michael C. Kampffmeyer, Xiaodan Liang, Min Tan, and Eric P. Xing. 2018. Query-Conditioned Three-Player Adversarial Network for VideoSummarization. In Procs. BMVC."},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang He Ma and Roger Zimmermann. 2013. Dynamic multi-video sum-marization of sensor-rich videos in geo-space. In Procs. ICMM.","DOI":"10.1007\/978-3-642-35725-1_35"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang Guanfeng Wang Beomjoo Seo and Roger Zimmermann. 2012. Multi-video summary and skim generation of sensor-rich videos in geo-space. In Procs. MMSys.","DOI":"10.1145\/2155555.2155565"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang and Roger Zimmermann. 2016. Efficient summarization from multiplegeo referenced user-generated videos. TM(2016).","DOI":"10.1109\/TMM.2016.2520827"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"crossref","unstructured":"Bin Zhao and Eric P Xing. 2014. Quasi real-time summarization for consumervideos. In Procs. CVPR.","DOI":"10.1109\/CVPR.2014.322"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Yu Qiao and Tao Xiang. 2018. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In Procs. AAAI.","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"e_1_3_2_2_82_1","unstructured":"Jianqing Zhu Shengcai Liao and Stan Z Li. 2015. Multicamera joint videosynopsis. TCSVT(2015)."},{"key":"e_1_3_2_2_83_1","volume-title":"CRC standard probability andstatistics tables and formulae","author":"Zwillinger Daniel","unstructured":"Daniel Zwillinger and Stephen Kokoska. 1999. CRC standard probability andstatistics tables and formulae. CRC Press."}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462959","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462959","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:20Z","timestamp":1750191500000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462959"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":83,"alternative-id":["10.1145\/3404835.3462959","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462959","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}