{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:28:10Z","timestamp":1772519290616,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"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":[[2021,4,14]]},"DOI":"10.1145\/3397481.3450672","type":"proceedings-article","created":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T06:07:18Z","timestamp":1618380438000},"page":"249-259","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Non-Linear Consumption of Videos Using a Sequence of Personalized Multimodal Fragments"],"prefix":"10.1145","author":[{"given":"Gaurav","family":"Verma","sequence":"first","affiliation":[{"name":"Adobe Research, India"}]},{"given":"Trikay","family":"Nalamada","sequence":"additional","affiliation":[{"name":"IIT Guwahati, India"}]},{"given":"Keerti","family":"Harpavat","sequence":"additional","affiliation":[{"name":"IIT Guwahati, India"}]},{"given":"Pranav","family":"Goel","sequence":"additional","affiliation":[{"name":"IIT Guwahati, India"}]},{"given":"Aman","family":"Mishra","sequence":"additional","affiliation":[{"name":"IIT Guwahati, India"}]},{"given":"Balaji Vasan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Big data Experience Lab Adobe Research, India"}]}],"member":"320","published-online":{"date-parts":[[2021,4,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Coefficient of variation. Encyclopedia of research design 1","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi . 2010. Coefficient of variation. Encyclopedia of research design 1 ( 2010 ), 169\u2013171. Herv\u00e9 Abdi. 2010. Coefficient of variation. Encyclopedia of research design 1 (2010), 169\u2013171."},{"key":"e_1_3_2_1_2_1","volume-title":"Online video viewing to reach 100 minutes a day","author":"Article Online","year":"2021","unstructured":"Online Article . 2019. Online video viewing to reach 100 minutes a day in 2021 . https:\/\/www.zenithmedia.com\/online-video-viewing-to-reach-100-minutes-a-day-in-2021\/. Accessed: 2020-10-08. Online Article. 2019. Online video viewing to reach 100 minutes a day in 2021. https:\/\/www.zenithmedia.com\/online-video-viewing-to-reach-100-minutes-a-day-in-2021\/. Accessed: 2020-10-08."},{"key":"e_1_3_2_1_3_1","unstructured":"Online Article. 2020. Microsoft Thinks Coronavirus will Forever Change the Way we Work And Learn. https:\/\/www.theverge.com\/2020\/4\/9\/21214314\/microsoft-teams-usage-coronavirus-pandemic-work-habit-change. Accessed: 2020-10-08.  Online Article. 2020. Microsoft Thinks Coronavirus will Forever Change the Way we Work And Learn. https:\/\/www.theverge.com\/2020\/4\/9\/21214314\/microsoft-teams-usage-coronavirus-pandemic-work-habit-change. Accessed: 2020-10-08."},{"key":"e_1_3_2_1_4_1","unstructured":"Online Article. 2020. The Virus Changed the Way We Internet. https:\/\/www.nytimes.com\/interactive\/2020\/04\/07\/technology\/coronavirus-internet-use.html. Accessed: 2020-10-08.  Online Article. 2020. The Virus Changed the Way We Internet. https:\/\/www.nytimes.com\/interactive\/2020\/04\/07\/technology\/coronavirus-internet-use.html. Accessed: 2020-10-08."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366583"},{"key":"e_1_3_2_1_6_1","unstructured":"Brodie Clark. 2020. How to Make the Most of Video Timestamp Results in Google Search. Search Engine Journal(2020). https:\/\/www.searchenginejournal.com\/video-timestamp-results-google-search\/364020\/  Brodie Clark. 2020. How to Make the Most of Video Timestamp Results in Google Search. Search Engine Journal(2020). https:\/\/www.searchenginejournal.com\/video-timestamp-results-google-search\/364020\/"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1).","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1)."},{"key":"e_1_3_2_1_8_1","unstructured":"Fartash Faghri David\u00a0J Fleet Jamie\u00a0Ryan Kiros and Sanja Fidler. 2017. Vse++: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612(2017).  Fartash Faghri David\u00a0J Fleet Jamie\u00a0Ryan Kiros and Sanja Fidler. 2017. Vse++: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612(2017)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.01.013"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486533"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.123"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Vladimir Iashin and Esa Rahtu. 2020. A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer. arXiv preprint arXiv:2005.08271(2020).  Vladimir Iashin and Esa Rahtu. 2020. A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer. arXiv preprint arXiv:2005.08271(2020).","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"e_1_3_2_1_15_1","unstructured":"Taehyeong Kim Min-Oh Heo Seonil Son Kyoung-Wha Park and Byoung-Tak Zhang. 2018. Glac net: Glocal attention cascading networks for multi-image cued story generation. arXiv preprint arXiv:1805.10973(2018).  Taehyeong Kim Min-Oh Heo Seonil Son Kyoung-Wha Park and Byoung-Tak Zhang. 2018. Glac net: Glocal attention cascading networks for multi-image cued story generation. arXiv preprint arXiv:1805.10973(2018)."},{"key":"e_1_3_2_1_16_1","unstructured":"Ryan Kiros Ruslan Salakhutdinov and Richard\u00a0S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539(2014).  Ryan Kiros Ruslan Salakhutdinov and Richard\u00a0S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539(2014)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186988"},{"key":"e_1_3_2_1_18_1","unstructured":"Jordi Mas and Gabriel Fernandez. 2003. Video Shot Boundary Detection Based on Color Histogram.. In TRECVID.  Jordi Mas and Gabriel Fernandez. 2003. Video Shot Boundary Detection Based on Color Histogram.. In TRECVID."},{"key":"e_1_3_2_1_19_1","unstructured":"Derek Miller. 2019. Leveraging BERT for extractive text summarization on lectures. arXiv preprint arXiv:1906.04165(2019).  Derek Miller. 2019. Leveraging BERT for extractive text summarization on lectures. arXiv preprint arXiv:1906.04165(2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"e_1_3_2_1_21_1","unstructured":"Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew\u00a0Y Ng. 2011. Multimodal deep learning. In ICML.  Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew\u00a0Y Ng. 2011. Multimodal deep learning. In ICML."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_23_1","unstructured":"Yair Shemer Daniel Rotman and Nahum Shimkin. 2019. ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization. arXiv preprint arXiv:1912.03650(2019).  Yair Shemer Daniel Rotman and Nahum Shimkin. 2019. ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization. arXiv preprint arXiv:1912.03650(2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1698924.1699063"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2015.7340419"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3048787.3231294"},{"key":"e_1_3_2_1_28_1","volume-title":"2016 International Joint Conference on Neural Networks (IJCNN). IEEE","author":"Wang Cheng","year":"2016","unstructured":"Cheng Wang , Haojin Yang , and Christoph Meinel . 2016 . Exploring multimodal video representation for action recognition . In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE , 1924\u20131931. Cheng Wang, Haojin Yang, and Christoph Meinel. 2016. Exploring multimodal video representation for action recognition. In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 1924\u20131931."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2125"},{"key":"e_1_3_2_1_30_1","unstructured":"Kaiyang Zhou Yu Qiao and Tao Xiang. 2017. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. arXiv preprint arXiv:1801.00054(2017).  Kaiyang Zhou Yu Qiao and Tao Xiang. 2017. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. arXiv preprint arXiv:1801.00054(2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"}],"event":{"name":"IUI '21: 26th International Conference on Intelligent User Interfaces","location":"College Station TX USA","acronym":"IUI '21","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["26th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397481.3450672","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397481.3450672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:33Z","timestamp":1750200093000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397481.3450672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,14]]},"references-count":31,"alternative-id":["10.1145\/3397481.3450672","10.1145\/3397481"],"URL":"https:\/\/doi.org\/10.1145\/3397481.3450672","relation":{},"subject":[],"published":{"date-parts":[[2021,4,14]]},"assertion":[{"value":"2021-04-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}