{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:15:15Z","timestamp":1781334915142,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,3]],"date-time":"2020-07-03T00:00:00Z","timestamp":1593734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100013343","name":"Craig Newmark Philanthropies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013343","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008939","name":"Center for Computing for Life Sciences, San Francisco State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008939","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,3]]},"DOI":"10.1145\/3357236.3395433","type":"proceedings-article","created":{"date-parts":[[2020,7,5]],"date-time":"2020-07-05T19:29:16Z","timestamp":1593977356000},"page":"47-60","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["Human-in-the-Loop Machine Learning to Increase Video Accessibility for Visually Impaired and Blind Users"],"prefix":"10.1145","author":[{"given":"Beste F.","family":"Yuksel","sequence":"first","affiliation":[{"name":"University of San Francisco, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooyan","family":"Fazli","sequence":"additional","affiliation":[{"name":"San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umang","family":"Mathur","sequence":"additional","affiliation":[{"name":"San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaishali","family":"Bisht","sequence":"additional","affiliation":[{"name":"San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soo Jung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of San Francisco, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua Junhee","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung Jung","family":"Jin","sequence":"additional","affiliation":[{"name":"University of San Francisco, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue-Ting","family":"Siu","sequence":"additional","affiliation":[{"name":"San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua A.","family":"Miele","sequence":"additional","affiliation":[{"name":"Smith-Kettlewell Eye Research Institute, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilmi","family":"Yoon","sequence":"additional","affiliation":[{"name":"San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,7,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"MAGpie 2.0. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/main.wgbh.org\/wgbh\/pages\/ncam_old\/webaccess\/magpie\/  MAGpie 2.0. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/main.wgbh.org\/wgbh\/pages\/ncam_old\/webaccess\/magpie\/"},{"key":"e_1_3_2_1_2_1","unstructured":"3play Media. Accessed Date 2019-09--15. (Accessed Date 2019-09--15). https:\/\/www.3playmedia.com\/  3play Media. Accessed Date 2019-09--15. (Accessed Date 2019-09--15). https:\/\/www.3playmedia.com\/"},{"key":"e_1_3_2_1_3_1","volume-title":"Wei Liu, Ajmal Mian, and Mubarak Shah.","author":"Aafaq Nayyer","year":"2018","unstructured":"Nayyer Aafaq , Syed Zulqarnain Gilani , Wei Liu, Ajmal Mian, and Mubarak Shah. 2018 . Video Description : A Survey of Methods, Datasets and Evaluation Metrics. CoRR abs\/1806.00186 (2018). Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu, Ajmal Mian, and Mubarak Shah. 2018. Video Description: A Survey of Methods, Datasets and Evaluation Metrics. CoRR abs\/1806.00186 (2018)."},{"key":"e_1_3_2_1_4_1","unstructured":"National Aeronautics and Space Administration (NASA). Accessed date 2019-07--17. NASA-TLX. (Accessed date 2019-07--17). https:\/\/humansystems.arc.nasa.gov\/groups\/TLX\/tlxapp.php  National Aeronautics and Space Administration (NASA). Accessed date 2019-07--17. NASA-TLX. (Accessed date 2019-07--17). https:\/\/humansystems.arc.nasa.gov\/groups\/TLX\/tlxapp.php"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)GT.1943-5606.0001284"},{"key":"e_1_3_2_1_7_1","unstructured":"Microsoft Azure. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/azure.microsoft.com\/en-us\/services\/media-services\/video-indexer\/  Microsoft Azure. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/azure.microsoft.com\/en-us\/services\/media-services\/video-indexer\/"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3241031"},{"key":"e_1_3_2_1_9_1","volume-title":"Jarrell Waggoner, Song Wang, Jinlian Wei, Yifan Yin, and Zhiqi Zhang.","author":"Barbu Andrei","year":"2012","unstructured":"Andrei Barbu , Alexander Bridge , Zachary Burchill , Dan Coroian , Sven Dickinson , Sanja Fidler , Aaron Michaux , Sam Mussman , Siddharth Narayanaswamy , Dhaval Salvi , Lara Schmidt , Jiangnan Shangguan , Jeffrey Mark Siskind , Jarrell Waggoner, Song Wang, Jinlian Wei, Yifan Yin, and Zhiqi Zhang. 2012 . Video In Sentences Out . (2012). Andrei Barbu, Alexander Bridge, Zachary Burchill, Dan Coroian, Sven Dickinson, Sanja Fidler, Aaron Michaux, Sam Mussman, Siddharth Narayanaswamy, Dhaval Salvi, Lara Schmidt, Jiangnan Shangguan, Jeffrey Mark Siskind, Jarrell Waggoner, Song Wang, Jinlian Wei, Yifan Yin, and Zhiqi Zhang. 2012. Video In Sentences Out. (2012)."},{"key":"e_1_3_2_1_10_1","unstructured":"United States Access Board. 2015. Proposed Information and Communication Technology (ICT) Standards and Guidelines. (2015). https:\/\/www.access-board.gov\/guidelines-and-standards\/communications-and-it\/about-the-ict-refresh\/proposed-rule  United States Access Board. 2015. Proposed Information and Communication Technology (ICT) Standards and Guidelines. (2015). https:\/\/www.access-board.gov\/guidelines-and-standards\/communications-and-it\/about-the-ict-refresh\/proposed-rule"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(17)30293-0"},{"key":"e_1_3_2_1_12_1","unstructured":"Matthew Brand. 1997. The\" Inverse hollywood problem\": from video to scripts and storyboards via causal analysis. In AAAI\/IAAI. Citeseer 132--137.  Matthew Brand. 1997. The\" Inverse hollywood problem\": from video to scripts and storyboards via causal analysis. In AAAI\/IAAI. Citeseer 132--137."},{"key":"e_1_3_2_1_13_1","volume-title":"LiveDescribe. AMCIS 2006 Proceedings","author":"Branje Carmen","year":"2006","unstructured":"Carmen Branje , Susan Marshall , Ashley Tyndall , and Deborah Fels . 2006 . LiveDescribe. AMCIS 2006 Proceedings (2006), 368. Carmen Branje, Susan Marshall, Ashley Tyndall, and Deborah Fels. 2006. LiveDescribe. AMCIS 2006 Proceedings (2006), 368."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384916.2384954"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639642.1639685"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_1_17_1","unstructured":"World Wide Web Consortium. 2018. Web Content Accessibility Guidelines 2.1. (2018). https:\/\/www.w3.org\/TR\/WCAG21\/  World Wide Web Consortium. 2018. Web Content Accessibility Guidelines 2.1. (2018). https:\/\/www.w3.org\/TR\/WCAG21\/"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300861"},{"key":"e_1_3_2_1_19_1","volume-title":"Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR.","author":"Das Abhishek","year":"2017","unstructured":"Abhishek Das , Satwik Kottur , Khushi Gupta , Avi Singh , Deshraj Yadav , Jose M. F. Moura , Devi Parikh , and Dhruv Batra . 2017 . Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, Jose M. F. Moura, Devi Parikh, and Dhruv Batra. 2017. Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR.","author":"Das Pradipto","unstructured":"Pradipto Das , Chenliang Xu , Richard F. Doell , and Jason J. Corso . 2013. A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Pradipto Das, Chenliang Xu, Richard F. Doell, and Jason J. Corso. 2013. A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461121.2461130"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049536.2049560"},{"key":"e_1_3_2_1_23_1","unstructured":"Be My Eyes. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/www.bemyeyes.com\/  Be My Eyes. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/www.bemyeyes.com\/"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3233\/TAD-2008-20208"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661334.2661404"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543575"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-008-0141-0"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1328202.1328255"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2593928"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_32_1","volume-title":"Burghouts","author":"Hanckmann Patrick","year":"2012","unstructured":"Patrick Hanckmann , Klamer Schutte , and Gertjan J . Burghouts . 2012 . Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions. Lecture Notes in Computer Science ( 2012), 372--380. Patrick Hanckmann, Klamer Schutte, and Gertjan J. Burghouts. 2012. Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions. Lecture Notes in Computer Science (2012), 372--380."},{"key":"e_1_3_2_1_33_1","volume-title":"Development of NASA-TLX: Results of empirical and theoretical research.\" inP","author":"Hart SG","year":"1988","unstructured":"SG Hart and others. 1988. Development of NASA-TLX: Results of empirical and theoretical research.\" inP . A. Hancock and N. Meshkati (eds.), Human Mental Workload . ( 1988 ). SG Hart and others. 1988. Development of NASA-TLX: Results of empirical and theoretical research.\" inP. A. Hancock and N. Meshkati (eds.), Human Mental Workload. (1988)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45507-5_6"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1658"},{"key":"e_1_3_2_1_37_1","unstructured":"Ting-Yao Hsu Chieh-Yang Huang Yen-Chia Hsu and Ting-Hao 'Kenneth' Huang. 2019b. Visual Story Post-Editing. (2019).  Ting-Yao Hsu Chieh-Yang Huang Yen-Chia Hsu and Ting-Hao 'Kenneth' Huang. 2019b. Visual Story Post-Editing. (2019)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_39_1","unstructured":"Common Objects in Context (COCO). Accessed date 2019-07--17. (Accessed date 2019-07--17). http:\/\/cocodataset.org\/#home  Common Objects in Context (COCO). Accessed date 2019-07--17. (Accessed date 2019-07--17). http:\/\/cocodataset.org\/#home"},{"key":"e_1_3_2_1_40_1","volume-title":"Pythia v0.1: the Winning Entry to the VQA Challenge","author":"Jiang Yu","year":"2018","unstructured":"Yu Jiang , Vivek Natarajan , Xinlei Chen , Marcus Rohrbach , Dhruv Batra , and Devi Parikh . 2018. Pythia v0.1: the Winning Entry to the VQA Challenge 2018 . (2018). Yu Jiang, Vivek Natarajan, Xinlei Chen, Marcus Rohrbach, Dhruv Batra, and Devi Parikh. 2018. Pythia v0.1: the Winning Entry to the VQA Challenge 2018. (2018)."},{"key":"e_1_3_2_1_41_1","volume-title":"The expertise reversal effect. Educational psychologist 38, 1","author":"Kalyuga Slava","year":"2003","unstructured":"Slava Kalyuga . 2003. The expertise reversal effect. Educational psychologist 38, 1 ( 2003 ), 23--31. Slava Kalyuga. 2003. The expertise reversal effect. Educational psychologist 38, 1 (2003), 23--31."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10648-007-9054-3"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025171.3025231"},{"key":"e_1_3_2_1_44_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. (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. (2018)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639642.1639699"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1878803.1878833"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1991.139667"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1090785.1090814"},{"key":"e_1_3_2_1_49_1","unstructured":"ListenByCode. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/www.listenbycode.com\/  ListenByCode. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/www.listenbycode.com\/"},{"key":"e_1_3_2_1_50_1","unstructured":"LiveDescribe. Accessed date 2019-07--17. (Accessed date 2019-07--17).  LiveDescribe. Accessed date 2019-07--17. (Accessed date 2019-07--17)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11430"},{"key":"e_1_3_2_1_52_1","unstructured":"Microsoft. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/docs.microsoft.com\/en-us\/azure\/media-services\/video-indexer\/video-indexer-use-apis  Microsoft. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/docs.microsoft.com\/en-us\/azure\/media-services\/video-indexer\/video-indexer-use-apis"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1177\/0264619606064436"},{"key":"e_1_3_2_1_54_1","unstructured":"Robert Munro. 2020. Human-in-the-Loop Machine Learning. MEAP.  Robert Munro. 2020. Human-in-the-Loop Machine Learning. MEAP."},{"key":"e_1_3_2_1_55_1","volume-title":"Convention on the Rights of Persons with Disabilities and Optional Protocol.","author":"United Nations.","year":"2006","unstructured":"United Nations. 2006 . Convention on the Rights of Persons with Disabilities and Optional Protocol. (2006). https:\/\/www.un.org\/disabilities\/documents\/convention\/convoptprot-e.pdf United Nations. 2006. Convention on the Rights of Persons with Disabilities and Optional Protocol. (2006). https:\/\/www.un.org\/disabilities\/documents\/convention\/convoptprot-e.pdf"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753846.1754085"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . BLEU: a method for automatic evaluation of machine translation . In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180308.3180337"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174192"},{"key":"e_1_3_2_1_60_1","unstructured":"Pythia. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/learnpythia.readthedocs.io\/en\/latest\/  Pythia. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/learnpythia.readthedocs.io\/en\/latest\/"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9810"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049536.2049580"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1969289.1969299"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939505"},{"key":"e_1_3_2_1_65_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)."},{"key":"e_1_3_2_1_66_1","volume-title":"Advances in Neural Information Processing Systems 27","author":"Sutskever Ilya","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks . In Advances in Neural Information Processing Systems 27 , Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc. , 3104--3112. http:\/\/papers.nips.cc\/paper\/5346-sequence-to-sequence-learning-with-neural-networks. pdf Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 3104--3112. http:\/\/papers.nips.cc\/paper\/5346-sequence-to-sequence-learning-with-neural-networks. pdf"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_68_1","unstructured":"Automatic Sync Technologies. Accessed Date 2019-09--15. (Accessed Date 2019-09--15). https:\/\/www.automaticsync.com\/  Automatic Sync Technologies. Accessed Date 2019-09--15. (Accessed Date 2019-09--15). https:\/\/www.automaticsync.com\/"},{"key":"e_1_3_2_1_69_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz 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 Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124941"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.09.014"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209889.3209897"},{"key":"e_1_3_2_1_73_1","unstructured":"YouDescribe. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/youdescribe.org\/  YouDescribe. Accessed date 2019-07--17. (Accessed date 2019-07--17). https:\/\/youdescribe.org\/"}],"event":{"name":"DIS '20: Designing Interactive Systems Conference 2020","location":"Eindhoven Netherlands","acronym":"DIS '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2020 ACM Designing Interactive Systems Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357236.3395433","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357236.3395433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:35Z","timestamp":1750203875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357236.3395433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,3]]},"references-count":73,"alternative-id":["10.1145\/3357236.3395433","10.1145\/3357236"],"URL":"https:\/\/doi.org\/10.1145\/3357236.3395433","relation":{},"subject":[],"published":{"date-parts":[[2020,7,3]]},"assertion":[{"value":"2020-07-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}