{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:46:01Z","timestamp":1777376761373,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":109,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0-01347,Video Interaction Technologies Using Object-Oriented Video Modeling).","award":["2021-0-01347"],"award-info":[{"award-number":["2021-0-01347"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,18]]},"DOI":"10.1145\/3640543.3645164","type":"proceedings-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T18:23:12Z","timestamp":1712341392000},"page":"515-536","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["ExpressEdit: Video Editing with Natural Language and Sketching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0002-5400","authenticated-orcid":false,"given":"Bekzat","family":"Tilekbay","sequence":"first","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1776-4712","authenticated-orcid":false,"given":"Saelyne","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3522-2259","authenticated-orcid":false,"given":"Michal Adam","family":"Lewkowicz","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yale University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9494-2256","authenticated-orcid":false,"given":"Alex","family":"Suryapranata","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6348-4127","authenticated-orcid":false,"given":"Juho","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST, Korea, Republic of"}]}],"member":"320","published-online":{"date-parts":[[2024,4,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103915"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Khan Academy. 2024. Khan Academy. https:\/\/www.khanacademy.org Accessed: 2024-01-25.","DOI":"10.5465\/AMPROC.2024.20562abstract"},{"key":"e_1_3_2_1_3_1","unstructured":"Adobe. 2024. Adobe Photoshop. https:\/\/www.adobe.com\/products\/photoshop.html Accessed: 2024-01-25."},{"key":"e_1_3_2_1_4_1","unstructured":"Adobe. 2024. Adobe Premiere Pro. https:\/\/www.adobe.com\/products\/premiere.html Accessed: 2024-01-25."},{"key":"e_1_3_2_1_5_1","unstructured":"Remotion AG. 2024. Remotion. https:\/\/www.remotion.dev Accessed: 2024-01-25."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Saleema Amershi Dan Weld Mihaela Vorvoreanu Adam Fourney Besmira Nushi Penny Collisson Jina Suh Shamsi Iqbal Paul Bennett Kori Inkpen Jaime Teevan Ruth Kikin-Gil and Eric Horvitz. 2019. Guidelines for Human-AI Interaction. https:\/\/www.microsoft.com\/en-us\/research\/publication\/guidelines-for-human-ai-interaction\/","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_2_1_7_1","unstructured":"Apple. 2024. Final Cut Pro. https:\/\/www.apple.com\/final-cut-pro Accessed: 2024-01-25."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Omer Bar-Tal Dolev Ofri-Amar Rafail Fridman Yoni Kasten and Tali Dekel. 2022. Text2LIVE: Text-Driven Layered Image and Video Editing. https:\/\/doi.org\/10.48550\/arXiv.2204.02491","DOI":"10.48550\/arXiv.2204.02491"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185563"},{"key":"e_1_3_2_1_10_1","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/arxiv.org\/abs\/2005.14165v4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449287"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2018.08.035"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3329-y"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Linda Candy. 2013. Evaluating Creativity. 57\u201384. https:\/\/doi.org\/10.1007\/978-1-4471-4111-2_4","DOI":"10.1007\/978-1-4471-4111-2_4"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Yihan Cao Siyu Li Yixin Liu Zhiling Yan Yutong Dai Philip\u00a0S. Yu and Lichao Sun. 2023. A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT. https:\/\/doi.org\/10.48550\/arXiv.2303.04226","DOI":"10.48550\/arXiv.2303.04226"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/778712.778737"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Wenhao Chai Xun Guo Gaoang Wang and Yan Lu. 2023. StableVideo: Text-driven Consistency-aware Diffusion Video Editing. https:\/\/doi.org\/10.48550\/arXiv.2308.09592","DOI":"10.48550\/arXiv.2308.09592"},{"key":"e_1_3_2_1_18_1","volume-title":"Cut by cut: editing your film or video. Michael Wiese Productions","author":"Chandler Gael","unstructured":"Gael Chandler. 2004. Cut by cut: editing your film or video. Michael Wiese Productions, Studio City, CA."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445131"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114806"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2617588"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545676"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474778"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415814"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2502052"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501819"},{"key":"e_1_3_2_1_27_1","volume-title":"Livestream: Getting Started with C++ (Episode 1). Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/OKQpOzEY_A4","year":"2018","unstructured":"Codecademy. 2018. Livestream: Getting Started with C++ (Episode 1). Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/OKQpOzEY_A4"},{"key":"e_1_3_2_1_28_1","unstructured":"Descript. 2024. Descript. https:\/\/www.descript.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_29_1","unstructured":"Nick DiGiovanni. 2023. Learn To Cook In Less Than 1 Hour. Video. Retrieved on 2024-01-25 from https:\/\/youtu.be\/zhI7bQyTmHw"},{"key":"e_1_3_2_1_30_1","unstructured":"edX LLC. 2024. edX. https:\/\/www.edx.org Accessed: 2024-01-25."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2018.07.015"},{"key":"e_1_3_2_1_32_1","unstructured":"Ohad Fried and Maneesh Agrawala. 2019. Puppet Dubbing. https:\/\/arxiv.org\/abs\/1902.04285v1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2876456.2879472"},{"key":"e_1_3_2_1_35_1","unstructured":"Google. 2024. Google Slides. https:\/\/slides.google.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556325.2566239"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.02303"},{"key":"e_1_3_2_1_39_1","unstructured":"P.\u00a0T. Hove. 2014. Characteristics of instructional videos for conceptual knowledge development. https:\/\/www.semanticscholar.org\/paper\/Characteristics-of-instructional-videos-for-Hove\/c377da3ea8c08dbe79cd36927b25154ecb51cb48"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101318"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Nisha Huang Yuxin Zhang and Weiming Dong. 2023. Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer. https:\/\/doi.org\/10.48550\/arXiv.2305.05464","DOI":"10.48550\/arXiv.2305.05464"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300311"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581494"},{"key":"e_1_3_2_1_44_1","unstructured":"Imvidu. 2024. Imvidu. https:\/\/imvidu.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_45_1","unstructured":"Apple Inc. 2024. iMovie. https:\/\/www.apple.com\/ca\/imovie Accessed: 2024-01-25."},{"key":"e_1_3_2_1_46_1","unstructured":"Coursera Inc. 2024. Coursera. https:\/\/www.coursera.org Accessed: 2024-01-25."},{"key":"e_1_3_2_1_47_1","unstructured":"Upwork\u00a0Global Inc.2024. Upwork. https:\/\/www.upwork.com\/ Accessed: 2024-01-25."},{"key":"e_1_3_2_1_48_1","unstructured":"Zoom Video\u00a0Communications Inc. 2024. Zoom. https:\/\/zoom.us Accessed: 2024-01-25."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517741"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581196"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1378063.1378140"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4275-4"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC50065.2020.9127288"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2556986"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501931"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. https:\/\/doi.org\/10.48550\/arXiv.2304.02643","DOI":"10.48550\/arXiv.2304.02643"},{"key":"e_1_3_2_1_57_1","unstructured":"KonvaJS. 2024. KonvaJS. https:\/\/konvajs.org Accessed: 2024-01-25."},{"key":"e_1_3_2_1_58_1","unstructured":"LangChain. 2024. LangChain. https:\/\/www.langchain.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481301"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073653"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376519"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206505.3206602"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.06818"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. https:\/\/doi.org\/10.48550\/arXiv.2301.12597 arXiv:2301.12597 [cs].","DOI":"10.48550\/arXiv.2301.12597"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545702"},{"key":"e_1_3_2_1_66_1","unstructured":"David Chuan-En Lin Fabian\u00a0Caba Heilbron Joon-Young Lee Oliver Wang and Nikolas Martelaro. 2022. VideoMap: Video Editing in Latent Space. https:\/\/arxiv.org\/abs\/2211.12492v1"},{"key":"e_1_3_2_1_67_1","unstructured":"Steve\u00a0Kaufmann lingosteve. 2019. Language Learning Live Stream. Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/3_nLdcHBJY4"},{"key":"e_1_3_2_1_68_1","unstructured":"Doctor\u00a0Gary Linkov. 2022. Surgeon does Live QA | Hair Loss Awareness Month. Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/sz8Lo3NY1m0"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","unstructured":"Zachary\u00a0C. Lipton. 2017. The Mythos of Model Interpretability. https:\/\/doi.org\/10.48550\/arXiv.1606.03490","DOI":"10.48550\/arXiv.1606.03490"},{"key":"e_1_3_2_1_70_1","unstructured":"Google LLC. 2024. YouTube. https:\/\/www.youtube.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_71_1","unstructured":"Blackmagic Design\u00a0Pty. Ltd. 2024. DaVinci Resolve. https:\/\/www.blackmagicdesign.com\/products\/davinciresolve Accessed: 2024-01-25."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2190389"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","unstructured":"Jiaju Ma Anyi Rao Li-Yi Wei Rubaiat\u00a0Habib Kazi Hijung\u00a0Valentina Shin and Maneesh Agrawala. 2023. Automated Conversion of Music Videos into Lyric Videos. https:\/\/doi.org\/10.1145\/3586183.3606757","DOI":"10.1145\/3586183.3606757"},{"key":"e_1_3_2_1_74_1","unstructured":"Meta. 2024. React. https:\/\/react.dev Accessed: 2024-01-25."},{"key":"e_1_3_2_1_75_1","unstructured":"MobX. 2024. MobX. https:\/\/mobx.js.org Accessed: 2024-01-25."},{"key":"e_1_3_2_1_76_1","unstructured":"Jamie Oliver. 2011. Jamie Oliver live - pasta. Video. Retrieved on 2024-01-25 from https:\/\/youtu.be\/b3TVLNNqgdc"},{"key":"e_1_3_2_1_77_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2303.08774"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027957"},{"key":"e_1_3_2_1_79_1","unstructured":"Pallets. 2024. Flask. https:\/\/flask.palletsprojects.com Accessed: 2024-01-25."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580676"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807502"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984552"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647400"},{"key":"e_1_3_2_1_84_1","unstructured":"Gillian Perkins. 2020. How To SURVIVE As An Entrepreneur. Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/oYMAX90kNkU"},{"key":"e_1_3_2_1_85_1","unstructured":"Gillian Perkins. 2023. the mindset shift that will finally change your work-life. Video. Retrieved on 2024-01-25 from https:\/\/youtu.be\/T8LE3SpZdag"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","unstructured":"Chenyang Qi Xiaodong Cun Yong Zhang Chenyang Lei Xintao Wang Ying Shan and Qifeng Chen. 2023. FateZero: Fusing Attentions for Zero-shot Text-based Video Editing. https:\/\/doi.org\/10.48550\/arXiv.2303.09535","DOI":"10.48550\/arXiv.2303.09535"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","unstructured":"Bosheng Qin Juncheng Li Siliang Tang Tat-Seng Chua and Yueting Zhuang. 2023. InstructVid2Vid: Controllable Video Editing with Natural Language Instructions. https:\/\/doi.org\/10.48550\/arXiv.2305.12328","DOI":"10.48550\/arXiv.2305.12328"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"e_1_3_2_1_89_1","unstructured":"Gordon Ramsey. 2021. At Home for the Holidays with Gordon Ramsay. Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/kdN41iYTg3U"},{"key":"e_1_3_2_1_90_1","unstructured":"Nils Reimers. 2024. SentenceTransformers. https:\/\/www.sbert.net Accessed: 2024-01-25."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300852"},{"key":"e_1_3_2_1_92_1","volume-title":"Benchmarks & Best Practices","author":"Sauro Jeff","unstructured":"Jeff Sauro. 2011. A Practical Guide to the System Usability Scale: Background, Benchmarks & Best Practices. CreateSpace Independent Publishing Platform. Open Library ID: OL26858541M."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173893"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2021.12.005"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"e_1_3_2_1_96_1","unstructured":"Linus\u00a0Tech Tips. 2018. Microsoft Surface Go - Classic LIVE Unboxing. Video. Retrieved on 2024-01-25 from https:\/\/www.youtube.com\/live\/4LdIvyfzoGY"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984569"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00230"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/1983302.1983311"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356520"},{"key":"e_1_3_2_1_101_1","unstructured":"Yi Wang Kunchang Li Yizhuo Li Yinan He Bingkun Huang Zhiyu Zhao Hongjie Zhang Jilan Xu Yi Liu Zun Wang Sen Xing Guo Chen Junting Pan Jiashuo Yu Yali Wang Limin Wang and Yu Qiao. 2022. InternVideo: General Video Foundation Models via Generative and Discriminative Learning. https:\/\/arxiv.org\/abs\/2212.03191v2"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","unstructured":"Tongshuang Wu Michael Terry and Carrie\u00a0J. Cai. 2022. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. https:\/\/doi.org\/10.48550\/arXiv.2110.01691","DOI":"10.48550\/arXiv.2110.01691"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415882"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517461"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","unstructured":"Xinwei Yao Ohad Fried Kayvon Fatahalian and Maneesh Agrawala. 2020. Iterative Text-based Editing of Talking-heads Using Neural Retargeting. https:\/\/doi.org\/10.48550\/arXiv.2011.10688","DOI":"10.48550\/arXiv.2011.10688"},{"key":"e_1_3_2_1_106_1","unstructured":"youtube-dl developers. 2024. youtube-dl. https:\/\/ytdl-org.github.io\/youtube-dl Accessed: 2024-01-25."},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502036"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474812"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502062"}],"event":{"name":"IUI '24: 29th International Conference on Intelligent User Interfaces","location":"Greenville SC USA","acronym":"IUI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 29th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645164","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640543.3645164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:58:47Z","timestamp":1764550727000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640543.3645164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":109,"alternative-id":["10.1145\/3640543.3645164","10.1145\/3640543"],"URL":"https:\/\/doi.org\/10.1145\/3640543.3645164","relation":{},"subject":[],"published":{"date-parts":[[2024,3,18]]},"assertion":[{"value":"2024-04-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}