{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:19:25Z","timestamp":1781335165062,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3635636.3656192","type":"proceedings-article","created":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T06:24:22Z","timestamp":1719037462000},"page":"311-327","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["VideoMap: Supporting Video Exploration, Brainstorming, and Prototyping in the Latent Space"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0116-0463","authenticated-orcid":false,"given":"David Chuan-En","family":"Lin","sequence":"first","affiliation":[{"name":"Human-Computer Interaction Institute, Carnegie Mellon University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3129-1985","authenticated-orcid":false,"given":"Fabian","family":"Caba Heilbron","sequence":"additional","affiliation":[{"name":"Adobe Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-855X","authenticated-orcid":false,"given":"Joon-Young","family":"Lee","sequence":"additional","affiliation":[{"name":"Adobe Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-7153","authenticated-orcid":false,"given":"Oliver","family":"Wang","sequence":"additional","affiliation":[{"name":"Adobe Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1824-0243","authenticated-orcid":false,"given":"Nikolas","family":"Martelaro","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Descript \u2014 All-in-one video & podcast editing, easy as a doc.Retrieved","year":"2023","unstructured":"2023. Descript \u2014 All-in-one video & podcast editing, easy as a doc.Retrieved March 10, 2023 from https:\/\/www.descript.com"},{"key":"e_1_3_2_1_2_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Get directions and show routes. Retrieved March 10, 2023 from https:\/\/support.google.com\/maps\/answer\/144339"},{"key":"e_1_3_2_1_3_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Match Cuts and Creative Transitions with Examples \u2014 Editing Techniques. Retrieved March 10, 2023 from https:\/\/www.studiobinder.com\/blog\/match-cuts-creative-transitions-examples"},{"key":"e_1_3_2_1_4_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Reflections on Foundation Models. Retrieved August 15, 2023 from https:\/\/hai.stanford.edu\/news\/reflections-foundation-models"},{"key":"e_1_3_2_1_5_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Surprising Facts on The History of Video Editing. Retrieved March 10, 2023 from https:\/\/www.videoeditinginstitute.com\/surprising-facts-on-the-history-of-video-editing"},{"key":"e_1_3_2_1_6_1","volume-title":"Type Studio \u2014 Edit Your Video By Editing Text. Retrieved","year":"2023","unstructured":"2023. Type Studio \u2014 Edit Your Video By Editing Text. Retrieved March 10, 2023 from https:\/\/www.typestudio.co"},{"key":"e_1_3_2_1_7_1","unstructured":"2023. Upwork. Retrieved March 10 2023 from https:\/\/www.upwork.com"},{"key":"e_1_3_2_1_8_1","volume-title":"Retrieved","year":"2023","unstructured":"2023. Working in the Project panel. Retrieved March 10, 2023 from https:\/\/helpx.adobe.com\/premiere-pro\/using\/customizing-project-panel.html"},{"key":"e_1_3_2_1_9_1","volume-title":"Principal component analysis","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi and Lynne\u00a0J Williams. 2010. Principal component analysis. Wiley interdisciplinary reviews: computational statistics 2, 4 (2010), 433\u2013459."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511122"},{"key":"e_1_3_2_1_11_1","volume-title":"On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258","author":"Bommasani Rishi","year":"2021","unstructured":"Rishi Bommasani, Drew\u00a0A Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael\u00a0S Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380296.2380325"},{"key":"e_1_3_2_1_13_1","volume-title":"Video editing with pen-based technology. Multimedia tools and applications 76","author":"Cabral Diogo","year":"2017","unstructured":"Diogo Cabral and Nuno Correia. 2017. Video editing with pen-based technology. Multimedia tools and applications 76 (2017), 6889\u20136914."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/778712.778737"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1412196.1412201"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174025"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445131"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00215"},{"key":"e_1_3_2_1_19_1","volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474778"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415814"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2502052"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV.2005.28"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445765"},{"key":"e_1_3_2_1_25_1","volume-title":"Visual exploration of relationships and structure in low-dimensional embeddings","author":"Eckelt Klaus","year":"2022","unstructured":"Klaus Eckelt, Andreas Hinterreiter, Patrick Adelberger, Conny Walchshofer, Vaishali Dhanoa, Christina Humer, Moritz Heckmann, Christian Steinparz, and Marc Streit. 2022. Visual exploration of relationships and structure in low-dimensional embeddings. IEEE Transactions on Visualization and Computer Graphics (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/354401.354415"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449719"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2022.04.013"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_31_1","volume-title":"Computer Graphics Forum, Vol.\u00a039","author":"Hogr\u00e4fer Marius","unstructured":"Marius Hogr\u00e4fer, Magnus Heitzler, and Hans-J\u00f6rg Schulz. 2020. The state of the art in map-like visualization. In Computer Graphics Forum, Vol.\u00a039. Wiley Online Library, 647\u2013674."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957121"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00437"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00360"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300311"},{"key":"e_1_3_2_1_36_1","volume-title":"Direct manipulation interfaces. Human\u2013computer interaction 1, 4","author":"Hutchins L","year":"1985","unstructured":"Edwin\u00a0L Hutchins, James\u00a0D Hollan, and Donald\u00a0A Norman. 1985. Direct manipulation interfaces. Human\u2013computer interaction 1, 4 (1985), 311\u2013338."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2502038"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357097"},{"key":"e_1_3_2_1_39_1","volume-title":"Surch: Enabling Structural Search and Comparison for Surgical Videos.","author":"Kim Jeongyeon","year":"2023","unstructured":"Jeongyeon Kim, Daeun Choi, Nicole Lee, Matt Beane, and Juho Kim. 2023. Surch: Enabling Structural Search and Comparison for Surgical Videos. (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284825"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073653"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Mackenzie Leake Hijung\u00a0Valentina Shin Joy\u00a0O Kim and Maneesh Agrawala. 2020. Generating Audio-Visual Slideshows from Text Articles Using Word Concreteness.. In CHI Vol.\u00a020. 25\u201330.","DOI":"10.1145\/3313831.3376519"},{"key":"e_1_3_2_1_43_1","volume-title":"Using the\" thinking-aloud\" method in cognitive interface design","author":"Lewis Clayton","unstructured":"Clayton Lewis. 1982. Using the\" thinking-aloud\" method in cognitive interface design. IBM TJ Watson Research Center Yorktown Heights, NY."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2018.8802454"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1\u201313","author":"Chuan-En Lin David","year":"2023","unstructured":"David Chuan-En Lin, Anastasis Germanidis, Crist\u00f3bal Valenzuela, Yining Shi, and Nikolas Martelaro. 2023. Soundify: Matching sound effects to video. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1\u201313."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 16th Conference on Creativity and Cognition.","author":"Chuan-En Lin David","year":"2024","unstructured":"David Chuan-En Lin, Fabian\u00a0Caba Heilbron, Joon-Young Lee, Oliver Wang, and Nikolas Martelaro. 2024. Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior. In Proceedings of the 16th Conference on Creativity and Cognition."},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems.","author":"Chuan-En Lin David","year":"2024","unstructured":"David Chuan-En Lin and Nikolas Martelaro. 2024. Jigsaw: Supporting Designers to Prototype Multimodal Applications by Assembling AI Foundation Models. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems."},{"key":"e_1_3_2_1_48_1","volume-title":"Visual exploration of semantic relationships in neural word embeddings","author":"Liu Shusen","year":"2017","unstructured":"Shusen Liu, Peer-Timo Bremer, Jayaraman\u00a0J Thiagarajan, Vivek Srikumar, Bei Wang, Yarden Livnat, and Valerio Pascucci. 2017. Visual exploration of semantic relationships in neural word embeddings. IEEE transactions on visualization and computer graphics 24, 1 (2017), 553\u2013562."},{"key":"e_1_3_2_1_49_1","volume-title":"Computer graphics forum, Vol.\u00a038","author":"Liu Yang","unstructured":"Yang Liu, Eunice Jun, Qisheng Li, and Jeffrey Heer. 2019. Latent space cartography: Visual analysis of vector space embeddings. In Computer graphics forum, Vol.\u00a038. Wiley Online Library, 67\u201378."},{"key":"e_1_3_2_1_50_1","volume-title":"conference on Artificial intelligence, Vol.\u00a02. 674\u2013679","author":"Lucas D","year":"1981","unstructured":"Bruce\u00a0D Lucas and Takeo Kanade. 1981. An iterative image registration technique with an application to stereo vision. In IJCAI\u201981: 7th international joint conference on Artificial intelligence, Vol.\u00a02. 674\u2013679."},{"key":"e_1_3_2_1_51_1","volume-title":"Reconsidering the image of the city","author":"Lynch Kevin","unstructured":"Kevin Lynch. 1984. Reconsidering the image of the city. Springer."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2466149"},{"key":"e_1_3_2_1_53_1","volume-title":"Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426","author":"McInnes Leland","year":"2018","unstructured":"Leland McInnes, John Healy, and James Melville. 2018. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3202185.3210758"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2466150"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00678"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807502"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Amy Pavel Colorado Reed Bj\u00f6rn Hartmann and Maneesh Agrawala. 2014. Video digests: a browsable skimmable format for informational lecture videos.. In UIST Vol.\u00a010. Citeseer 2642918\u20132647400.","DOI":"10.1145\/2642918.2647400"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471234"},{"key":"e_1_3_2_1_60_1","volume-title":"Computer Graphics Forum, Vol.\u00a035","author":"Pezzotti Nicola","unstructured":"Nicola Pezzotti, Thomas H\u00f6llt, B Lelieveldt, Elmar Eisemann, and Anna Vilanova. 2016. Hierarchical stochastic neighbor embedding. In Computer Graphics Forum, Vol.\u00a035. Wiley Online Library, 21\u201330."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866053"},{"key":"e_1_3_2_1_62_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_63_1","unstructured":"Karel Reisz and Gavin Millar. 1971. The technique of film editing. (1971)."},{"key":"e_1_3_2_1_64_1","volume-title":"The craft of information visualization","author":"Shneiderman Ben","unstructured":"Ben Shneiderman. 2003. The eyes have it: A task by data type taxonomy for information visualizations. In The craft of information visualization. Elsevier, 364\u2013371."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511137"},{"key":"e_1_3_2_1_66_1","volume-title":"Embedding projector: Interactive visualization and interpretation of embeddings. arXiv preprint arXiv:1611.05469","author":"Smilkov Daniel","year":"2016","unstructured":"Daniel Smilkov, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda\u00a0B Vi\u00e9gas, and Martin Wattenberg. 2016. Embedding projector: Interactive visualization and interpretation of embeddings. arXiv preprint arXiv:1611.05469 (2016)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"crossref","unstructured":"Tomas Sokoler H\u00e5kan Edeholt and Martin Johansson. 2002. VideoTable: a tangible interface for collaborative exploration of video material during design sessions. In CHI\u201902 Extended Abstracts on Human Factors in Computing Systems. 656\u2013657.","DOI":"10.1145\/506443.506531"},{"key":"e_1_3_2_1_68_1","volume-title":"Who belongs in the family?Psychometrika 18, 4","author":"Thorndike Robert","year":"1953","unstructured":"Robert Thorndike. 1953. Who belongs in the family?Psychometrika 18, 4 (1953), 267\u2013276."},{"key":"e_1_3_2_1_69_1","volume-title":"Computer Graphics Forum, Vol.\u00a030","author":"Tong Ruo-Feng","year":"2049","unstructured":"Ruo-Feng Tong, Yun Zhang, and Meng Ding. 2011. Video brush: A novel interface for efficient video cutout. In Computer Graphics Forum, Vol.\u00a030. Wiley Online Library, 2049\u20132057."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/169059.169117"},{"key":"e_1_3_2_1_71_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_72_1","volume-title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing. arXiv preprint arXiv:2402.10294","author":"Wang Bryan","year":"2024","unstructured":"Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu, and Raj Sodhi. 2024. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing. arXiv preprint arXiv:2402.10294 (2024)."},{"key":"e_1_3_2_1_73_1","volume-title":"Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos. arXiv preprint arXiv:2103.17261","author":"Wang Kevin","year":"2021","unstructured":"Kevin Wang, Deva Ramanan, and Aayush Bansal. 2021. Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos. arXiv preprint arXiv:2103.17261 (2021)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356520"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVMP.2009.8"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415882"},{"key":"e_1_3_2_1_77_1","volume-title":"Content based lecture video retrieval using speech and video text information","author":"Yang Haojin","year":"2014","unstructured":"Haojin Yang and Christoph Meinel. 2014. Content based lecture video retrieval using speech and video text information. IEEE transactions on learning technologies 7, 2 (2014), 142\u2013154."},{"key":"e_1_3_2_1_78_1","volume-title":"SoftVideo: Improving the Learning Experience of Software Tutorial Videos with Collective Interaction Data. In 27th International Conference on Intelligent User Interfaces. 646\u2013660","author":"Yang Saelyne","year":"2022","unstructured":"Saelyne Yang, Jisu Yim, Aitolkyn Baigutanova, Seoyoung Kim, Minsuk Chang, and Juho Kim. 2022. SoftVideo: Improving the Learning Experience of Software Tutorial Videos with Collective Interaction Data. In 27th International Conference on Intelligent User Interfaces. 646\u2013660."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159703"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/1226969.1226978"}],"event":{"name":"C&C '24: Creativity and Cognition","location":"Chicago IL USA","acronym":"C&C '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Creativity and Cognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635636.3656192","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3635636.3656192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:58:41Z","timestamp":1755885521000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635636.3656192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":80,"alternative-id":["10.1145\/3635636.3656192","10.1145\/3635636"],"URL":"https:\/\/doi.org\/10.1145\/3635636.3656192","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}