{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:22:56Z","timestamp":1790832176744,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"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":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676326","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["BlendScape: Enabling End-User Customization of Video-Conferencing Environments through Generative AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7645-4488","authenticated-orcid":false,"given":"Shwetha","family":"Rajaram","sequence":"first","affiliation":[{"name":"Microsoft Research, United States and School of Information, University of Michigan, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2931-7653","authenticated-orcid":false,"given":"Nels","family":"Numan","sequence":"additional","affiliation":[{"name":"Microsoft Research, United States and Department of Computer Science, University College London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4816-2063","authenticated-orcid":false,"given":"Balasaravanan Thoravi","family":"Kumaravel","sequence":"additional","affiliation":[{"name":"Microsoft Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5473-2448","authenticated-orcid":false,"given":"Nicolai","family":"Marquardt","sequence":"additional","affiliation":[{"name":"Microsoft Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5751-9354","authenticated-orcid":false,"given":"Andrew D","family":"Wilson","sequence":"additional","affiliation":[{"name":"Microsoft Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015718"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276390"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445450"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606725"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_2_2_6_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a033. Curran Associates","author":"Brown Tom","year":"1877","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D 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 Ziegler, Jeffrey Wu, Clemens Winter, Chris 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. In Advances in Neural Information Processing Systems, Vol.\u00a033. Curran Associates, Inc., 1877\u20131901."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-483-6_13"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445192"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610196"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468080"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3595961"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","unstructured":"John Joon\u00a0Young Chung and Eytan Adar. 2023. PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions. https:\/\/doi.org\/10.1145\/3586183.3606777 arxiv:2308.05184\u00a0[cs]","DOI":"10.1145\/3586183.3606777"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501819"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383316"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Hai Dang Frederik Brudy George Fitzmaurice and Fraser Anderson. 2023. WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI. arxiv:2308.13355\u00a0[cs]","DOI":"10.1145\/3586183.3606772"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502141"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208589"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01040"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbr.2021.100119"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810543.1810550"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445191"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Georgia Gkioxari Jitendra Malik and Justin Johnson. 2020. Mesh R-CNN. arxiv:1906.02739\u00a0[cs]","DOI":"10.1109\/ICCV.2019.00988"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606767"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445698"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581515"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581350"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567721"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581013"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581148"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557382"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581085"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294211.1294256"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating Conditional 3D Implicit Functions. https:\/\/doi.org\/10.48550\/arXiv.2305.02463 arxiv:2305.02463\u00a0[cs]","DOI":"10.48550\/arXiv.2305.02463"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208333"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.02960"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347872"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492829"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517545"},{"key":"e_1_3_2_2_40_1","volume-title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation. arxiv","author":"Li Jialu","year":"2023","unstructured":"Jialu Li and Mohit Bansal. 2023. PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation. arxiv (2023)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545621"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. https:\/\/doi.org\/10.48550\/arXiv.1411.1784 arxiv:1411.1784\u00a0[cs stat]","DOI":"10.48550\/arXiv.1411.1784"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/289444.289489"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642419"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/VRW58643.2023.00108"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676361"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1959022.1959025"},{"key":"e_1_3_2_2_49_1","volume-title":"Simplifying Object Segmentation with PixelLib Library. (Jan","author":"Olafenwa Ayoola","year":"2021","unstructured":"Ayoola Olafenwa. 2021. Simplifying Object Segmentation with PixelLib Library. (Jan. 2021)."},{"key":"e_1_3_2_2_50_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2303.08774 arxiv:2303.08774\u00a0[cs]"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2819965"},{"key":"e_1_3_2_2_52_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving Language Understanding by Generative Pre-Training."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.17730\/humo.56.2.x335923511444655"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","unstructured":"Shikhar Sharma Dendi Suhubdy Vincent Michalski Samira\u00a0Ebrahimi Kahou and Yoshua Bengio. 2018. ChatPainter: Improving Text to Image Generation Using Dialogue. https:\/\/doi.org\/10.48550\/arXiv.1802.08216 arxiv:1802.08216\u00a0[cs]","DOI":"10.48550\/arXiv.1802.08216"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610200"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519026"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3229434.3229476"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242597"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347875"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445512"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858224"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581136"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. https:\/\/doi.org\/10.48550\/arXiv.2302.05543 arxiv:2302.05543\u00a0[cs]","DOI":"10.48550\/arXiv.2302.05543"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073703"}],"event":{"name":"UIST '24: The 37th Annual ACM Symposium on User Interface Software and Technology","location":"Pittsburgh PA USA","acronym":"UIST '24"},"container-title":["Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676326","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:13:15Z","timestamp":1754341995000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":66,"alternative-id":["10.1145\/3654777.3676326","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676326","relation":{},"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"2024-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}