{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:12:28Z","timestamp":1776114748835,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":87,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,13]]},"DOI":"10.1145\/3654777.3676379","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:50:36Z","timestamp":1728643836000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":57,"title":["Augmented Object Intelligence with XR-Objects"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3983-1955","authenticated-orcid":false,"given":"Mustafa Doga","family":"Dogan","sequence":"first","affiliation":[{"name":"Google, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2846-7687","authenticated-orcid":false,"given":"Eric J","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-0530","authenticated-orcid":false,"given":"Karan","family":"Ahuja","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2471-9776","authenticated-orcid":false,"given":"Ruofei","family":"Du","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6661-2216","authenticated-orcid":false,"given":"Andrea","family":"Cola\u00e7o","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3084-4553","authenticated-orcid":false,"given":"Johnny","family":"Lee","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6165-4495","authenticated-orcid":false,"given":"Mar","family":"Gonzalez-Franco","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0508-3509","authenticated-orcid":false,"given":"David","family":"Kim","sequence":"additional","affiliation":[{"name":"Google, Switzerland"}]}],"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\/3332165.3347884"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/259964.260139"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616536"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2076354.2076378"},{"key":"e_1_3_2_2_5_1","unstructured":"Navyata Bawa. 2022. Building Intuitive Interactions in VR: Interaction SDK First Hand Showcase and Other Resources. https:\/\/developers.facebook.com\/blog\/post\/2022\/11\/22\/building-intuitive-interactions-vr\/"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1188816.1188820"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580988"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526114.3558697"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642734"},{"key":"e_1_3_2_2_10_1","unstructured":"Xi Chen Xiao Wang Soravit Changpinyo A.\u00a0J. Piergiovanni Piotr Padlewski Daniel Salz Sebastian Goodman Adam Grycner Basil Mustafa Lucas Beyer Alexander Kolesnikov Joan Puigcerver Nan Ding Keran Rong Hassan Akbari Gaurav Mishra Linting Xue Ashish Thapliyal James Bradbury Weicheng Kuo Mojtaba Seyedhosseini Chao Jia Burcu\u00a0Karagol Ayan Carlos Riquelme Andreas Steiner Anelia Angelova Xiaohua Zhai Neil Houlsby and Radu Soricut. 2023. PaLI: A Jointly-Scaled Multilingual Language-Image Model. _eprint: 2209.06794."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376436"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474750"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606717"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461778.3462126"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR55827.2022.00048"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606827"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585738"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings Ninth IEEE International Conference on Computer Vision. IEEE, 1403\u20131410","year":"2003","unstructured":"Davison. 2003. Real-time simultaneous localisation and mapping with a single camera. In Proceedings Ninth IEEE International Conference on Computer Vision. IEEE, 1403\u20131410."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.11748"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3516510"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474733"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376202"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606758"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585905"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501951"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519905"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519911"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415881"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501836"},{"key":"e_1_3_2_2_30_1","volume-title":"XDTK: A Cross-Device Toolkit for Input & Interaction in XR. In 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE.","author":"Gonzalez J.","year":"2024","unstructured":"Eric\u00a0J. Gonzalez, Khushman Patel, Karan Ahuja, and Mar Gonzalez-Franco. 2024. XDTK: A Cross-Device Toolkit for Input & Interaction in XR. In 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE."},{"key":"e_1_3_2_2_31_1","volume-title":"Guidelines for Productivity in Virtual Reality. ACM Interactions Magazine","author":"Gonzalez-Franco Mar","year":"2024","unstructured":"Mar Gonzalez-Franco and Andrea Colaco. 2024. Guidelines for Productivity in Virtual Reality. ACM Interactions Magazine (2024). Publisher: ACM."},{"key":"e_1_3_2_2_32_1","volume-title":"Model of illusions and virtual reality. Frontiers in psychology 8","author":"Gonzalez-Franco Mar","year":"2017","unstructured":"Mar Gonzalez-Franco and Jaron Lanier. 2017. Model of illusions and virtual reality. Frontiers in psychology 8 (2017), 273943. Publisher: Frontiers."},{"key":"e_1_3_2_2_33_1","unstructured":"Google. 2024. ARCore. https:\/\/developers.google.com\/ar"},{"key":"e_1_3_2_2_34_1","unstructured":"Google. 2024. XR-Objects repository. https:\/\/github.com\/google\/xr-objects original-date: 2024-02-17T11:08:33Z."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626472"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300577"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580704"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1450579.1450625"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858134"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494091.2494185"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581072"},{"key":"e_1_3_2_2_42_1","unstructured":"Apple Inc. 2024. ARKit. https:\/\/developer.apple.com\/augmented-reality\/arkit\/"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1347390.1347392"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/258549.258715"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606793"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_47_1","volume-title":"Statistical reasoning in the behavioral sciences","author":"King M","unstructured":"Bruce\u00a0M King, Patrick\u00a0J Rosopa, and Edward\u00a0W Minium. 2018. Statistical reasoning in the behavioral sciences. John Wiley & Sons."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486950"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642230"},{"key":"e_1_3_2_2_50_1","volume-title":"Evaluating human-language model interaction. arXiv preprint arXiv:2212.09746","author":"Lee Mina","year":"2022","unstructured":"Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang\u00a0Lisa Li, Faisal Ladhak, Frieda Rong, and others. 2022. Evaluating human-language model interaction. arXiv preprint arXiv:2212.09746 (2022)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1520340.1520511"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642068"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300917"},{"key":"e_1_3_2_2_54_1","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C.\u00a0Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. http:\/\/arxiv.org\/abs\/1405.0312 arXiv:1405.0312 [cs]."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347945"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858457"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173703"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517723"},{"key":"e_1_3_2_2_59_1","volume-title":"Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172","author":"Lugaresi Camillo","year":"2019","unstructured":"Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming\u00a0Guang Yong, Juhyun Lee, and others. 2019. Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376479"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581449"},{"key":"e_1_3_2_2_62_1","unstructured":"Meredith\u00a0Ringel Morris Jascha Sohl-dickstein Noah Fiedel Tris Warkentin Allan Dafoe Aleksandra Faust Clement Farabet and Shane Legg. 2024. Levels of AGI: Operationalizing Progress on the Path to AGI. _eprint: 2311.02462."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3636313"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359997.3365693"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517486"},{"key":"e_1_3_2_2_66_1","volume-title":"Understanding the potential of technology to support enhanced activities of daily living (EADLs).Gerontechnology 19, 2","author":"Rogers A","year":"2020","unstructured":"Wendy\u00a0A Rogers, Tracy\u00a0L Mitzner, and Michael\u00a0T Bixter. 2020. Understanding the potential of technology to support enhanced activities of daily living (EADLs).Gerontechnology 19, 2 (2020)."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/1842993.1843021"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300767"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610879"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642400"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586182.3617432"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415892"},{"key":"e_1_3_2_2_73_1","volume-title":"attend, and segment: Unsupervised zero-shot segmentation using stable diffusion. arXiv preprint arXiv:2308.12469","author":"Tian Junjiao","year":"2023","unstructured":"Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, and Mar Gonzalez-Franco. 2023. Diffuse, attend, and segment: Unsupervised zero-shot segmentation using stable diffusion. arXiv preprint arXiv:2308.12469 (2023)."},{"key":"e_1_3_2_2_74_1","volume-title":"Designing Interfaces: Patterns for Effective Interaction Design (3 ed.). O\u2019Reilly Media. https:\/\/www.amazon.com\/Designing-Interfaces-Patterns-Effective-Interaction\/dp\/1492051969","author":"Tidwell Jenifer","year":"2020","unstructured":"Jenifer Tidwell, Charles Brewer, and Aynne Valencia. 2020. Designing Interfaces: Patterns for Effective Interaction Design (3 ed.). O\u2019Reilly Media. https:\/\/www.amazon.com\/Designing-Interfaces-Patterns-Effective-Interaction\/dp\/1492051969"},{"key":"e_1_3_2_2_75_1","volume-title":"Understanding Physical Breakdowns in Virtual Reality. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems(CHI EA \u201923)","author":"Tseng Wen-Jie","year":"2023","unstructured":"Wen-Jie Tseng. 2023. Understanding Physical Breakdowns in Virtual Reality. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems(CHI EA \u201923). Association for Computing Machinery, New York, NY, USA. event-place: Hamburg,Germany."},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517728"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275041"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631413"},{"key":"e_1_3_2_2_79_1","first-page":"7","article-title":"Hick\u2013Hyman Law is Mediated by the Cognitive Control Network in the Brain","volume":"28","author":"Wu Tingting","year":"2017","unstructured":"Tingting Wu, Alexander\u00a0J Dufford, Laura\u00a0J Egan, Melissa-Ann Mackie, Cong Chen, Changhe Yuan, Chao Chen, Xiaobo Li, Xun Liu, Patrick\u00a0R Hof, and Jin Fan. 2017. Hick\u2013Hyman Law is Mediated by the Cognitive Control Network in the Brain. Cerebral Cortex 28, 7 (May 2017), 2267\u20132282.","journal-title":"Cerebral Cortex"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109046"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526114.3558721"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","unstructured":"Bingjie Xu Shunan Guo Eunyee Koh Jane Hoffswell Ryan Rossi and Fan Du. 2022. ARShopping: In-Store Shopping Decision Support Through Augmented Reality and Immersive Visualization. In 2022 IEEE Visualization and Visual Analytics (VIS). 120\u2013124. https:\/\/doi.org\/10.1109\/VIS54862.2022.00033 ISSN: 2771-9553.","DOI":"10.1109\/VIS54862.2022.00033"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581500"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347954"},{"key":"e_1_3_2_2_85_1","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A Survey on Multimodal Large Language Models. _eprint: 2306.13549."},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/2638404.2638518"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545668"}],"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\/3654777.3676379","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654777.3676379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T21:12:04Z","timestamp":1754341924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654777.3676379"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":87,"alternative-id":["10.1145\/3654777.3676379","10.1145\/3654777"],"URL":"https:\/\/doi.org\/10.1145\/3654777.3676379","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"}}]}}