{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T19:23:13Z","timestamp":1784143393397,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DGE-2140004"],"award-info":[{"award-number":["DGE-2140004"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642230","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:38:25Z","timestamp":1715416705000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":93,"title":["GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Reality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1481-9290","authenticated-orcid":false,"given":"Jaewook","family":"Lee","sequence":"first","affiliation":[{"name":"Paul G. Allen School of Computer Science & Engineering, University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6066-4286","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Paul G. Allen School of Computer Science & Engineering, University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1554-7079","authenticated-orcid":false,"given":"Elizabeth","family":"Brown","sequence":"additional","affiliation":[{"name":"Computational Linguistics, University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2918-8152","authenticated-orcid":false,"given":"Liam","family":"Chu","sequence":"additional","affiliation":[{"name":"Applied and Computational Mathematical Sciences, University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7003-1764","authenticated-orcid":false,"given":"Sebastian S.","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana-Champaign, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8291-3353","authenticated-orcid":false,"given":"Jon E.","family":"Froehlich","sequence":"additional","affiliation":[{"name":"Paul G. Allen School of Computer Science & Engineering, University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445638"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174156"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19574.2021.9720526"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356093"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","unstructured":"Shay Aharon Louis-Dupont Ofri Masad Kate Yurkova Lotem Fridman Lkdci Eugene Khvedchenya Ran Rubin Natan Bagrov Borys Tymchenko Tomer Keren Alexander Zhilko and Eran-Deci. 2023. Super-Gradients. https:\/\/doi.org\/10.5281\/ZENODO.7789328","DOI":"10.5281\/ZENODO.7789328"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3311956"},{"key":"e_1_3_3_3_7_1","unstructured":"Amazon AWS. 2023. Amazon Rekognition. https:\/\/aws.amazon.com\/rekognition\/"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3264901"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/800250.807503"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_3_3_12_1","volume-title":"SUS: A \u2019Quick and Dirty","author":"Brooke B.","year":"1996","unstructured":"J.\u00a0B. Brooke. 1996. SUS: A \u2019Quick and Dirty\u2019 Usability Scale."},{"key":"e_1_3_3_3_13_1","unstructured":"Donna\u00a0K. Byron and James\u00a0F. Allen. 1998. Resolving Demonstrative Anaphora in the TRAINS93 Corpus."},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00413"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820752"},{"key":"e_1_3_3_3_16_1","unstructured":"Google Cloud. 2023. Vision AI. https:\/\/cloud.google.com\/vision"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/266180.266328"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03196975"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/169891.169968"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448018.3458008"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196709.3196781"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492342"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2020.555265"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2004.38"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1075\/sl.27.1.04dix"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1378063.1378122"},{"key":"e_1_3_3_3_27_1","volume-title":"Autoethnography: An Overview. Historical Social Research \/ Historische Sozialforschung 36, 4 (138)","author":"Ellis Carolyn","year":"2011","unstructured":"Carolyn Ellis, Tony\u00a0E. Adams, and Arthur\u00a0P. Bochner. 2011. Autoethnography: An Overview. Historical Social Research \/ Historische Sozialforschung 36, 4 (138) (2011), 273\u2013290. http:\/\/www.jstor.org\/stable\/23032294"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807499"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300276"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1059981.1059982"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2543720"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685309"},{"key":"e_1_3_3_3_33_1","unstructured":"Liane Guillou. 2016. Incorporating pronoun function into statistical machine translation."},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.3115\/981175.981181"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR52148.2021.00060"},{"key":"e_1_3_3_3_36_1","volume-title":"Advances in Artificial Reality and Tele-Existence, Zhigeng Pan, Adrian Cheok, Michael Haller, Rynson W.\u00a0H","author":"Irawati Sylvia","unstructured":"Sylvia Irawati, Scott Green, Mark Billinghurst, Andreas Duenser, and Heedong Ko. 2006. An Evaluation of an Augmented Reality Multimodal Interface Using Speech and Paddle Gestures. In Advances in Artificial Reality and Tele-Existence, Zhigeng Pan, Adrian Cheok, Michael Haller, Rynson W.\u00a0H. Lau, Hideo Saito, and Ronghua Liang (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 272\u2013283."},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197391.3205404"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702393"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3236362"},{"key":"e_1_3_3_3_40_1","volume-title":"Enabling Fine-Grained Permissions for Augmented Reality Applications with Recognizers. In 22nd USENIX Security Symposium (USENIX Security 13)","author":"Jana Suman","year":"2013","unstructured":"Suman Jana, David Molnar, Alexander Moshchuk, Alan Dunn, Benjamin Livshits, Helen\u00a0J. Wang, and Eyal Ofek. 2013. Enabling Fine-Grained Permissions for Augmented Reality Applications with Recognizers. In 22nd USENIX Security Symposium (USENIX Security 13). USENIX Association, Washington, D.C., 415\u2013430. https:\/\/www.usenix.org\/conference\/usenixsecurity13\/technical-sessions\/presentation\/jana"},{"key":"e_1_3_3_3_41_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. YOLOv8 by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502134"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479938"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3107884.3107899"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173655"},{"key":"e_1_3_3_3_46_1","volume-title":"Proceedings of Speeh Tech\u201992 (1992","author":"T\u00a0S.","year":"1980","unstructured":"OVIATT\u00a0S. L.1992. Pen\/voice : Complementary multimodal communication. Proceedings of Speeh Tech\u201992 (1992), 238\u2013241. https:\/\/cir.nii.ac.jp\/crid\/1571980074518368256"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479902"},{"key":"e_1_3_3_3_48_1","volume-title":"Word frequencies in written and spoken English: Based on the British National Corpus","author":"Leech Geoffrey","unstructured":"Geoffrey Leech, Paul Rayson, and Andrew Wilson. 2001. Word frequencies in written and spoken English: Based on the British National Corpus. Routledge."},{"key":"e_1_3_3_3_49_1","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. arxiv:2301.12597\u00a0[cs.CV]"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545702"},{"key":"e_1_3_3_3_51_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. arxiv:1405.0312\u00a0[cs.CV]"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347945"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581566"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1137"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","unstructured":"Feiyu Lu and Doug\u00a0A. Bowman. 2021. Evaluating the Potential of Glanceable AR Interfaces for Authentic Everyday Uses. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR). 768\u2013777. https:\/\/doi.org\/10.1109\/VR50410.2021.00104","DOI":"10.1109\/VR50410.2021.00104"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR46266.2020.00113"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530886"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1983302.1983304"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702528"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376479"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3053117"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/1117309.1117345"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2317956.2318034"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/IE.2016.42"},{"key":"e_1_3_3_3_65_1","unstructured":"Christi Olson and Kelli Kemery. 2020. 2019 Voice report: Consumer adoption of voice technology and digital assistants. https:\/\/about.ads.microsoft.com\/en-us\/insights\/2019-voice-report"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415817"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2003.1240730"},{"key":"e_1_3_3_3_68_1","unstructured":"OpenAI. 2023. GPT-3.5. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5"},{"key":"e_1_3_3_3_69_1","unstructured":"OpenAI. 2023. GPT-4. https:\/\/openai.com\/research\/gpt-4"},{"key":"e_1_3_3_3_70_1","unstructured":"OpenAI. 2023. Models. https:\/\/platform.openai.com\/docs\/models\/overview"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/330534.330538"},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501898"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173867"},{"key":"e_1_3_3_3_74_1","doi-asserted-by":"publisher","DOI":"10.1177\/1541931213571043"},{"key":"e_1_3_3_3_75_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.01.001"},{"key":"e_1_3_3_3_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647397"},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2014.6948411"},{"key":"e_1_3_3_3_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174033"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_3_3_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379157.3388930"},{"key":"e_1_3_3_3_81_1","volume-title":"Research in the wild (1 ed.)","author":"Rogers Yvonne","unstructured":"Yvonne Rogers and Paul Marshall. 2017. Research in the wild (1 ed.). Springer Cham."},{"key":"e_1_3_3_3_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3239092.3265968"},{"key":"e_1_3_3_3_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379350.3416153"},{"key":"e_1_3_3_3_84_1","doi-asserted-by":"publisher","unstructured":"Natalie Ruiz Fang Chen and Sharon Oviatt. 2010. Chapter 12 - Multimodal Input. In Multimodal Signal Processing Jean-Philippe Thiran Ferran Marqu\u00e9s and Herv\u00e9 Bourlard (Eds.). Academic Press Oxford 231\u2013255. https:\/\/doi.org\/10.1016\/B978-0-12-374825-6.00010-1","DOI":"10.1016\/B978-0-12-374825-6.00010-1"},{"key":"e_1_3_3_3_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/355017.355028"},{"key":"e_1_3_3_3_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300852"},{"key":"e_1_3_3_3_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3134786"},{"key":"e_1_3_3_3_88_1","unstructured":"Yongliang Shen Kaitao Song Xu Tan Dongsheng Li Weiming Lu and Yueting Zhuang. 2023. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face. arxiv:2303.17580\u00a0[cs.CL]"},{"key":"e_1_3_3_3_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023566"},{"key":"e_1_3_3_3_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581500"},{"key":"e_1_3_3_3_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173652"},{"key":"e_1_3_3_3_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303053"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:23Z","timestamp":1750290263000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":92,"alternative-id":["10.1145\/3613904.3642230","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642230","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}