{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T11:35:40Z","timestamp":1791286540099,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":116,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3742413.3789112","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T11:32:24Z","timestamp":1772537544000},"page":"1821-1841","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Gazeify Then Voiceify: Physical Object Referencing Through Gaze and Voice Interaction with Displayless Smart Glasses"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7040-2326","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6105-1272","authenticated-orcid":false,"given":"Mengjie","family":"Yu","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Meta Inc., Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9382-6466","authenticated-orcid":false,"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Meta Inc., Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6174-2089","authenticated-orcid":false,"given":"Kashyap","family":"Todi","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4568-5812","authenticated-orcid":false,"given":"Ajoy Savio","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Meta, Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5577-0545","authenticated-orcid":false,"given":"Yue","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Reality Lab Research, Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9425-0881","authenticated-orcid":false,"given":"Haijun","family":"Xia","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0494-5373","authenticated-orcid":false,"given":"Tovi","family":"Grossman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Toronto, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-5076","authenticated-orcid":false,"given":"Tanya R.","family":"Jonker","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Meta Inc., Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2807532"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"crossref","unstructured":"Jennifer Angelo Curtis\u00a0L. Deterding and Jerry Weisman. 1991. Comparing three head-pointing systems using a single subject design.Assistive technology : the official journal of RESNA 3 2 (1991) 43\u20139. https:\/\/api.semanticscholar.org\/CorpusID:40600540","DOI":"10.1080\/10400435.1991.10132181"},{"key":"e_1_3_3_3_4_2","unstructured":"Muhammad Awais Muzammal Naseer Salman Khan Rao\u00a0Muhammad Anwer Hisham Cholakkal Mubarak Shah Ming-Hsuan Yang and Fahad\u00a0Shahbaz Khan. 2023. Foundational models defining a new era in vision: A survey and outlook. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.13721 (2023)."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2999508.2999530"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"Aaron Bangor Philip\u00a0T. Kortum and James\u00a0T. Miller. 2008. An Empirical Evaluation of the System Usability Scale. International Journal of Human\u2013Computer Interaction 24 (2008) 574 \u2013 594. https:\/\/api.semanticscholar.org\/CorpusID:29843973","DOI":"10.1080\/10447310802205776"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"e_1_3_3_3_8_2","volume-title":"Gaze Meets ML","author":"Beckmann Daniel","year":"2023","unstructured":"Daniel Beckmann, Jacqueline Kockwelp, J\u00f6rg Gromoll, Friedemann Kiefer, and Benjamin Risse. 2023. SAM meets Gaze: Passive Eye Tracking for Prompt-based Instance Segmentation. In Gaze Meets ML. https:\/\/api.semanticscholar.org\/CorpusID:269648349"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Shimmila Bhowmick Keyur Sorathia and Pratul\u00a0Chandra Kalita. 2021. Understanding Gesture Performance for Object Selection in VR: Classification and Taxonomy of Gestures in HCI. Proceedings of the 12th Indian Conference on Human-Computer Interaction (2021). https:\/\/api.semanticscholar.org\/CorpusID:247085066","DOI":"10.1145\/3506469.3506483"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3206343.3206349"},{"key":"e_1_3_3_3_11_2","volume-title":"International Conference on Computer Graphics and Interactive Techniques","author":"Bolt Richard\u00a0A.","year":"1980","unstructured":"Richard\u00a0A. Bolt. 1980. \u201cPut-that-there\u201d: Voice and gesture at the graphics interface. In International Conference on Computer Graphics and Interactive Techniques. https:\/\/api.semanticscholar.org\/CorpusID:15450886"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515511"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713953"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov and Sergey Zagoruyko. 2020. End-toend object detection with transformers. In eccv. Springer 1 2 (2020) 4.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Benedetta Cesqui Rolf van De\u00a0Langenberg Francesco Lacquaniti and Andrea d\u2019Avella. 2013. A novel method for measuring gaze orientation in space in unrestrained head conditions. Journal of vision 13 8 (2013) 28\u201328.","DOI":"10.1167\/13.8.28"},{"key":"e_1_3_3_3_17_2","unstructured":"Liang-Chieh Chen. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.05587 (2017)."},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen George Papandreou Iasonas Kokkinos Kevin Murphy and Alan\u00a0L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets atrous convolution and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40 4 (2017) 834\u2013848.","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Zhutian Chen Wai-Shun Tong Qianwen Wang Benjamin Bach and Huamin Qu. 2020. Augmenting Static Visualizations with PapARVis Designer. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (2020). https:\/\/api.semanticscholar.org\/CorpusID:218483267","DOI":"10.1145\/3313831.3376436"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Subramanian Chidambaram Sai\u00a0Swarup Reddy Matthew Rumple Ananya Ipsita Ana\u00a0M. Villanueva Thomas Redick Wolfgang Stuerzlinger and Karthik Ramani. 2022. EditAR: A Digital Twin Authoring Environment for Creation of AR\/VR and Video Instructions from a Single Demonstration. 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) (2022) 326\u2013335. https:\/\/api.semanticscholar.org\/CorpusID:254129085","DOI":"10.1109\/ISMAR55827.2022.00048"},{"key":"e_1_3_3_3_21_2","unstructured":"Hyunsung Cho Naveen Sendhilnathan Michael Nebeling Tianyi Wang Purnima Padmanabhan Jonathan Browder David Lindlbauer Tanya\u00a0R. Jonker and Kashyap Todi. 2024. SonoHaptics: An Audio-Haptic Cursor for Gaze-Based Object Selection in XR. https:\/\/api.semanticscholar.org\/CorpusID:272368428"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Shujie Deng Nan Jiang Jian Chang Shihui Guo and Jian\u00a0J Zhang. 2017. Understanding the impact of multimodal interaction using gaze informed mid-air gesture control in 3D virtual objects manipulation. International Journal of Human-Computer Studies 105 (2017) 68\u201380.","DOI":"10.1016\/j.ijhcs.2017.04.002"},{"key":"e_1_3_3_3_24_2","unstructured":"Mustafa\u00a0Doga Dogan. 2024. Ubiquitous Metadata: Design and Fabrication of Embedded Markers for Real-World Object Identification and Interaction. ArXiv abs\/2407.11748 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271218769"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Mustafa\u00a0Doga Dogan Eric\u00a0J. Gonzalez Karan Ahuja Ruofei Du Andrea Colacco Johnny Lee Mar Gonz\u00e1lez-Franco and David Kim. 2024. Augmented Object Intelligence with XR-Objects. https:\/\/api.semanticscholar.org\/CorpusID:269293799","DOI":"10.1145\/3654777.3676379"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74800-7_43"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126616"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747684"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Ajoy\u00a0S Fernandes T\u00a0Scott Murdison and Michael\u00a0J Proulx. 2023. Leveling the playing field: A comparative reevaluation of unmodified eye tracking as an input and interaction modality for VR. IEEE Transactions on Visualization and Computer Graphics 29 5 (2023) 2269\u20132279.","DOI":"10.1109\/TVCG.2023.3247058"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649902.3656369"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2785830.2785873"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_3_3_35_2","unstructured":"Xiuye Gu Tsung-Yi Lin Weicheng Kuo and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.13921 (2021)."},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3206343.3206344"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0G. Hart. 2006. Nasa-Task Load Index (NASA-TLX); 20 Years Later. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 50 (2006) 904 \u2013 908. https:\/\/api.semanticscholar.org\/CorpusID:6292200","DOI":"10.1177\/154193120605000909"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_3_3_39_2","volume-title":"Virtual Reality Software and Technology","author":"Henderson Steven\u00a0J.","year":"2008","unstructured":"Steven\u00a0J. Henderson and Steven\u00a0K. Feiner. 2008. Opportunistic controls: leveraging natural affordances as tangible user interfaces for augmented reality. In Virtual Reality Software and Technology. https:\/\/api.semanticscholar.org\/CorpusID:11199619"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Valentin Heun James Hobin and Pattie Maes. 2013. Reality editor: programming smarter objects. Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication (2013). https:\/\/api.semanticscholar.org\/CorpusID:14748376","DOI":"10.1145\/2494091.2494185"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2168556.2168602"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/1743666.1743740"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/97243.97246"},{"key":"e_1_3_3_3_44_2","unstructured":"Youngkyoon Jang Ikbeom Jeon Tae-Kyun Kim and Woontack Woo. 2017. Metaphoric Hand Gestures for Orientation-Aware VR Object Manipulation With an Egocentric Viewpoint. IEEE Transactions on Human-Machine Systems 47 (2017) 113\u2013127. https:\/\/api.semanticscholar.org\/CorpusID:24522968"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126630"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_3_49_2","unstructured":"Robert Konrad Nitish Padmanaban J\u00a0Gabriel Buckmaster Kevin\u00a0C Boyle and Gordon Wetzstein. 2024. Gazegpt: Augmenting human capabilities using gaze-contingent contextual ai for smart eyewear. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.17217 (2024)."},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300721"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173655"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"crossref","unstructured":"Linn\u00e9a Larsson Andrea Schwaller Marcus Nystr\u00f6m and Martin Stridh. 2016. Head movement compensation and multi-modal event detection in eye-tracking data for unconstrained head movements. Journal of neuroscience methods 274 (2016) 13\u201326.","DOI":"10.1016\/j.jneumeth.2016.09.005"},{"key":"e_1_3_3_3_53_2","unstructured":"Jaewook Lee Sebasti\u00e1n\u00a0Sanhueza Rodr\u00edguez Raahul Natarrajan Jacqueline Chen Harsh Deep and Alex Kirlik. 2021. What\u2019s This? A Voice and Touch Multimodal Approach for Ambiguity Resolution in Voice Assistants. Proceedings of the 2021 International Conference on Multimodal Interaction (2021). https:\/\/api.semanticscholar.org\/CorpusID:238992795"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642230"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Qin Liu Zhenlin Xu Gedas Bertasius and Marc Niethammer. 2022. SimpleClick: Interactive Image Segmentation with Simple Vision Transformers. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2022) 22233\u201322243. https:\/\/api.semanticscholar.org\/CorpusID:253018432","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"e_1_3_3_3_58_2","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chun yue Li Jianwei Yang Hang Su Jun-Juan Zhu and Lei Zhang. 2023. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection. ArXiv abs\/2303.05499 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257427307"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"crossref","unstructured":"Andreas L\u00f6cken Tobias Hesselmann Martin Pielot Niels Henze and Susanne Boll. 2012. User-centred process for the definition of free-hand gestures applied to controlling music playback. Multimedia systems 18 (2012) 15\u201331.","DOI":"10.1007\/s00530-011-0240-2"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485279.3485286"},{"key":"e_1_3_3_3_63_2","unstructured":"Wenyu Lv Shangliang Xu Yian Zhao Guanzhong Wang Jinman Wei Cheng Cui Yuning Du Qingqing Dang and Yi Liu. 2023. DETRs Beat YOLOs on Real-time Object Detection. ArXiv abs\/2304.08069 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258179840"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"crossref","unstructured":"Mathias\u00a0N Lystb\u00e6k Peter Rosenberg Ken Pfeuffer Jens\u00a0Emil Gr\u00f8nb\u00e6k and Hans Gellersen. 2022. Gaze-hand alignment: Combining eye gaze and mid-air pointing for interacting with menus in augmented reality. Proceedings of the ACM on Human-Computer Interaction 6 ETRA (2022) 1\u201318.","DOI":"10.1145\/3530886"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-6392-3_3"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"crossref","unstructured":"Sven Mayer Gierad Laput and Chris Harrison. 2020. Enhancing Mobile Voice Assistants with WorldGaze. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (2020). https:\/\/api.semanticscholar.org\/CorpusID:215776069","DOI":"10.1145\/3313831.3376479"},{"key":"e_1_3_3_3_67_2","unstructured":"Matthias Minderer Alexey\u00a0A. Gritsenko and Neil Houlsby. 2023. Scaling Open-Vocabulary Object Detection. ArXiv abs\/2306.09683 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259187664"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"crossref","unstructured":"Darius Miniotas Oleg Spakov Ivan Tugoy and I.\u00a0Scott MacKenzie. 2006. Speech-augmented eye gaze interaction with small closely spaced targets. Proceedings of the 2006 symposium on Eye tracking research & applications (2006). https:\/\/api.semanticscholar.org\/CorpusID:10705855","DOI":"10.1145\/1117309.1117345"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"crossref","unstructured":"Kyzyl Monteiro Ritik Vatsal Neil Chulpongsatorn Aman Parnami and Ryo Suzuki. 2023. Teachable Reality: Prototyping Tangible Augmented Reality with Everyday Objects by Leveraging Interactive Machine Teaching. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (2023). https:\/\/api.semanticscholar.org\/CorpusID:257078906","DOI":"10.1145\/3544548.3581449"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"crossref","unstructured":"Alexander Neubeck and Luc\u00a0Van Gool. 2006. Efficient Non-Maximum Suppression. 18th International Conference on Pattern Recognition (ICPR\u201906) 3 (2006) 850\u2013855. https:\/\/api.semanticscholar.org\/CorpusID:5057778","DOI":"10.1109\/ICPR.2006.479"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"crossref","unstructured":"Jakob Nielsen. 1993. Noncommand user interfaces. Commun. ACM 36 4 (1993) 83\u201399.","DOI":"10.1145\/255950.153582"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984751.2984754"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2008.4637353"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131277.3132180"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DUI.2017.7893315"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747770"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131277.3132182"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204541"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"crossref","unstructured":"Gang Ren and Eamonn O\u2019Neill. 2013. 3D selection with freehand gesture. Comput. Graph. 37 (2013) 101\u2013120. https:\/\/api.semanticscholar.org\/CorpusID:27651313","DOI":"10.1016\/j.cag.2012.12.006"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"crossref","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence 39 6 (2016) 1137\u20131149.","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"crossref","unstructured":"Yevhen Romaniak Anastasiia Smielova Yevhenii Yakishyn Valerii Dziubliuk Mykhailo Zlotnyk and Oleksandr Viatchaninov. 2020. Nimble: Mobile Interface for a Visual Question Answering Augmented by Gestures. Adjunct Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology (2020). https:\/\/api.semanticscholar.org\/CorpusID:222800232","DOI":"10.1145\/3379350.3416153"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"crossref","unstructured":"Du Ruofei Alex Olwal Mathieu\u00a0Le Goc WU Shengzhi Danhang Tang Yinda Zhang Jun Zhang David\u00a0Joseph Tan and Federico Tombari. 2022. Opportunistic Interfaces for Augmented Reality: Transforming Everyday Objects into Tangible 6DoF Interfaces Using Ad hoc UI. CHI Conference on Human Factors in Computing Systems Extended Abstracts (2022). https:\/\/api.semanticscholar.org\/CorpusID:248259431","DOI":"10.1145\/3491101.3519911"},{"key":"e_1_3_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340764.3344897"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"crossref","unstructured":"Katie Seaborn Norihisa\u00a0P Miyake Peter Pennefather and Mihoko Otake-Matsuura. 2021. Voice in human\u2013agent interaction: A survey. ACM Computing Surveys (CSUR) 54 4 (2021) 1\u201343.","DOI":"10.1145\/3386867"},{"key":"e_1_3_3_3_87_2","unstructured":"Naveen Sendhilnathan Ajoy\u00a0S Fernandes Michael\u00a0J Proulx and Tanya\u00a0R Jonker. 2024. Implicit gaze research for XR systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.13878 (2024)."},{"key":"e_1_3_3_3_88_2","unstructured":"Yingtian Shi Yukang Yan Zisu Li Chen Liang Yuntao Wang Chun Yu and Yuanchun Shi. 2024. CasualGaze: Towards Modeling and Recognizing Casual Gaze Behavior for Efficient Gaze-based Object Selection. https:\/\/api.semanticscholar.org\/CorpusID:271947351"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/332040.332445"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580685"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376438"},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347921"},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379155.3391312"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"crossref","unstructured":"Ludwig Sidenmark Zibo Sun and Hans Gellersen. 2024. Cone&Bubble: Evaluating Combinations of Gaze Head and Hand Pointing for Target Selection in Dense 3D Environments. 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (2024) 642\u2013649. https:\/\/api.semanticscholar.org\/CorpusID:270097765","DOI":"10.1109\/VRW62533.2024.00126"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"crossref","unstructured":"Yuki Sonoda Ryo Kurokawa Yuta Nakamura Jun Kanzawa Mariko Kurokawa Yuji Ohizumi Wataru Gonoi and Osamu Abe. 2024. Diagnostic performances of GPT-4o Claude 3 Opus and Gemini 1.5 Pro in \"Diagnosis Please\" cases.Japanese journal of radiology (2024). https:\/\/api.semanticscholar.org\/CorpusID:270922496","DOI":"10.1101\/2024.05.26.24307915"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"crossref","unstructured":"Ryo Suzuki Rubaiat\u00a0Habib Kazi Li-Yi Wei Stephen DiVerdi Wilmot Li and Daniel Leithinger. 2020. RealitySketch: Embedding Responsive Graphics and Visualizations in AR through Dynamic Sketching. Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology (2020). https:\/\/api.semanticscholar.org\/CorpusID:221186940","DOI":"10.1145\/3379337.3415892"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/332040.332443"},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/2598153.2598154"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747757"},{"key":"e_1_3_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493477"},{"key":"e_1_3_3_3_101_2","volume-title":"Gaze Meets ML","author":"Wang Bin","year":"2023","unstructured":"Bin Wang, Armstrong Aboah, Zheyuan Zhang, Hongyi Pan, and Ulas Bagci. 2023. GazeSAM: Interactive Image Segmentation with Eye Gaze and Segment Anything Model. In Gaze Meets ML. https:\/\/api.semanticscholar.org\/CorpusID:269648415"},{"key":"e_1_3_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"e_1_3_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581042"},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"crossref","unstructured":"Chenyun Wu Zhe Lin Scott\u00a0D. Cohen Trung Bui and Subhransu Maji. 2020. PhraseCut: Language-Based Image Segmentation in the Wild. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020) 10213\u201310222. https:\/\/api.semanticscholar.org\/CorpusID:218551213","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"e_1_3_3_3_105_2","unstructured":"Yunyang Xiong Bala Varadarajan Lemeng Wu Xiaoyu Xiang Fanyi Xiao Chenchen Zhu Xiaoliang Dai Dilin Wang Fei Sun Forrest\u00a0N. Iandola Raghuraman Krishnamoorthi and Vikas Chandra. 2023. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything. ArXiv abs\/2312.00863 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265608780"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"e_1_3_3_3_107_2","doi-asserted-by":"crossref","unstructured":"Zunnan Xu Zhihong Chen Yong Zhang Yibing Song Xiang Wan and Guanbin Li. 2023. Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023) 17457\u201317466. https:\/\/api.semanticscholar.org\/CorpusID:260091742","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"crossref","unstructured":"Jackie Yang and James\u00a0A. Landay. 2019. InfoLED: Augmenting LED Indicator Lights for Device Positioning and Communication. Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology (2019). https:\/\/api.semanticscholar.org\/CorpusID:204812192","DOI":"10.1145\/3332165.3347954"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"crossref","unstructured":"Ionu\u0163-Alexandru Zai\u0163i \u015etefan-Gheorghe Pentiuc and Radu-Daniel Vatavu. 2015. On free-hand TV control: experimental results on user-elicited gestures with Leap Motion. Personal and Ubiquitous Computing 19 (2015) 821\u2013838.","DOI":"10.1007\/s00779-015-0863-y"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0Campos Zamora Mustafa\u00a0Doga Dogan Alexa\u00a0F. Siu Eunyee Koh and Chang Xiao. 2024. Moir\u00e9Widgets: High-Precision Passive Tangible Interfaces via Moir\u00e9 Effect. Proceedings of the CHI Conference on Human Factors in Computing Systems (2024). https:\/\/api.semanticscholar.org\/CorpusID:269743279","DOI":"10.1145\/3613904.3642734"},{"key":"e_1_3_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747694"},{"key":"e_1_3_3_3_112_2","unstructured":"Hao Zhang Feng Li Shilong Liu Lei Zhang Hang Su Jun Zhu Lionel\u00a0M Ni and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.03605 (2022)."},{"key":"e_1_3_3_3_113_2","doi-asserted-by":"crossref","unstructured":"Jingyi Zhang Jiaxing Huang Sheng Jin and Shijian Lu. 2023. Vision-Language Models for Vision Tasks: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (2023) 5625\u20135644. https:\/\/api.semanticscholar.org\/CorpusID:257913547","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_3_3_114_2","unstructured":"Xiaowei Zhao Yuqing Ma Duorui Wang Yifan Shen Yixuan Qiao and Xianglong Liu. 2023. Revisiting open world object detection. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_3_3_115_2","unstructured":"Chaoyang Zhu and Long Chen. 2024. A survey on open-vocabulary detection and segmentation: Past present and future. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_3_3_116_2","doi-asserted-by":"crossref","unstructured":"Pengkai Zhu Hanxiao Wang and Venkatesh Saligrama. 2019. Zero shot detection. IEEE Transactions on Circuits and Systems for Video Technology 30 4 (2019) 998\u20131010.","DOI":"10.1109\/TCSVT.2019.2899569"},{"key":"e_1_3_3_3_117_2","unstructured":"Xueyan Zou Jianwei Yang Hao Zhang Feng Li Linjie Li Jianfeng Gao and Yong\u00a0Jae Lee. 2023. Segment Everything Everywhere All at Once. ArXiv abs\/2304.06718 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258108410"}],"event":{"name":"IUI '26: 31st International Conference on Intelligent User Interfaces","location":"Paphos Cyprus","acronym":"IUI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 31st International Conference on Intelligent User Interfaces"],"original-title":[],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:01:16Z","timestamp":1773493276000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742413.3789112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":116,"alternative-id":["10.1145\/3742413.3789112","10.1145\/3742413"],"URL":"https:\/\/doi.org\/10.1145\/3742413.3789112","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}