{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:24Z","timestamp":1776931224168,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":105,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,4,13]],"date-time":"2027-04-13T00:00:00Z","timestamp":1807574400000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1839971"],"award-info":[{"award-number":["1839971"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2329804"],"award-info":[{"award-number":["2329804"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Feddersen Distinguished Professorship Funds"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790715","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:33Z","timestamp":1776053553000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ARify: Leveraging Narrated Instructional Videos to Create Augmented Reality Tutorials for Procedural Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9497-6925","authenticated-orcid":false,"given":"Xiyun","family":"Hu","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3408-2876","authenticated-orcid":false,"given":"Chenfei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7893-5613","authenticated-orcid":false,"given":"Shao-Kang","family":"Hsia","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1711-4930","authenticated-orcid":false,"given":"Dizhi","family":"Ma","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3723-5482","authenticated-orcid":false,"given":"Rahul","family":"Jain","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8639-5135","authenticated-orcid":false,"given":"Karthik","family":"Ramani","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2019.8733642"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3056540.3056547"},{"key":"e_1_3_3_3_4_2","unstructured":"Andres\u00a0M Bran Sam Cox Oliver Schilter Carlo Baldassari Andrew\u00a0D White and Philippe Schwaller. 2023. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.05376 (2023)."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519639"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606832"},{"key":"e_1_3_3_3_7_2","unstructured":"Shimin Chen Xiaohan Lan Yitian Yuan Zequn Jie and Lin Ma. 2024. Timemarker: A versatile video-llm for long and short video understanding with superior temporal localization ability. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.18211 (2024)."},{"key":"e_1_3_3_3_8_2","first-page":"193","volume-title":"European Conference on Computer Vision","author":"Chen Yuxiao","year":"2024","unstructured":"Yuxiao Chen, Kai Li, Wentao Bao, Deep Patel, Yu Kong, Martin\u00a0Renqiang Min, and Dimitris\u00a0N Metaxas. 2024. Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment. In European Conference on Computer Vision. Springer, 193\u2013210."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642443"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-2074-6_36"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312879"},{"key":"e_1_3_3_3_12_2","unstructured":"Ana Regina\u00a0Mizrahy Cuperschmid Marina\u00a0Graf Grachet and M\u00e1rcio\u00a0Minto Fabricio. [n. d.]. Augmented Reality as a Tutorial Tool for Construction Tasks. ([n. d.])."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SVR.2015.39"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01285"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Andreas Dengel Muhammad\u00a0Zahid Iqbal Silke Grafe and Eleni Mangina. 2022. A review on augmented reality authoring toolkits for education. Frontiers in Virtual Reality 3 (2022) 798032.","DOI":"10.3389\/frvir.2022.798032"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Henrik Detjen Robert\u00a0Niklas Degenhart Stefan Schneegass and Stefan Geisler. 2021. Supporting user onboarding in automated vehicles through multimodal augmented reality tutorials. Multimodal Technologies and Interaction 5 5 (2021) 22.","DOI":"10.3390\/mti5050022"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/VRW66409.2025.00214"},{"key":"e_1_3_3_3_18_2","unstructured":"Runlin Duan Yuzhao Chen Rahul Jain Yichen Hu Jingyu Shi and Karthik Ramani. 2025. Canvas3D: Empowering Precise Spatial Control for Image Generation with Constraints from a 3D Virtual Canvas. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.07135 (2025)."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715336.3735824"},{"key":"e_1_3_3_3_20_2","unstructured":"Runlin Duan Chenfei Zhu Yuzhao Chen Dizhi Ma Jingyu Shi Ziyi Liu and Karthik Ramani. 2025. SketchConcept: Sketching-based Concept Recomposition for Product Design using Generative AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.07141 (2025)."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3284398.3284399"},{"key":"e_1_3_3_3_22_2","unstructured":"Epic Games. 2025. Unreal Engine. https:\/\/www.unrealengine.com\/en-US."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"John Estrada Sidike Paheding Xiaoli Yang and Quamar Niyaz. 2022. Deep-learning-incorporated augmented reality application for engineering lab training. Applied Sciences 12 10 (2022) 5159.","DOI":"10.3390\/app12105159"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Yalda Ghasemi Allison Bayro Justin MacDonald Heejin Jeong Joel Reynolds and Chang\u00a0S Nam. 2023. Embedding spatial augmented reality in culinary training: A comparative evaluation of sAR kitchen and video tutorials. IEEE Transactions on Learning Technologies 17 (2023) 765\u2013775.","DOI":"10.1109\/TLT.2023.3334788"},{"key":"e_1_3_3_3_25_2","unstructured":"Google. 2025. Gemini Nano Banana. https:\/\/gemini.google\/overview\/image-generation\/"},{"key":"e_1_3_3_3_26_2","unstructured":"Google DeepMind. 2024. Gemini 2.5 Flash Model. https:\/\/deepmind.google\/technologies\/gemini\/."},{"key":"e_1_3_3_3_27_2","unstructured":"Michihiko Goto Yuko Uematsu Hideo Saito Shuji Senda and Akihiko Iketani. 2010. AR-Based Supporting System by Overlay Display of Instruction Video. Journal of the Institute of Image Electronics Engineers of Japan 39 5 (2010) 631\u2013643."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Thilo Hagendorff. 2024. Mapping the ethics of generative AI: A comprehensive scoping review. Minds and Machines 34 4 (2024) 39.","DOI":"10.1007\/s11023-024-09694-w"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580704"},{"key":"e_1_3_3_3_31_2","unstructured":"Yisheng He et\u00a0al. 2024. FoundationPose: Unified 6D Pose Estimation. arxiv:https:\/\/arXiv.org\/abs\/2403.12345\u00a0[cs.CV]"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3322753"},{"key":"e_1_3_3_3_33_2","volume-title":"The twelfth international conference on learning representations","author":"Hong Sirui","year":"2023","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka\u00a0Shing Yau, Zijuan Lin, et\u00a0al. 2023. MetaGPT: Meta programming for a multi-agent collaborative framework. In The twelfth international conference on learning representations."},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715336.3735769"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32374"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445283"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Emin \u0130bili Mevl\u00fct \u00c7at Dmitry Resnyansky Sami \u015eahin and Mark Billinghurst. 2020. An assessment of geometry teaching supported with augmented reality teaching materials to enhance students\u2019 3D geometry thinking skills. International Journal of Mathematical Education in Science and Technology 51 2 (2020) 224\u2013246.","DOI":"10.1080\/0020739X.2019.1583382"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712159"},{"key":"e_1_3_3_3_40_2","unstructured":"Intel. 2025. Intel\u00ae RealSense\u2122 Depth Camera D435i - Product Specifications. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/190004\/intel-realsense-depth-camera-d435i\/specifications.html"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580897"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Dominic Kao Alejandra\u00a0J Magana and Christos Mousas. 2021. Evaluating tutorial-based instructions for controllers in virtual reality games. Proceedings of the ACM on human-computer interaction 5 CHI PLAY (2021) 1\u201328.","DOI":"10.1145\/3474661"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485279.3485289"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"crossref","unstructured":"Ze-Hao Lai Wenjin Tao Ming\u00a0C Leu and Zhaozheng Yin. 2020. Smart augmented reality instructional system for mechanical assembly towards worker-centered intelligent manufacturing. Journal of Manufacturing Systems 55 (2020) 69\u201381.","DOI":"10.1016\/j.jmsy.2020.02.010"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Joakim Laine Matti Minkkinen and Matti M\u00e4ntym\u00e4ki. 2025. Understanding the ethics of generative AI: Established and new ethical principles. Communications of the Association for Information Systems 56 1 (2025) 7.","DOI":"10.17705\/1CAIS.05601"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Vianney Lara-Prieto Efra\u00edn Bravo-Quirino Miguel\u00a0\u00c1ngel Rivera-Campa and Jos\u00e9\u00a0Enrique Guti\u00e9rrez-Arredondo. 2015. An innovative self-learning approach to 3D printing using multimedia and augmented reality on mobile devices. Procedia computer science 75 (2015) 59\u201365.","DOI":"10.1016\/j.procs.2015.12.206"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01086"},{"key":"e_1_3_3_3_48_2","unstructured":"Wengxi Li Roy Pea Nick Haber and Hari Subramonyam. 2024. Tutorly: Turning programming videos into apprenticeship learning environments with llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.12946 (2024)."},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581006"},{"key":"e_1_3_3_3_50_2","unstructured":"Hanchao Liu Wenyuan Xue Yifei Chen Dapeng Chen Xiutian Zhao Ke Wang Liping Hou Rongjun Li and Wei Peng. 2024. A survey on hallucination in large vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.00253 (2024)."},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581442"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676400"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Faraz Mahmood Eitezaz Mahmood Robert\u00a0Gregory Dorfman John Mitchell Feroze-Udin Mahmood Stephanie\u00a0B Jones and Robina Matyal. 2018. Augmented reality and ultrasound education: initial experience. Journal of cardiothoracic and vascular anesthesia 32 3 (2018) 1363\u20131367.","DOI":"10.1053\/j.jvca.2017.12.006"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/MetroXRAINE58569.2023.10405829"},{"key":"e_1_3_3_3_55_2","unstructured":"Meta. 2025. Meta Quest Pro Headset For Business. https:\/\/forwork.meta.com\/quest\/quest-pro\/"},{"key":"e_1_3_3_3_56_2","unstructured":"Meta Platforms. 2023. Meta XR SDK for Unity. https:\/\/developer.oculus.com\/downloads\/package\/meta-xr-sdk\/."},{"key":"e_1_3_3_3_57_2","unstructured":"Meta Platforms. 2024. Wit.ai Speech-to-Text API. https:\/\/wit.ai\/."},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702490"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Pedro Morillo Inmaculada Garcia-Garcia Juan\u00a0M Orduna Marcos Fernandez and M\u00a0Carmen Juan. 2020. Comparative study of AR versus video tutorials for minor maintenance operations. Multimedia Tools and Applications 79 11 (2020) 7073\u20137100.","DOI":"10.1007\/s11042-019-08437-9"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03161-3_11"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"crossref","unstructured":"James Munkres. 1957. Algorithms for the assignment and transportation problems. J. Soc. Indust. Appl. Math. 5 1 (1957) 32\u201338.","DOI":"10.1137\/0105003"},{"key":"e_1_3_3_3_62_2","first-page":"15","volume-title":"Graphics Interface","author":"Nawhal Megha","year":"2019","unstructured":"Megha Nawhal, Jacqueline\u00a0B Lang, Greg Mori, and Parmit\u00a0K Chilana. 2019. VideoWhiz: Non-Linear Interactive Overviews for Recipe Videos.. In Graphics Interface. 15\u20131."},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"crossref","unstructured":"Rohith Peddi Shivvrat Arya Bharath Challa Likhitha Pallapothula Akshay Vyas Bhavya Gouripeddi Qifan Zhang Jikai Wang Vasundhara Komaragiri Eric Ragan et\u00a0al. 2024. CaptainCook4D: A dataset for understanding errors in procedural activities. Advances in Neural Information Processing Systems 37 (2024) 135626\u2013135679.","DOI":"10.52202\/079017-4307"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/METROI4.2018.8428320"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047213"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517665"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.3389\/feduc.2021.700760"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517486"},{"key":"e_1_3_3_3_69_2","unstructured":"Sebasti\u00e1n Ramirez. 2018. FastAPI: Modern Fast (High-performance) Web Framework for Building APIs with Python. https:\/\/fastapi.tiangolo.com\/."},{"key":"e_1_3_3_3_70_2","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et\u00a0al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00714 (2024)."},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517735"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"crossref","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. Advances in Neural Information Processing Systems 36 (2023) 38154\u201338180.","DOI":"10.52202\/075280-1657"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713348"},{"key":"e_1_3_3_3_75_2","unstructured":"Jingyu Shi Rahul Jain Hyungjun Doh Ryo Suzuki and Karthik Ramani. 2023. An HCI-centric survey and taxonomy of human-generative-AI interactions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.07127 (2023)."},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00797"},{"key":"e_1_3_3_3_77_2","unstructured":"Fangxun Shu Lei Zhang Hao Jiang and Cihang Xie. 2023. Audio-visual llm for video understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.06720 (2023)."},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"crossref","unstructured":"Roland Sigrist Georg Rauter Robert Riener and Peter Wolf. 2013. Augmented visual auditory haptic and multimodal feedback in motor learning: a review. Psychonomic bulletin & review 20 1 (2013) 21\u201353.","DOI":"10.3758\/s13423-012-0333-8"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00146"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"crossref","unstructured":"Ana Stanescu Peter Mohr Dieter Schmalstieg and Denis Kalkofen. 2022. Model-free authoring by demonstration of assembly instructions in augmented reality. IEEE Transactions on Visualization and Computer Graphics 28 11 (2022) 3821\u20133831.","DOI":"10.1109\/TVCG.2022.3203104"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415892"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR50242.2020.00077"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01289"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300514"},{"key":"e_1_3_3_3_85_2","unstructured":"Unity Technologies. 2024. Unity 2022.3.20f1 LTS. https:\/\/unity.com\/releases\/editor\/whats-new\/2022.3.20."},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714015"},{"key":"e_1_3_3_3_87_2","unstructured":"Yizhou Wang Ruiyi Zhang Haoliang Wang Uttaran Bhattacharya Yun Fu and Gang Wu. 2023. Vaquita: Enhancing alignment in llm-assisted video understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02310 (2023)."},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675219"},{"key":"e_1_3_3_3_90_2","volume-title":"Graphics Interface 2020","author":"Whitlock Matt","year":"2020","unstructured":"Matt Whitlock, George Fitzmaurice, Tovi Grossman, and Justin Matejka. 2020. AuthAR: concurrent authoring of tutorials for AR assembly guidance. In Graphics Interface 2020."},{"key":"e_1_3_3_3_91_2","unstructured":"Zehao Wu Xiang Li Hao Zhang and Dahua Lin. 2023. YOLO-World: Real-Time Open-Vocabulary Object Detection. arxiv:https:\/\/arXiv.org\/abs\/2304.00501\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.00501"},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA54631.2023.10275362"},{"key":"e_1_3_3_3_93_2","unstructured":"Zhiqin Xu et\u00a0al. 2023. InstantMesh: Efficient 3D Mesh Generation from a Single Image. arxiv:https:\/\/arXiv.org\/abs\/2306.00969\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2306.00969"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415819"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581126"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712144"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642752"},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"crossref","unstructured":"Joanne Yip Sze-Ham Wong Kit-Lun Yick Kannass Chan and Ka-Hing Wong. 2019. Improving quality of teaching and learning in classes by using augmented reality video. Computers & Education 128 (2019) 88\u2013101.","DOI":"10.1016\/j.compedu.2018.09.014"},{"key":"e_1_3_3_3_99_2","unstructured":"Ce Zhang Taixi Lu Md\u00a0Mohaiminul Islam Ziyang Wang Shoubin Yu Mohit Bansal and Gedas Bertasius. 2023. A simple llm framework for long-range video question-answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17235 (2023)."},{"key":"e_1_3_3_3_100_2","unstructured":"Muru Zhang Ofir Press William Merrill Alisa Liu and Noah\u00a0A Smith. 2023. How language model hallucinations can snowball. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13534 (2023)."},{"key":"e_1_3_3_3_101_2","unstructured":"Shaofei Zhang et\u00a0al. 2023. HaMeR: Hand Mesh Recovery from Monocular Images. arxiv:https:\/\/arXiv.org\/abs\/2306.00970\u00a0[cs.CV]"},{"key":"e_1_3_3_3_102_2","doi-asserted-by":"crossref","unstructured":"Ada\u00a0Yi Zhao Aditya Gunturu Ellen Yi-Luen Do and Ryo Suzuki. 2025. Guided Reality: Generating Visually-Enriched AR Task Guidance with LLMs and Vision Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.03547 (2025).","DOI":"10.1145\/3746059.3747784"},{"key":"e_1_3_3_3_103_2","unstructured":"Henghao Zhao Ge-Peng Ji Rui Yan Huan Xiong and Zechao Li. 2025. VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.07519 (2025)."},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"crossref","unstructured":"Running Zhao Zhihan Jiang Xinchen Zhang Chirui Chang Handi Chen Weipeng Deng Luyao Jin Xiaojuan Qi Xun Qian and Edith\u00a0CH Ngai. 2025. NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.14395 (2025).","DOI":"10.1145\/3746059.3747626"},{"key":"e_1_3_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747676"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"crossref","unstructured":"Hazem Zohny John McMillan and Mike King. 2023. Ethics of generative AI. 79\u201380\u00a0pages.","DOI":"10.1136\/jme-2023-108909"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790715","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T08:52:27Z","timestamp":1776415947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":105,"alternative-id":["10.1145\/3772318.3790715","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790715","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}