{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:07Z","timestamp":1776931147707,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791929","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:28Z","timestamp":1776053548000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9135-6080","authenticated-orcid":false,"given":"Tianyu","family":"Xu","sequence":"first","affiliation":[{"name":"Google, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4355-7241","authenticated-orcid":false,"given":"Sieun","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5664-3431","authenticated-orcid":false,"given":"Qianhui","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8323-5503","authenticated-orcid":false,"given":"Ruoyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3260-5519","authenticated-orcid":false,"given":"Tejasvi","family":"Ravi","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8896-7504","authenticated-orcid":false,"given":"Anuva","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8670-1833","authenticated-orcid":false,"given":"Katrina","family":"Passarella-Ward","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6166-6138","authenticated-orcid":false,"given":"Junyi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4428-889X","authenticated-orcid":false,"given":"Adarsh","family":"Kowdle","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Holger Caesar Jasper Uijlings and Vittorio Ferrari. 2018. COCO-Stuff: Thing and Stuff Classes in Context. arxiv:https:\/\/arXiv.org\/abs\/1612.03716\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1612.03716"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Jean-Fran\u00e7ois Cardoso. 1998. Blind Signal Separation: Statistical Principles. Proc. IEEE 86 10 (1998) 2009\u20132025. 10.1109\/5.720250","DOI":"10.1109\/5.720250"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661556"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Ishan Chatterjee Maruchi Kim Vivek Jayaram Shyamnath Gollakota Ira Kemelmacher Shwetak Patel and Steven\u00a0M. Seitz. 2022. ClearBuds: wireless binaural earbuds for learning-based speech enhancement(MobiSys \u201922). Association for Computing Machinery New York NY USA 384\u2013396. 10.1145\/3498361.3538933","DOI":"10.1145\/3498361.3538933"},{"key":"e_1_3_3_3_6_2","unstructured":"Jiaben Chen Renrui Zhang Dongze Lian Jiaqi Yang Ziyao Zeng and Jianbo Shi. 2022. iQuery: Instruments as Queries for Audio-Visual Sound Separation. arxiv:https:\/\/arXiv.org\/abs\/2212.03814\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2212.03814"},{"key":"e_1_3_3_3_7_2","unstructured":"Liang-Chieh Chen Yukun Zhu George Papandreou Florian Schroff and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. arxiv:https:\/\/arXiv.org\/abs\/1802.02611\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1802.02611"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713745"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","unstructured":"E.\u00a0Colin Cherry. 1953. Some Experiments on the Recognition of Speech with One and with Two Ears. The Journal of the Acoustical Society of America 25 5 (1953) 975\u2013979. 10.1121\/1.1907229","DOI":"10.1121\/1.1907229"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676384"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676424"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Jung-Woo Choi Franz Zotter Byeongho Jo and Jae-Hyoun Yoo. 2022. Multiarray Eigenbeam-ESPRIT for 3D Sound Source Localization With Multiple Spherical Microphone Arrays. IEEE\/ACM Transactions on Audio Speech and Language Processing 30 (2022) 2310\u20132325. 10.1109\/TASLP.2022.3183929","DOI":"10.1109\/TASLP.2022.3183929"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625008.3625042"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Jiankang Deng Jia Guo Jing Yang Niannan Xue Irene Kotsia and Stefanos Zafeiriou. 2022. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 10 (Oct. 2022) 5962\u20135979. 10.1109\/tpami.2021.3087709","DOI":"10.1109\/tpami.2021.3087709"},{"key":"e_1_3_3_3_15_2","volume-title":"yolov8-face: YOLOv8 face detection with landmarks","year":"2024","unstructured":"derronqi. 2024. yolov8-face: YOLOv8 face detection with landmarks. https:\/\/github.com\/derronqi\/yolov8-face GitHub repository, commit 18f9fde."},{"key":"e_1_3_3_3_16_2","unstructured":"Henghui Du Guangyao Li Chang Zhou Chunjie Zhang Alan Zhao and Di Hu. 2025. Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation. arxiv:https:\/\/arXiv.org\/abs\/2503.13068\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2503.13068"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Ariel Ephrat Inbar Mosseri Oran Lang Tali Dekel Kevin Wilson Avinatan Hassidim William\u00a0T. Freeman and Michael Rubinstein. 2018. Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Transactions on Graphics 37 4 (July 2018) 1\u201311. 10.1145\/3197517.3201357","DOI":"10.1145\/3197517.3201357"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/I3DA48870.2021.9610916"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"e_1_3_3_3_20_2","unstructured":"Google. 2025. Gemini. https:\/\/gemini.google.com\/."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Gabriel Haas Evgeny Stemasov Michael Rietzler and Enrico Rukzio. 2020. Interactive Auditory Mediated Reality: Towards User-defined Personal Soundscapes(DIS \u201920). Association for Computing Machinery New York NY USA 16\u00a0pages. 10.1145\/3357236.3395493","DOI":"10.1145\/3357236.3395493"},{"key":"e_1_3_3_3_22_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arxiv:https:\/\/arXiv.org\/abs\/1503.02531\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_3_3_23_2","first-page":"35","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV)","author":"Huang Chao","year":"2024","unstructured":"Chao Huang, Susan Liang, Yapeng Tian, Anurag Kumar, and Chenliang Xu. 2024. High-Quality Visually-Guided Sound Separation from Diverse Categories. In Proceedings of the Asian Conference on Computer Vision (ACCV). 35\u201349."},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","unstructured":"Aapo Hyv\u00e4rinen and Erkki Oja. 2000. Independent Component Analysis: Algorithms and Applications. Neural Networks 13 4-5 (2000) 411\u2013430. 10.1016\/S0893-6080(00)00026-5","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047270"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502020"},{"key":"e_1_3_3_3_27_2","volume-title":"Ultralytics YOLO","author":"Jocher Glenn","year":"2023","unstructured":"Glenn Jocher, Jing Qiu, and Ayush Chaurasia. 2023. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_3_3_28_2","unstructured":"Ilya Kavalerov Scott Wisdom Hakan Erdogan Brian Patton Kevin Wilson Jonathan\u00a0Le Roux and John\u00a0R. Hershey. 2019. Universal Sound Separation. arxiv:https:\/\/arXiv.org\/abs\/1905.03330\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/1905.03330"},{"key":"e_1_3_3_3_29_2","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arxiv:https:\/\/arXiv.org\/abs\/2304.02643\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.02643"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446843"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Joanna Luberadzka Enric Gus\u00f3\u00a0Mu\u00f1oz Umut Sayin and Adan Garriga. 2025. Audio technology for improving social interaction in extended reality. Frontiers in Virtual Reality Volume 5 - 2024 (2025). 10.3389\/frvir.2024.1442774","DOI":"10.3389\/frvir.2024.1442774"},{"key":"e_1_3_3_3_32_2","unstructured":"Meta Reality Labs Research. 2022. Audio Presence: The \u201cperceptual superpower\u201d that will make the metaverse feel real. https:\/\/tech.facebook.com\/reality-labs\/2022\/06\/audio-presence-the-perceptual-superpower-that-will-make-the-metaverse-feel-real. Meta Tech Blog."},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Nikolaos Moustakas Andreas Floros Emmanouel Rovithis and Konstantinos Vogklis. 2021. Prediction and Controlling of Auditory Perception in Augmented Environments. A Loudness-Based Dynamic Mixing Technique. Applied Sciences 11 22 (2021). 10.3390\/app112210944","DOI":"10.3390\/app112210944"},{"key":"e_1_3_3_3_34_2","unstructured":"Rajeev Nongpiur and Tianyu Xu. 2025. Passively measuring room reverb. U.S. Patent Application No. 18\/739 899. Published December 11 2025."},{"key":"e_1_3_3_3_35_2","unstructured":"Rajeev Nongpiur and Tianyu Xu. 2025. System for measuring room reverb. U.S. Patent Application No. 18\/627 621. Published October 9 2025."},{"key":"e_1_3_3_3_36_2","unstructured":"Peter Ochieng. 2023. Deep neural network techniques for monaural speech enhancement: state of the art analysis. arxiv:https:\/\/arXiv.org\/abs\/2212.00369\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2212.00369"},{"key":"e_1_3_3_3_37_2","unstructured":"OpenAI. 2025. ChatGPT. https:\/\/chat.openai.com\/."},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984517"},{"key":"e_1_3_3_3_39_2","unstructured":"Katharine Patterson Kevin Wilson Scott Wisdom and John\u00a0R. Hershey. 2022. Distance-Based Sound Separation. arxiv:https:\/\/arXiv.org\/abs\/2207.00562\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2207.00562"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Songyou Peng Kyle Genova Chiyu\u00a0\"Max\" Jiang Andrea Tagliasacchi Marc Pollefeys and Thomas Funkhouser. 2023. OpenScene: 3D Scene Understanding with Open Vocabularies. arxiv:https:\/\/arXiv.org\/abs\/2211.15654\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.15654","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"e_1_3_3_3_41_2","unstructured":"Darius Petermann Gordon Wichern Zhong-Qiu Wang and Jonathan\u00a0Le Roux. 2022. The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks. arxiv:https:\/\/arXiv.org\/abs\/2110.09958\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2110.09958"},{"key":"e_1_3_3_3_42_2","unstructured":"Chandan K\u00a0A Reddy Vishak Gopal and Ross Cutler. 2021. DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors. arxiv:https:\/\/arXiv.org\/abs\/2010.15258\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2010.15258"},{"key":"e_1_3_3_3_43_2","unstructured":"Simon Rouard Francisco Massa and Alexandre D\u00e9fossez. 2022. Hybrid Transformers for Music Source Separation. arxiv:https:\/\/arXiv.org\/abs\/2211.08553\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2211.08553"},{"key":"e_1_3_3_3_44_2","unstructured":"Jonathan\u00a0Le Roux Scott Wisdom Hakan Erdogan and John\u00a0R. Hershey. 2018. SDR - half-baked or well done? arxiv:https:\/\/arXiv.org\/abs\/1811.02508\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/1811.02508"},{"key":"e_1_3_3_3_45_2","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2019. MobileNetV2: Inverted Residuals and Linear Bottlenecks. arxiv:https:\/\/arXiv.org\/abs\/1801.04381\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1801.04381"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR67309.2025.00030"},{"key":"e_1_3_3_3_47_2","unstructured":"Dongeek Shin and Tianyu Xu. 2025. Context-based user input control of near-eye displays. U.S. Patent Application No. 18\/669 279. Published November 20 2025."},{"key":"e_1_3_3_3_48_2","unstructured":"Dongeek Shin Tianyu Xu and Jennifer Irturk. 2025. Saliency-based mixed-order ambisonics encoding of multiple sound sources for immersive spatial audio. U.S. Patent No. 12 494 214. Issued December 9 2025."},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676406"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","unstructured":"John Sweller. 1988. Cognitive Load During Problem Solving: Effects on Learning. Cognitive Science 12 2 (1988) 257\u2013285. 10.1207\/s15516709cog1202_4","DOI":"10.1207\/s15516709cog1202_4"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","unstructured":"Jiwen Tang. 2023. Research on the Application of Sound in Virtual Reality. Highlights in Science Engineering and Technology 44 (04 2023) 206\u2013212. 10.54097\/hset.v44i.7323","DOI":"10.54097\/hset.v44i.7323"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","unstructured":"Bart Thomee David\u00a0A. Shamma Gerald Friedland Benjamin Elizalde Karl Ni Douglas Poland Damian Borth and Li-Jia Li. 2016. YFCC100M: the new data in multimedia research. Commun. ACM 59 2 (2016). 10.1145\/2812802","DOI":"10.1145\/2812802"},{"key":"e_1_3_3_3_53_2","unstructured":"Efthymios Tzinis Scott Wisdom Aren Jansen Shawn Hershey Tal Remez Daniel P.\u00a0W. Ellis and John\u00a0R. Hershey. 2021. Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds. arxiv:https:\/\/arXiv.org\/abs\/2011.01143\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2011.01143"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"crossref","unstructured":"Efthymios Tzinis Scott Wisdom Tal Remez and John\u00a0R. Hershey. 2022. AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation. arxiv:https:\/\/arXiv.org\/abs\/2207.10141\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2207.10141","DOI":"10.1007\/978-3-031-19836-6_21"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606779"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642057"},{"key":"e_1_3_3_3_58_2","unstructured":"Helin Wang Jiarui Hai Yen-Ju Lu Karan Thakkar Mounya Elhilali and Najim Dehak. 2025. SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer. arxiv:https:\/\/arXiv.org\/abs\/2409.08425\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2409.08425"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474769"},{"key":"e_1_3_3_3_60_2","unstructured":"Scott Wisdom Efthymios Tzinis Hakan Erdogan Ron\u00a0J. Weiss Kevin Wilson and John\u00a0R. Hershey. 2020. Unsupervised Sound Separation Using Mixture Invariant Training. arxiv:https:\/\/arXiv.org\/abs\/2006.12701\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2006.12701"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1978963"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"crossref","unstructured":"Brandon Woodard Margarita Geleta Joseph J.\u00a0LaViola Jr. Andrea Fanelli and Rhonda Wilson. 2025. AudioMiXR: Spatial Audio Object Manipulation with 6DoF for Sound Design in Augmented Reality. arxiv:https:\/\/arXiv.org\/abs\/2502.02929\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2502.02929","DOI":"10.1145\/3749478"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00053"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Tianyu Xu Jihan Li Penghe Zu Pranav Sahay Maruchi Kim Jack Obeng-Marnu Farley Miller Xun Qian Katrina Passarella Mahitha Rachumalla Rajeev Nongpiur and D Shin. 2025. Enhancing XR Auditory Realism via Multimodal Scene-Aware Acoustic Rendering(UIST \u201925). Association for Computing Machinery New York NY USA Article 17 16\u00a0pages. 10.1145\/3746059.3747730","DOI":"10.1145\/3746059.3747730"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Jing Yang Amit Barde and M. Billinghurst. 2022. Audio Augmented Reality: A Systematic Review of Technologies Applications and Future Research Directions. Journal of the Audio Engineering Society (2022). 10.17743\/jaes.2022.0048","DOI":"10.17743\/jaes.2022.0048"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"crossref","unstructured":"Shengkui Zhao Yukun Ma Chongjia Ni Chong Zhang Hao Wang Trung\u00a0Hieu Nguyen Kun Zhou Jiaqi Yip Dianwen Ng and Bin Ma. 2024. MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation. arxiv:https:\/\/arXiv.org\/abs\/2312.11825\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2312.11825","DOI":"10.1109\/ICASSP48485.2024.10445985"},{"key":"e_1_3_3_3_68_2","unstructured":"Shengkui Zhao Zexu Pan and Bin Ma. 2025. ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment. arxiv:https:\/\/arXiv.org\/abs\/2506.19398\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2506.19398"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747671"}],"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\/3772318.3791929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:15:46Z","timestamp":1776417346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791929"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":68,"alternative-id":["10.1145\/3772318.3791929","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791929","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"}}]}}