{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:00:05Z","timestamp":1772906405014,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,9]],"date-time":"2023-05-09T00:00:00Z","timestamp":1683590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CONIX","award":["JUMP 2.0 Center"],"award-info":[{"award-number":["JUMP 2.0 Center"]}]},{"name":"NSF IoCT","award":["2211301"],"award-info":[{"award-number":["2211301"]}]},{"name":"ARL IoBT","award":["W911NF1720196"],"award-info":[{"award-number":["W911NF1720196"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,9]]},"DOI":"10.1145\/3576842.3582363","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T22:58:08Z","timestamp":1682549888000},"page":"79-92","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Acuity: Creating Realistic Digital Twins Through Multi-resolution Pointcloud Processing and Audiovisual Sensor Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8174-4751","authenticated-orcid":false,"given":"Jason","family":"Wu","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0232-125X","authenticated-orcid":false,"given":"Ziqi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4232-3345","authenticated-orcid":false,"given":"Ankur","family":"Sarker","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3782-9192","authenticated-orcid":false,"given":"Mani","family":"Srivastava","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,5,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885251"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2018.00031"},{"key":"e_1_3_2_1_3_1","unstructured":"Anthony Capaccio. 2022. Microsoft (MSFT) US Army HoloLens Goggles Gave Soldiers Nausea Headaches - Bloomberg. https:\/\/www.bloomberg.com\/news\/articles\/2022-10-13\/microsoft-s-us-army-version-of-hololens-goggles-gave-soldiers-nausea-headaches."},{"key":"e_1_3_2_1_4_1","volume-title":"Multi-view 3d object detection network for autonomous driving. arXiv. arXiv preprint arXiv:1611.07759","author":"Chen X","year":"2016","unstructured":"X Chen, H Ma, J Wan, B Li, and T Xia. 2016. Multi-view 3d object detection network for autonomous driving. arXiv. arXiv preprint arXiv:1611.07759 (2016)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2091502"},{"key":"e_1_3_2_1_6_1","volume-title":"ATSC Implementation Subcommittee Finding: Relative Timing of Sound and Vision for Broadcast Operations. IS-191 26","author":"Advanced Television\u00a0Systems Committee 2003.","year":"2003","unstructured":"Advanced Television\u00a0Systems Committee 2003. ATSC Implementation Subcommittee Finding: Relative Timing of Sound and Vision for Broadcast Operations. IS-191 26 (2003)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2945292.2945311"},{"key":"e_1_3_2_1_8_1","unstructured":"HARK development team. 2021. GHDSS. hark. https:\/\/www.hark.jp\/document\/hark-document-en\/subsec-GHDSS.html"},{"key":"e_1_3_2_1_9_1","unstructured":"HARK development team. 2021. HARKTOOL5GUI 3.3.0 Documentation. hark. https:\/\/www.hark.jp\/document\/packages\/harktool5-gui-en\/harktool5-gui.html#fd-conv-label"},{"key":"e_1_3_2_1_10_1","unstructured":"HARK development team. 2021. How to Generate a Transfer Function Using HARKTOOL5. https:\/\/www.hark.jp\/document\/tf\/generating_transfer_functions\/Generating_a_Transfer_Function_Using_HARKTOOL5.html. (Accessed on 10\/04\/2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIM.2021.9436090"},{"key":"e_1_3_2_1_12_1","unstructured":"C\u00e9dric F\u00e9votte R\u00e9mi Gribonval and Emmanuel Vincent. 2005. BSS_EVAL toolbox user guide\u2013Revision 2.0. (2005)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_14_1","volume-title":"The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Geiger Andreas","year":"2012","unstructured":"Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_15_1","volume-title":"CVFNet: Real-time 3D Object Detection by Learning Cross View Features. arXiv preprint arXiv:2203.06585","author":"Gu Jiaqi","year":"2022","unstructured":"Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, and Zhiyuan Zhang. 2022. CVFNet: Real-time 3D Object Detection by Learning Cross View Features. arXiv preprint arXiv:2203.06585 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS47537.2019.9008727"},{"key":"e_1_3_2_1_17_1","volume-title":"Exploring extended reality with illixr: A new playground for architecture research. arXiv preprint arXiv:2004.04643","author":"Huzaifa Muhammad","year":"2020","unstructured":"Muhammad Huzaifa, Rishi Desai, Samuel Grayson, Xutao Jiang, Ying Jing, Jae Lee, Fang Lu, Yihan Pang, Joseph Ravichandran, Finn Sinclair, 2020. Exploring extended reality with illixr: A new playground for architecture research. arXiv preprint arXiv:2004.04643 (2020)."},{"key":"e_1_3_2_1_18_1","unstructured":"Leia Inc.2020. Leia Inc. \u2013 3D Lightfield Experience Platform. https:\/\/www.leiainc.com\/#Product. (Accessed on 10\/30\/2022)."},{"key":"e_1_3_2_1_19_1","unstructured":"Intel. 2018. Llibrealsense. https:\/\/github.com\/IntelRealSense\/librealsense"},{"key":"e_1_3_2_1_20_1","unstructured":"Intel. 2022. Intel Realsense Lidar L515. https:\/\/www.intelrealsense.com\/lidar-camera-l515\/"},{"key":"e_1_3_2_1_21_1","unstructured":"Mike Isaac. 2022. Meta\u2019s Move to the Metaverse Drags Down Profit - The New York Times. https:\/\/www.nytimes.com\/2022\/02\/02\/technology\/meta-facebook-earnings-metaverse.html. (Accessed on 10\/20\/2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2004.1414674"},{"key":"e_1_3_2_1_23_1","unstructured":"Jungbeom Ko Hyunchul Kim and Jungsuk Kim. 2022. Real-Time Sound Source Localization for Low-Power IoT Devices Based on Multi-Stream CNN. In Sensors."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20123527"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.101.2000364"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yi Luo Zhuo Chen and Takuya Yoshioka. 2019. Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation. arXiv:arXiv:1910.06379","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IRS.2012.6233370"},{"key":"e_1_3_2_1_30_1","unstructured":"Microsoft. 2022. Microsoft HoloLens | Mixed Reality Technology for Business. https:\/\/www.microsoft.com\/en-us\/hololens. (Accessed on 10\/20\/2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2469142"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288455"},{"key":"e_1_3_2_1_33_1","volume-title":"31st Conference on Neural Information Processing Systems.","author":"Qi R","year":"2017","unstructured":"Charles\u00a0R Qi, Li Yi, Hao Su, and Leonidas\u00a0J Guibas. 2017. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In 31st Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_34_1","volume-title":"Spherical microphone array beamforming. Speech Processing in Modern Communication","author":"Rafaely Boaz","year":"2010","unstructured":"Boaz Rafaely, Yotam Peled, Morag Agmon, Dima Khaykin, and Etan Fisher. 2010. Spherical microphone array beamforming. Speech Processing in Modern Communication (2010), 281\u2013305."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.06.141"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10842-y"},{"key":"e_1_3_2_1_38_1","volume-title":"Point-voxel feature set abstraction with local vector representation for 3D object detection. arXiv preprint arXiv:2102.00463","author":"Shi Shaoshuai","year":"2021","unstructured":"Shaoshuai Shi, Li Jiang, Jiajun Deng, Zhe Wang, Chaoxu Guo, Jianping Shi, Xiaogang Wang, and Hongsheng Li. 2021. PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection. arXiv preprint arXiv:2102.00463 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"e_1_3_2_1_40_1","volume-title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. arXiv preprint arXiv:1907.03670","author":"Shi Shaoshuai","year":"2019","unstructured":"Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, and Hongsheng Li. 2019. From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. arXiv preprint arXiv:1907.03670 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"e_1_3_2_1_42_1","volume-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation. arXiv preprint arXiv:1806.03185","author":"Stoller Daniel","year":"2018","unstructured":"Daniel Stoller, Sebastian Ewert, and Simon Dixon. 2018. Wave-u-net: A multi-scale neural network for end-to-end audio source separation. arXiv preprint arXiv:1806.03185 (2018)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2873186"},{"key":"e_1_3_2_1_45_1","unstructured":"Krisp Technologies. 2022. Noise Cancelling App & Echo Reduction Software | Krisp. https:\/\/krisp.ai\/. (Accessed on 10\/20\/2022)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"e_1_3_2_1_47_1","volume-title":"Advanced Signal Processing and Digital Noise Reduction","author":"Vaseghi V","unstructured":"Saeed\u00a0V Vaseghi. 1996. Spectral subtraction. In Advanced Signal Processing and Digital Noise Reduction. Springer, 242\u2013260."},{"key":"e_1_3_2_1_48_1","unstructured":"Velodyne. 2022. How does LiDAR Work?https:\/\/velodynelidar.com\/what-is-lidar\/"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agsy.2020.103046"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"e_1_3_2_1_51_1","volume-title":"Performance measurement in blind audio source separation","author":"Vincent Emmanuel","unstructured":"Emmanuel Vincent, R\u00e9mi Gribonval, and C\u00e9dric F\u00e9votte. 2006. Performance measurement in blind audio source separation. In IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, Vol.\u00a014. 1462\u20131469. https:\/\/doi.org\/nria-00544230"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759617"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2014.2323139"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.07.003"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446382.3448663"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Yin Zhou and Oncel Tuzel. 2017. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection. In arXiv:1711.06396 [cs.CV].","DOI":"10.1109\/CVPR.2018.00472"}],"event":{"name":"IoTDI '23: International Conference on Internet-of-Things Design and Implementation","location":"San Antonio TX USA","acronym":"IoTDI '23","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 8th ACM\/IEEE Conference on Internet of Things Design and Implementation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576842.3582363","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3576842.3582363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:58Z","timestamp":1750183738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576842.3582363"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,9]]},"references-count":58,"alternative-id":["10.1145\/3576842.3582363","10.1145\/3576842"],"URL":"https:\/\/doi.org\/10.1145\/3576842.3582363","relation":{},"subject":[],"published":{"date-parts":[[2023,5,9]]},"assertion":[{"value":"2023-05-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}