{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:25:37Z","timestamp":1774628737909,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,7]]},"DOI":"10.1145\/3587819.3590972","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T17:24:19Z","timestamp":1686245059000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Learning to Predict Head Pose in Remotely-Rendered Virtual Reality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7976-0261","authenticated-orcid":false,"given":"Gazi Karam","family":"Illahi","sequence":"first","affiliation":[{"name":"Nokia Technologies, Espoo, Finland"},{"name":"Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8365-6237","authenticated-orcid":false,"given":"Ashutosh","family":"Vaishnav","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4685-6763","authenticated-orcid":false,"given":"Teemu","family":"K\u00e4m\u00e4r\u00e4inen","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0423-1060","authenticated-orcid":false,"given":"Matti","family":"Siekkinen","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"},{"name":"University of Helsinki, Helsinki, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1351-1988","authenticated-orcid":false,"given":"Mario","family":"Di Francesco","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}]}],"member":"320","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Markus Wiedemann, and Dieter Kranzlm\u00fcller.","author":"Anthes Christoph","year":"2016","unstructured":"Christoph Anthes, Rub\u00e9n Jes\u00fas Garc\u00eda-Hern\u00e1ndez, Markus Wiedemann, and Dieter Kranzlm\u00fcller. 2016. State of the art of virtual reality technology. In 2016 IEEE aerospace conference. IEEE, 1--19."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767965"},{"key":"e_1_3_2_1_3_1","unstructured":"Shaojie Bai J. Zico Kolter and Vladlen Koltun. 2018. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. http:\/\/arxiv.org\/abs\/1803.01271 arXiv:1803.01271 [cs]."},{"key":"e_1_3_2_1_4_1","volume-title":"Pattern recognition and machine learning","author":"Bishop Christopher M","unstructured":"Christopher M Bishop and Nasser M Nasrabadi. 2006. Pattern recognition and machine learning. Vol. 4. Springer."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180785"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1052-4"},{"key":"e_1_3_2_1_7_1","volume-title":"Virtual reality technology","author":"Burdea Grigore C","unstructured":"Grigore C Burdea and Philippe Coiffet. 2003. Virtual reality technology. John Wiley & Sons."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420036206"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177102.3177115"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2006.01.001"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings, Part V 16","author":"Droste Richard","year":"2020","unstructured":"Richard Droste, Jianbo Jiao, and J Alison Noble. 2020. Unified image and video saliency modeling. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part V 16. Springer, 419--435."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448018.3457996"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"William Falcon and the PyTorch Lightning team. 2019. PyTorch Lightning. 10.5281\/zenodo.7545285","DOI":"10.5281\/zenodo.7545285"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229878"},{"key":"e_1_3_2_1_15_1","volume-title":"Virtual reality","author":"Greengard Samuel","unstructured":"Samuel Greengard. 2019. Virtual reality. Mit Press."},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in robot kinematics: Analysis and design","author":"Gregorio Raffaele Di","unstructured":"Raffaele Di Gregorio. 2008. A novel point of view to define the distance between two rigid-body poses. In Advances in robot kinematics: Analysis and design. Springer, 361--369."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413699"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. IEEE 85, 1 (Jan. 1997), 6--23. https:\/\/doi.org\/10.1109Z5.554205 Conference Name: Proceedings of the IEEE.","author":"Hall D.L.","unstructured":"D.L. Hall and J. Llinas. 1997. An introduction to multisensor data fusion. Proc. IEEE 85, 1 (Jan. 1997), 6--23. https:\/\/doi.org\/10.1109Z5.554205 Conference Name: Proceedings of the IEEE."},{"key":"e_1_3_2_1_19_1","volume-title":"6D Rotation Representation For Unconstrained Head Pose Estimation. arXiv preprint arXiv:2202.12555","author":"Hempel Thorsten","year":"2022","unstructured":"Thorsten Hempel, Ahmed A Abdelrahman, and Ayoub Al-Hamadi. 2022. 6D Rotation Representation For Unconstrained Head Pose Estimation. arXiv preprint arXiv:2202.12555 (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2009.2016571"},{"key":"e_1_3_2_1_21_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.3032608"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014097"},{"key":"e_1_3_2_1_24_1","unstructured":"Huawei. 2018. Cloud VR Solution White Paper. http:\/\/https:\/\/www.huawei.com\/minisite\/pdf\/ilab\/cloud_vr_solutions_wp_en.pdf"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-009-0161-2"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3463383"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534086.3534331"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8193-6"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240620"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.694"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"e_1_3_2_1_32_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2913364"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906608"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/769953.769976"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2007.4458059"},{"key":"e_1_3_2_1_37_1","volume-title":"Shape, contour and grouping in computer vision","author":"LeCun Yann","unstructured":"Yann LeCun, Patrick Haffner, L\u00e9on Bottou, and Yoshua Bengio. 1999. Object recognition with gradient-based learning. In Shape, contour and grouping in computer vision. Springer, 319--345."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423328.3423497"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"e_1_3_2_1_40_1","volume-title":"A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019","author":"Lipton Zachary C","year":"2015","unstructured":"Zachary C Lipton, John Berkowitz, and Charles Elkan. 2015. A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)."},{"key":"e_1_3_2_1_41_1","volume-title":"Flight Mechanics (Estimation Theory Symposium","author":"Markley F Landis","year":"1993","unstructured":"F Landis Markley. 1993. Attitude determination using vector observations: A fast optimal matrix algorithm. In Flight Mechanics (Estimation Theory Symposium, 1992."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"e_1_3_2_1_43_1","first-page":"64","article-title":"Recurrent neural networks","volume":"5","author":"Medsker Larry R","year":"2001","unstructured":"Larry R Medsker and LC Jain. 2001. Recurrent neural networks. Design and Applications 5 (2001), 64--67.","journal-title":"Design and Applications"},{"key":"e_1_3_2_1_44_1","volume-title":"Retrieved","year":"2022","unstructured":"Nvidia. 2022. NVIDIA TensorRT. Retrieved November 11, 2022 from https:\/\/developer.nvidia.com\/tensorrt"},{"key":"e_1_3_2_1_45_1","unstructured":"The Insight Partners. 2022. AR\/VR market size worldwide 2021 2028. https:\/\/www.statista.com\/statistics\/591181\/global-augmented-virtual-reality-market-size"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929472"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01901476"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3083073"},{"key":"e_1_3_2_1_49_1","volume-title":"Deep multimodal learning: A survey on recent advances and trends","author":"Ramachandram Dhanesh","year":"2017","unstructured":"Dhanesh Ramachandram and Graham W Taylor. 2017. Deep multimodal learning: A survey on recent advances and trends. IEEE signal processing magazine 34, 6 (2017), 96--108."},{"key":"e_1_3_2_1_50_1","volume-title":"Computer Graphics Forum","author":"Reinert Bernhard","unstructured":"Bernhard Reinert, Johannes Kopf, Tobias Ritschel, Eduardo Cuervo, David Chu, and Hans-Peter Seidel. 2016. Proxy-guided image-based rendering for mobile devices. In Computer Graphics Forum, Vol. 35. Wiley Online Library, 353--362."},{"key":"e_1_3_2_1_51_1","volume-title":"Virtual Reality Market Size & Share Report","author":"Research Grand View","year":"2022","unstructured":"Grand View Research. 2022. Virtual Reality Market Size & Share Report, 2022--2030. https:\/\/www.grandviewresearch.com\/industry-analysis\/virtual-reality-vr-market"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070520"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2348816.2348825"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/325334.325242"},{"key":"e_1_3_2_1_55_1","volume-title":"Computer vision: algorithms and applications","author":"Szeliski Richard","unstructured":"Richard Szeliski. 2022. Computer vision: algorithms and applications. Springer Nature."},{"key":"e_1_3_2_1_56_1","volume-title":"Extended Reality: Its Challenges, Usage and Future Ahead. https:\/\/www.etelligens.com\/blog\/extended-reality-its-challenges-usage-and-future-ahead\/","author":"Technologies Etelligens","year":"2023","unstructured":"Etelligens Technologies. 2023. Extended Reality: Its Challenges, Usage and Future Ahead. https:\/\/www.etelligens.com\/blog\/extended-reality-its-challenges-usage-and-future-ahead\/"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798108"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2005.1492755"},{"key":"e_1_3_2_1_59_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_60_1","unstructured":"Greg Welch Gary Bishop et al. 1995. An introduction to the Kalman filter. (1995)."},{"key":"e_1_3_2_1_61_1","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems 34 (2021), 22419--22430.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE53296.2022.9730327"},{"key":"e_1_3_2_1_63_1","volume-title":"Recent trends in deep learning based natural language processing. ieee Computational intelligenCe magazine 13, 3","author":"Young Tom","year":"2018","unstructured":"Tom Young, Devamanyu Hazarika, Soujanya Poria, and Erik Cambria. 2018. Recent trends in deep learning based natural language processing. ieee Computational intelligenCe magazine 13, 3 (2018), 55--75."},{"key":"e_1_3_2_1_64_1","volume-title":"Progress in astronautics and aeronautics: fundamentals of Kalman filtering: a practical approach","author":"Zarchan Paul","unstructured":"Paul Zarchan. 2005. Progress in astronautics and aeronautics: fundamentals of Kalman filtering: a practical approach. Vol. 208. Aiaa."},{"key":"e_1_3_2_1_65_1","unstructured":"Ailing Zeng Muxi Chen Lei Zhang and Qiang Xu. 2022. Are Transformers Effective for Time Series Forecasting? http:\/\/arxiv.org\/abs\/2205.13504 arXiv:2205.13504 [cs]."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517260"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/45.666641"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"event":{"name":"MMSys '23: 14th Conference on ACM Multimedia Systems","location":"Vancouver BC Canada","acronym":"MMSys '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 14th ACM Multimedia Systems Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3587819.3590972","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3587819.3590972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:01Z","timestamp":1750183681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3587819.3590972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":69,"alternative-id":["10.1145\/3587819.3590972","10.1145\/3587819"],"URL":"https:\/\/doi.org\/10.1145\/3587819.3590972","relation":{},"subject":[],"published":{"date-parts":[[2023,6,7]]},"assertion":[{"value":"2023-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}