{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:18:38Z","timestamp":1777655918765,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Nissan Motor Corporation"},{"name":"NSERC Discovery Grant"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599312","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"1837-1849","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Domain-Guided Spatio-Temporal Self-Attention for Egocentric 3D Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0870-8185","authenticated-orcid":false,"given":"Jinman","family":"Park","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2034-2638","authenticated-orcid":false,"given":"Kimathi","family":"Kaai","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9844-8437","authenticated-orcid":false,"given":"Saad","family":"Hossain","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8716-1565","authenticated-orcid":false,"given":"Norikatsu","family":"Sumi","sequence":"additional","affiliation":[{"name":"Nissan Motor Corporation, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9389-727X","authenticated-orcid":false,"given":"Sirisha","family":"Rambhatla","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7260-2260","authenticated-orcid":false,"given":"Paul","family":"Fieguth","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_3_2_2_3_1","volume-title":"Is space-time attention all you need for video understanding. arXiv preprint arXiv:2102.05095","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius , Heng Wang , and Lorenzo Torresani . 2021. Is space-time attention all you need for video understanding. arXiv preprint arXiv:2102.05095 , Vol. 2 , 3 ( 2021 ), 4. Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding. arXiv preprint arXiv:2102.05095, Vol. 2, 3 (2021), 4."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"e_1_3_2_2_5_1","volume-title":"Media Conference (GEM). IEEE, 1--6.","author":"Carroll Michael","year":"2019","unstructured":"Michael Carroll , Ethan Osborne , and Caglar Yildirim . 2019 . Effects of VR gaming and game genre on player experience. In 2019 IEEE Games, Entertainment , Media Conference (GEM). IEEE, 1--6. Michael Carroll, Ethan Osborne, and Caglar Yildirim. 2019. Effects of VR gaming and game genre on player experience. In 2019 IEEE Games, Entertainment, Media Conference (GEM). IEEE, 1--6."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.610"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6689"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00081"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"e_1_3_2_2_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_12_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly etal 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).  Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_13_1","volume-title":"Dong In Kim, and Chunyan Miao","author":"Du Hongyang","year":"2021","unstructured":"Hongyang Du , Dusit Niyato , Jiawen Kang , Dong In Kim, and Chunyan Miao . 2021 . Optimal Targeted Advertising Strategy For Secure Wireless Edge Metaverse . arXiv preprint arXiv:2111.00511 (2021). Hongyang Du, Dusit Niyato, Jiawen Kang, Dong In Kim, and Chunyan Miao. 2021. Optimal Targeted Advertising Strategy For Secure Wireless Edge Metaverse. arXiv preprint arXiv:2111.00511 (2021)."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research , Vol. 9), Yee Whye Teh and Mike Titterington (Eds.). PMLR, Chia Laguna Resort, Sardinia, Italy, 249-- 256 . https:\/\/proceedings.mlr.press\/v9\/glorot10a.html Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 9), Yee Whye Teh and Mike Titterington (Eds.). PMLR, Chia Laguna Resort, Sardinia, Italy, 249--256. https:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"key":"e_1_3_2_2_15_1","volume-title":"Philippines. arXiv preprint arXiv:2103.06238","author":"Grepon Benzar Glen","year":"2021","unstructured":"Benzar Glen Grepon and Aldwin Lester Martinez . 2021. Architectural Visualization Using Virtual Reality: A User Experience in Simulating Buildings of a Community College in Bukidnon , Philippines. arXiv preprint arXiv:2103.06238 ( 2021 ). Benzar Glen Grepon and Aldwin Lester Martinez. 2021. Architectural Visualization Using Virtual Reality: A User Experience in Simulating Buildings of a Community College in Bukidnon, Philippines. arXiv preprint arXiv:2103.06238 (2021)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 68--84","author":"Imtiaz Hossain Mir Rayat","year":"2018","unstructured":"Mir Rayat Imtiaz Hossain and James J Little . 2018 . Exploiting temporal information for 3d human pose estimation . In Proceedings of the European Conference on Computer Vision (ECCV). 68--84 . Mir Rayat Imtiaz Hossain and James J Little. 2018. Exploiting temporal information for 3d human pose estimation. In Proceedings of the European Conference on Computer Vision (ECCV). 68--84."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct54149.2021.00036"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"e_1_3_2_2_21_1","volume-title":"On loss functions for deep neural networks in classification. arXiv preprint arXiv:1702.05659","author":"Janocha Katarzyna","year":"2017","unstructured":"Katarzyna Janocha and Wojciech Marian Czarnecki . 2017. On loss functions for deep neural networks in classification. arXiv preprint arXiv:1702.05659 ( 2017 ). Katarzyna Janocha and Wojciech Marian Czarnecki. 2017. On loss functions for deep neural networks in classification. arXiv preprint arXiv:1702.05659 (2017)."},{"key":"e_1_3_2_2_22_1","volume-title":"Inverse Kinematics and Temporal Convolutional Networks for Sequential Pose Analysis in VR. In 2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR). 274--281","author":"Jeong David C.","year":"2020","unstructured":"David C. Jeong , Jackie Jingyi Xu , and Lynn C. Miller . 2020 . Inverse Kinematics and Temporal Convolutional Networks for Sequential Pose Analysis in VR. In 2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR). 274--281 . https:\/\/doi.org\/10.1109\/AIVR50618. 2020 .00056 10.1109\/AIVR50618.2020.00056 David C. Jeong, Jackie Jingyi Xu, and Lynn C. Miller. 2020. Inverse Kinematics and Temporal Convolutional Networks for Sequential Pose Analysis in VR. In 2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR). 274--281. https:\/\/doi.org\/10.1109\/AIVR50618.2020.00056"},{"key":"e_1_3_2_2_23_1","volume-title":"OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos. arXiv preprint arXiv:2207.09725","author":"Jin Kyung-Min","year":"2022","unstructured":"Kyung-Min Jin , Gun-Hee Lee , and Seong-Whan Lee . 2022. OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos. arXiv preprint arXiv:2207.09725 ( 2022 ). Kyung-Min Jin, Gun-Hee Lee, and Seong-Whan Lee. 2022. OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos. arXiv preprint arXiv:2207.09725 (2022)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.24.12"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"e_1_3_2_2_26_1","volume-title":"Use of augmented and virtual reality tools in a general secondary education institution in the context of blended learning. arXiv preprint arXiv:2201.07003","author":"Kovalenko Valentyna","year":"2022","unstructured":"Valentyna Kovalenko , Maiia Marienko , and Alisa Sukhikh . 2022. Use of augmented and virtual reality tools in a general secondary education institution in the context of blended learning. arXiv preprint arXiv:2201.07003 ( 2022 ). Valentyna Kovalenko, Maiia Marienko, and Alisa Sukhikh. 2022. Use of augmented and virtual reality tools in a general secondary education institution in the context of blended learning. arXiv preprint arXiv:2201.07003 (2022)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01012"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.326"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_29"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"e_1_3_2_2_32_1","volume-title":"Post-processing of engineering analysis results for visualization in VR systems. arXiv preprint arXiv:1308.5847","author":"Maleshkov Stoyan","year":"2013","unstructured":"Stoyan Maleshkov and Dimo Chotrov . 2013. Post-processing of engineering analysis results for visualization in VR systems. arXiv preprint arXiv:1308.5847 ( 2013 ). Stoyan Maleshkov and Dimo Chotrov. 2013. Post-processing of engineering analysis results for visualization in VR systems. arXiv preprint arXiv:1308.5847 (2013)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"e_1_3_2_2_34_1","volume-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178","author":"Mehta Sachin","year":"2021","unstructured":"Sachin Mehta and Mohammad Rastegari . 2021. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 ( 2021 ). Sachin Mehta and Mohammad Rastegari. 2021. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)."},{"key":"e_1_3_2_2_35_1","volume-title":"Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588","author":"Mei Jianbiao","year":"2021","unstructured":"Jianbiao Mei , Mengmeng Wang , Yeneng Lin , Yi Yuan , and Yong Liu . 2021 . Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588 (2021). Jianbiao Mei, Mengmeng Wang, Yeneng Lin, Yi Yuan, and Yong Liu. 2021. Transvos: Video object segmentation with transformers. arXiv preprint arXiv:2106.00588 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.139"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.134"},{"key":"e_1_3_2_2_41_1","volume-title":"Lcr-net: Multi-person 2d and 3d pose detection in natural images","author":"Rogez Gregory","year":"2019","unstructured":"Gregory Rogez , Philippe Weinzaepfel , and Cordelia Schmid . 2019 . Lcr-net: Multi-person 2d and 3d pose detection in natural images . IEEE transactions on pattern analysis and machine intelligence, Vol. 42 , 5 (2019), 1146--1161. Gregory Rogez, Philippe Weinzaepfel, and Cordelia Schmid. 2019. Lcr-net: Multi-person 2d and 3d pose detection in natural images. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 5 (2019), 1146--1161."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.284"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341344"},{"key":"e_1_3_2_2_45_1","volume-title":"Structured prediction of 3d human pose with deep neural networks. arXiv preprint arXiv:1605.05180","author":"Tekin Bugra","year":"2016","unstructured":"Bugra Tekin , Isinsu Katircioglu , Mathieu Salzmann , Vincent Lepetit , and Pascal Fua . 2016a. Structured prediction of 3d human pose with deep neural networks. arXiv preprint arXiv:1605.05180 ( 2016 ). Bugra Tekin, Isinsu Katircioglu, Mathieu Salzmann, Vincent Lepetit, and Pascal Fua. 2016a. Structured prediction of 3d human pose with deep neural networks. arXiv preprint arXiv:1605.05180 (2016)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.113"},{"key":"e_1_3_2_2_47_1","volume-title":"Selfpose: 3d egocentric pose estimation from a headset mounted camera. arXiv preprint arXiv:2011.01519","author":"Tome Denis","year":"2020","unstructured":"Denis Tome , Thiemo Alldieck , Patrick Peluse , Gerard Pons-Moll , Lourdes Agapito , Hernan Badino , and Fernando De la Torre . 2020. Selfpose: 3d egocentric pose estimation from a headset mounted camera. arXiv preprint arXiv:2011.01519 ( 2020 ). Denis Tome, Thiemo Alldieck, Patrick Peluse, Gerard Pons-Moll, Lourdes Agapito, Hernan Badino, and Fernando De la Torre. 2020. Selfpose: 3d egocentric pose estimation from a headset mounted camera. arXiv preprint arXiv:2011.01519 (2020)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00782"},{"key":"e_1_3_2_2_49_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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 , Vol. 30 ( 2017 ). 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, Vol. 30 (2017)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103760"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01130"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"e_1_3_2_2_53_1","volume-title":"Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint arXiv:2001.02908","author":"Xu Mingxing","year":"2020","unstructured":"Mingxing Xu , Wenrui Dai , Chunmiao Liu , Xing Gao , Weiyao Lin , Guo-Jun Qi , and Hongkai Xiong . 2020. Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint arXiv:2001.02908 ( 2020 ). Mingxing Xu, Wenrui Dai, Chunmiao Liu, Xing Gao, Weiyao Lin, Guo-Jun Qi, and Hongkai Xiong. 2020. Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint arXiv:2001.02908 (2020)."},{"key":"e_1_3_2_2_54_1","volume-title":"Mo 2 cap 2: Real-time mobile 3d motion capture with a cap-mounted fisheye camera","author":"Xu Weipeng","year":"2019","unstructured":"Weipeng Xu , Avishek Chatterjee , Michael Zollhoefer , Helge Rhodin , Pascal Fua , Hans-Peter Seidel , and Christian Theobalt . 2019. Mo 2 cap 2: Real-time mobile 3d motion capture with a cap-mounted fisheye camera . IEEE transactions on visualization and computer graphics, Vol. 25 , 5 ( 2019 ), 2093--2101. Weipeng Xu, Avishek Chatterjee, Michael Zollhoefer, Helge Rhodin, Pascal Fua, Hans-Peter Seidel, and Christian Theobalt. 2019. Mo 2 cap 2: Real-time mobile 3d motion capture with a cap-mounted fisheye camera. IEEE transactions on visualization and computer graphics, Vol. 25, 5 (2019), 2093--2101."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"e_1_3_2_2_56_1","volume-title":"Application of VR Technology in Museum Narrative Design with Computer Vision Models. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). 913--916","author":"Zeng Keming","year":"2021","unstructured":"Keming Zeng and Guoyuan Cao . 2021 . Application of VR Technology in Museum Narrative Design with Computer Vision Models. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). 913--916 . https:\/\/doi.org\/10.1109\/ICCMC51019.2021.9418483 10.1109\/ICCMC51019.2021.9418483 Keming Zeng and Guoyuan Cao. 2021. Application of VR Technology in Museum Narrative Design with Computer Vision Models. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). 913--916. https:\/\/doi.org\/10.1109\/ICCMC51019.2021.9418483"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00181"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00243"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.537"},{"key":"e_1_3_2_2_62_1","volume-title":"Monocap: Monocular human motion capture using a cnn coupled with a geometric prior","author":"Zhou Xiaowei","year":"2018","unstructured":"Xiaowei Zhou , Menglong Zhu , Georgios Pavlakos , Spyridon Leonardos , Konstantinos G Derpanis , and Kostas Daniilidis . 2018 . Monocap: Monocular human motion capture using a cnn coupled with a geometric prior . IEEE transactions on pattern analysis and machine intelligence, Vol. 41 , 4 (2018), 901--914. Xiaowei Zhou, Menglong Zhu, Georgios Pavlakos, Spyridon Leonardos, Konstantinos G Derpanis, and Kostas Daniilidis. 2018. Monocap: Monocular human motion capture using a cnn coupled with a geometric prior. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 4 (2018), 901--914."},{"key":"e_1_3_2_2_63_1","volume-title":"MotionBERT: Unified Pretraining for Human Motion Analysis. arXiv preprint arXiv:2210.06551","author":"Zhu Wentao","year":"2022","unstructured":"Wentao Zhu , Xiaoxuan Ma , Zhaoyang Liu , Libin Liu , Wayne Wu , and Yizhou Wang . 2022. MotionBERT: Unified Pretraining for Human Motion Analysis. arXiv preprint arXiv:2210.06551 ( 2022 ). Wentao Zhu, Xiaoxuan Ma, Zhaoyang Liu, Libin Liu, Wayne Wu, and Yizhou Wang. 2022. MotionBERT: Unified Pretraining for Human Motion Analysis. arXiv preprint arXiv:2210.06551 (2022)."}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599312","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:47Z","timestamp":1750178267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":63,"alternative-id":["10.1145\/3580305.3599312","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599312","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}