{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T04:42:55Z","timestamp":1777092175064,"version":"3.51.4"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"DOI":"10.1007\/s11063-026-11835-4","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T07:16:39Z","timestamp":1770362199000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Symbolic Action Representation for Human Motion Understanding"],"prefix":"10.1007","volume":"58","author":[{"given":"Zhen","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"key":"11835_CR1","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"11835_CR2","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211","DOI":"10.1109\/ICCV.2019.00630"},{"key":"11835_CR3","first-page":"12493","volume":"34","author":"M Patrick","year":"2021","unstructured":"Patrick M, Campbell D, Asano Y, Misra I, Metze F, Feichtenhofer C, Vedaldi A, Henriques JF (2021) Keeping your eye on the ball: Trajectory attention in video transformers. Adv Neural Inf Process Syst 34:12493\u201312506","journal-title":"Adv Neural Inf Process Syst"},{"key":"11835_CR4","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? In: Icml, vol. 2, pp. 4\u20136"},{"key":"11835_CR5","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, pp. 7444\u20137452","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"11835_CR6","doi-asserted-by":"crossref","unstructured":"Caetano C, Sena J, Br\u00e9mond F, Dos\u00a0Santos JA, Schwartz WR (2019) SkeleMotion: A new representation of skeleton joint sequences based on motion information for 3d action recognition. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20138","DOI":"10.1109\/AVSS.2019.8909840"},{"issue":"2","key":"11835_CR7","doi-asserted-by":"publisher","first-page":"203007","DOI":"10.3788\/IRLA201847.0203007","volume":"47","author":"P Xiaomin","year":"2018","unstructured":"Xiaomin P, Huijie F, Yandong T (2018) Action recognition method of spatio-temporal feature fusion deep learning network. Infrared and Laser Engineering 47(2):203007\u20130203007","journal-title":"Infrared and Laser Engineering"},{"key":"11835_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219","volume":"208","author":"C Plizzari","year":"2021","unstructured":"Plizzari C, Cannici M, Matteucci M (2021) Skeleton-based action recognition via spatial and temporal transformer networks. Comput Vis Image Underst 208:103219","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"11835_CR9","doi-asserted-by":"publisher","first-page":"28355","DOI":"10.1038\/s41598-025-11073-z","volume":"15","author":"R Ji","year":"2025","unstructured":"Ji R, Lu C, Huang Z, Zhong J (2025) Learning behavior aware features across spaces for improved 3D human motion prediction. Sci Rep 15(1):28355","journal-title":"Sci Rep"},{"key":"11835_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103055","volume":"76","author":"L Song","year":"2021","unstructured":"Song L, Yu G, Yuan J, Liu Z (2021) Human pose estimation and its application to action recognition: A survey. J Vis Commun Image Represent 76:103055","journal-title":"J Vis Commun Image Represent"},{"key":"11835_CR11","doi-asserted-by":"crossref","unstructured":"Kulal S, Mao J, Aiken A, Wu J (2021) Hierarchical motion understanding via motion programs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6568\u20136576","DOI":"10.1109\/CVPR46437.2021.00650"},{"key":"11835_CR12","doi-asserted-by":"crossref","unstructured":"Kulal S, Mao J, Aiken A, Wu J (2022) Programmatic concept learning for human motion description and synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13843\u201313852","DOI":"10.1109\/CVPR52688.2022.01347"},{"issue":"6088","key":"11835_CR13","first-page":"533","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors nature 323(6088):533\u2013536","journal-title":"Learning representations by back-propagating errors nature"},{"issue":"8","key":"11835_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"11835_CR15","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"11835_CR16","doi-asserted-by":"crossref","unstructured":"Nair VS, Sree S, Singh G, Joseph J, Sivaprakasam M (2024) Online action representation using change detection and symbolic programming. In: 2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp. 1\u20136","DOI":"10.1109\/MeMeA60663.2024.10596877"},{"issue":"1\/2","key":"11835_CR17","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2307\/2333009","volume":"41","author":"ES Page","year":"1954","unstructured":"Page ES (1954) Continuous inspection schemes. Biometrika 41(1\/2):100\u2013115","journal-title":"Biometrika"},{"key":"11835_CR18","doi-asserted-by":"crossref","unstructured":"Warner B, Chaffin A, Clavi\u00e9 B, Weller O, Hallstr\u00f6m O, Taghadouini S, Gallagher A, Biswas R, Ladhak F, Aarsen T. et al (2024) Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference. arXiv preprint arXiv:2412.13663","DOI":"10.18653\/v1\/2025.acl-long.127"},{"issue":"2","key":"11835_CR19","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1504\/IJBM.2019.099014","volume":"11","author":"M Ramanathan","year":"2019","unstructured":"Ramanathan M, Yau W-Y, Thalmann NM, Teoh EK (2019) Mutually reinforcing motion-pose framework for pose invariant action recognition. International Journal of Biometrics 11(2):113\u2013147","journal-title":"International Journal of Biometrics"},{"key":"11835_CR20","unstructured":"Jiang J, Cao Y, Song L, Zhang S, Li Y, Xu Z, Wu Q, Gan C, Zhang C, Yu G (2018) Human centric spatio-temporal action localization. In: ActivityNet Workshop on CVPR, vol. 14"},{"key":"11835_CR21","doi-asserted-by":"crossref","unstructured":"Ramanathan M, Yau W-Y, Teoh EK, Thalmann NM (2017) Pose-invariant kinematic features for action recognition. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 292\u2013299","DOI":"10.1109\/APSIPA.2017.8282038"},{"key":"11835_CR22","doi-asserted-by":"crossref","unstructured":"Xu J, Yin S, Peng Y (2025) Human-centric fine-grained action quality assessment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6242\u20136255","DOI":"10.1109\/TPAMI.2025.3556935"},{"key":"11835_CR23","doi-asserted-by":"crossref","unstructured":"Lin K-Y, Zhou J, Zheng W-S (2024) Human-centric transformer for domain adaptive action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 679\u2013696","DOI":"10.1109\/TPAMI.2024.3429387"},{"key":"11835_CR24","doi-asserted-by":"crossref","unstructured":"Cai J, Jiang N, Han X, Jia K, Lu J (2021) JOLO-GCN: Mining joint-centered light-weight information for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2735\u20132744","DOI":"10.1109\/WACV48630.2021.00278"},{"key":"11835_CR25","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhang Z, Yuan C, Li B, Deng Y, Hu W (2021) Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13359\u201313368","DOI":"10.1109\/ICCV48922.2021.01311"},{"issue":"7","key":"11835_CR26","doi-asserted-by":"publisher","first-page":"2097","DOI":"10.1007\/s11263-021-01470-y","volume":"129","author":"P Gupta","year":"2021","unstructured":"Gupta P, Thatipelli A, Aggarwal A, Maheshwari S, Trivedi N, Das S, Sarvadevabhatla RK (2021) Quo vadis, skeleton action recognition? Int J Comput Vision 129(7):2097\u20132112","journal-title":"Int J Comput Vision"},{"issue":"2","key":"11835_CR27","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"Y-F Song","year":"2022","unstructured":"Song Y-F, Zhang Z, Shan C, Wang L (2022) Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans Pattern Anal Mach Intell 45(2):1474\u20131488","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11835_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109231","volume":"136","author":"L Wu","year":"2023","unstructured":"Wu L, Zhang C, Zou Y (2023) Spatiotemporal focus for skeleton-based action recognition. Pattern Recogn 136:109231","journal-title":"Pattern Recogn"},{"key":"11835_CR29","unstructured":"Joze HRV, Shaban A, Iuzzolino ML, Koishida K (2020) MMTM: Multimodal transfer module for CNN fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13289\u201313299"},{"key":"11835_CR30","doi-asserted-by":"crossref","unstructured":"Luvizon DC, Picard D, Tabia H (2018) 2D\/3D pose estimation and action recognition using multitask deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5137\u20135146","DOI":"10.1109\/CVPR.2018.00539"},{"key":"11835_CR31","doi-asserted-by":"crossref","unstructured":"Duan H, Zhao Y, Chen K, Lin D, Dai B (2022) Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978","DOI":"10.1109\/CVPR52688.2022.00298"},{"issue":"2","key":"11835_CR32","first-page":"225","volume":"47","author":"F Zirong","year":"2021","unstructured":"Zirong F, Shengxi W, Xiaoying W, Xingsheng G (2021) Human action recognition using BI-LSTM network based on spatial features. Journal of East China University of Science and Technology 47(2):225\u2013232","journal-title":"Journal of East China University of Science and Technology"},{"key":"11835_CR33","doi-asserted-by":"crossref","unstructured":"Qiu H, Hou B, Ren B, Zhang X (2022) Spatio-temporal tuples transformer for skeleton-based action recognition. arXiv preprint arXiv:2201.02849","DOI":"10.1016\/j.neucom.2022.10.084"},{"key":"11835_CR34","doi-asserted-by":"crossref","unstructured":"Gao Z, Wang P, Lv P, Jiang X, Liu Q, Wang P, Xu M, Li W (2022) Focal and global spatial-temporal transformer for skeleton-based action recognition. In: Proceedings of the Asian Conference on Computer Vision, pp. 382\u2013398","DOI":"10.1007\/978-3-031-26316-3_10"},{"key":"11835_CR35","doi-asserted-by":"crossref","unstructured":"Xin W, Miao Q, Liu Y, Liu R, Pun C-M, Shi C (2023) Skeleton MixFormer: Multivariate topology representation for skeleton-based action recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2211\u20132220","DOI":"10.1145\/3581783.3611900"},{"key":"11835_CR36","doi-asserted-by":"crossref","unstructured":"Qiu J, Wang L (2025) Evolving skeletons: Motion dynamics in action recognition. In: Companion Proceedings of the ACM on Web Conference 2025, pp. 1916\u20131937","DOI":"10.1145\/3701716.3717739"},{"key":"11835_CR37","doi-asserted-by":"crossref","unstructured":"Ray A, Raj A, Kolekar MH (2025) Autoregressive adaptive hypergraph transformer for skeleton-based activity recognition. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 9690\u20139699","DOI":"10.1109\/WACV61041.2025.00938"},{"key":"11835_CR38","unstructured":"Jiang Y-G, Liu J, Roshan\u00a0Zamir A, Toderici G, Laptev I, Shah M, Sukthankar R (2014) THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"11835_CR39","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron F, Escorcia V, Ghanem B, Carlos\u00a0Niebles J (2015) ActivityNet: A large-scale video benchmark for human activity understanding. In: Proceedings of the Ieee Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"11835_CR40","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang S-F (2016) Temporal action localization in untrimmed videos via multi-stage CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"11835_CR41","unstructured":"Wang X, Qing Z, Huang Z, Feng Y, Zhang S, Jiang J, Tang M, Gao C, Sang N (2021) Proposal relation network for temporal action detection. arXiv preprint arXiv:2106.11812"},{"key":"11835_CR42","doi-asserted-by":"crossref","unstructured":"Yeung S, Russakovsky O, Mori G, Fei-Fei L (2016) End-to-end learning of action detection from frame glimpses in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2678\u20132687","DOI":"10.1109\/CVPR.2016.293"},{"key":"11835_CR43","doi-asserted-by":"crossref","unstructured":"Zeng R, Huang W, Tan M, Rong Y, Zhao P, Huang J, Gan C (2019) Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7094\u20137103","DOI":"10.1109\/ICCV.2019.00719"},{"key":"11835_CR44","doi-asserted-by":"crossref","unstructured":"Zhao Y, Xiong Y, Wang L, Wu Z, Tang X, Lin D (2017) Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923","DOI":"10.1109\/ICCV.2017.317"},{"key":"11835_CR45","doi-asserted-by":"crossref","unstructured":"Cheng F, Bertasius G (2022) Tallformer: Temporal action localization with a long-memory transformer. In: European Conference on Computer Vision, pp. 503\u2013521","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"11835_CR46","doi-asserted-by":"crossref","unstructured":"Zhang C-L, Wu J, Li Y (2022) Actionformer: Localizing moments of actions with transformers. In: European Conference on Computer Vision, pp. 492\u2013510","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"11835_CR47","doi-asserted-by":"crossref","unstructured":"Shi D, Zhong Y, Cao Q, Ma L, Li J, Tao D (2023) Tridet: Temporal action detection with relative boundary modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18857\u201318866","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"11835_CR48","doi-asserted-by":"crossref","unstructured":"Paul S, Roy S, Roy-Chowdhury AK (2018) W-TALC: Weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013579","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"11835_CR49","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Lin D, Van\u00a0Gool L (2017) Untrimmednets for weakly supervised action recognition and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4325\u20134334","DOI":"10.1109\/CVPR.2017.678"},{"key":"11835_CR50","doi-asserted-by":"crossref","unstructured":"Nguyen P, Liu T, Prasad G, Han B (2018) Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761","DOI":"10.1109\/CVPR.2018.00706"},{"key":"11835_CR51","unstructured":"Aklilu J, Wang X, Yeung-Levy S (2024) Zero-shot action localization via the confidence of large vision-language models. arXiv preprint arXiv:2410.14340"},{"key":"11835_CR52","doi-asserted-by":"crossref","unstructured":"Zhai Y, Wang L, Tang W, Zhang Q, Yuan J, Hua G (2020) Two-stream consensus network for weakly-supervised temporal action localization. In: European Conference on Computer Vision, pp. 37\u201354","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"11835_CR53","doi-asserted-by":"crossref","unstructured":"Huang D-A, Fei-Fei L, Niebles JC (2016) Connectionist temporal modeling for weakly supervised action labeling. In: European Conference on Computer Vision, pp. 137\u2013153","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"11835_CR54","doi-asserted-by":"crossref","unstructured":"Graves A, Fern\u00e1ndez S, Gomez F, Schmidhuber J (2006) Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376","DOI":"10.1145\/1143844.1143891"},{"key":"11835_CR55","unstructured":"Zhang X, Sheng VS (2024) Neuro-symbolic AI: Explainability, challenges, and future trends. arXiv preprint arXiv:2411.04383"},{"key":"11835_CR56","doi-asserted-by":"crossref","unstructured":"Rong Y, Shiratori T, Joo H (2020) FrankMocap: Fast monocular 3d hand and body motion capture by regression and integration. arXiv preprint arXiv:2008.08324","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"11835_CR57","doi-asserted-by":"crossref","unstructured":"Sabater A, Santos L, Santos-Victor J, Bernardino A, Montesano L, Murillo AC (2021) One-shot action recognition in challenging therapy scenarios. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2777\u20132785","DOI":"10.1109\/CVPRW53098.2021.00312"},{"key":"11835_CR58","unstructured":"Wu Y, Kirillov A, Massa F, Lo W-Y, Girshick R (2019) Detectron2. https:\/\/github.com\/facebookresearch\/detectron2. Accessed: 2023-10-08"},{"key":"11835_CR59","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: Common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"8","key":"11835_CR60","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1021\/ac60214a047","volume":"36","author":"A Savitzky","year":"1964","unstructured":"Savitzky A, Golay MJ (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36(8):1627\u20131639","journal-title":"Anal Chem"},{"key":"11835_CR61","unstructured":"Duarte M (2021) detecta: A Python module to detect events in data. https:\/\/github.com\/demotu\/detecta. Version v0.0.5. http:\/\/doi.org\/10.5281\/zenodo.4598962"},{"issue":"2","key":"11835_CR62","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s11222-006-8450-8","volume":"16","author":"P Fearnhead","year":"2006","unstructured":"Fearnhead P (2006) Exact and efficient Bayesian inference for multiple changepoint problems. Stat Comput 16(2):203\u2013213","journal-title":"Stat Comput"},{"key":"11835_CR63","unstructured":"Hildensia: Bayesian changepoint detection. https:\/\/github.com\/hildensia\/bayesian_changepoint_detection. Accessed on 20 August 2025 (2025)"},{"key":"11835_CR64","doi-asserted-by":"crossref","unstructured":"Zou Y, Yang J, Ceylan D, Zhang J, Perazzi F, Huang J-B (2020) Reducing footskate in human motion reconstruction with ground contact constraints. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 459\u2013468","DOI":"10.1109\/WACV45572.2020.9093329"},{"key":"11835_CR65","doi-asserted-by":"crossref","unstructured":"Pavllo D, Feichtenhofer C, Grangier D, Auli M (2019) 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762","DOI":"10.1109\/CVPR.2019.00794"},{"key":"11835_CR66","doi-asserted-by":"crossref","unstructured":"Ionescu C, Papava D, Olaru V, Sminchisescu C (2013) Human3.6 M: Large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE transactions on pattern analysis and machine intelligence 36(7), 1325\u20131339","DOI":"10.1109\/TPAMI.2013.248"},{"key":"11835_CR67","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (long and Short Papers), pp. 4171\u20134186","DOI":"10.18653\/v1\/N19-1423"},{"key":"11835_CR68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su J, Ahmed M, Lu Y, Pan S, Bo W, Liu Y (2024) RoFormer: Enhanced transformer with rotary position embedding. Neurocomputing 568:127063","journal-title":"Neurocomputing"},{"key":"11835_CR69","doi-asserted-by":"crossref","unstructured":"McNally W, Vats K, Pinto T, Dulhanty C, McPhee J, Wong A (2019) Golfdb: A video database for golf swing sequencing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","DOI":"10.1109\/CVPRW.2019.00311"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-026-11835-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-026-11835-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-026-11835-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T04:10:36Z","timestamp":1777090236000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-026-11835-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":69,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["11835"],"URL":"https:\/\/doi.org\/10.1007\/s11063-026-11835-4","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,6]]},"assertion":[{"value":"16 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online version of this article was revised due to update in the tagging of author affiliation.","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"22"}}