{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:10:41Z","timestamp":1784218241711,"version":"3.55.0"},"reference-count":177,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-03708-9","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T04:03:36Z","timestamp":1739851416000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An Assessment Towards 2D and 3D Human Pose Estimation and its Applications to Activity Recognition: A Review"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1571-392X","authenticated-orcid":false,"given":"Pratishtha","family":"Verma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajeev","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santosh Kumar","family":"Tripathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"issue":"3","key":"3708_CR1","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.3390\/s140304189","volume":"14","author":"X Perez-Sala","year":"2014","unstructured":"Perez-Sala X, Escalera S, Angulo C, Gonzalez J. A survey on model based approaches for 2D and 3D visual human pose recovery. Sensors. 2014;14(3):4189\u2013210.","journal-title":"Sensors"},{"key":"3708_CR2","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jvcir.2015.06.013","volume":"32","author":"Z Liu","year":"2015","unstructured":"Liu Z, Zhu J, Bu J, Chen C. A survey of human pose estimation: the body parts parsing based methods. J Vis Commun Image Represent. 2015;32:10\u20139.","journal-title":"J Vis Commun Image Represent"},{"issue":"3","key":"3708_CR3","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1080\/10798587.2015.1095419","volume":"22","author":"H-B Zhang","year":"2016","unstructured":"Zhang H-B, Lei Q, Zhong B-N, Du J-X, Peng J. A survey on human pose estimation. Intell Autom Soft Comput. 2016;22(3):483\u20139.","journal-title":"Intell Autom Soft Comput"},{"issue":"1","key":"3708_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3603618","volume":"56","author":"C Zheng","year":"2023","unstructured":"Zheng C, Wu W, Chen C, Yang T, Zhu S, Shen J, Kehtarnavaz N, Shah M. Deep learning-based human pose estimation: a survey. ACM Comput Surv. 2023;56(1):1\u201337.","journal-title":"ACM Comput Surv"},{"issue":"6","key":"3708_CR5","doi-asserted-by":"publisher","first-page":"663","DOI":"10.26599\/TST.2018.9010100","volume":"24","author":"Q Dang","year":"2019","unstructured":"Dang Q, Yin J, Wang B, Zheng W. Deep learning based 2D human pose estimation: a survey. Tsinghua Sci Technol. 2019;24(6):663\u201376.","journal-title":"Tsinghua Sci Technol"},{"issue":"2\u20133","key":"3708_CR6","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"104","author":"TB Moeslund","year":"2006","unstructured":"Moeslund TB, Hilton A, Kr\u00fcger V. A survey of advances in vision-based human motion capture and analysis. Comput Vis Image Underst. 2006;104(2\u20133):90\u2013126.","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"3708_CR7","first-page":"13","volume":"40","author":"X Ji","year":"2009","unstructured":"Ji X, Liu H. Advances in view-invariant human motion analysis: a review. IEEE Trans Syst Man Cybern Part C (Appl Rev). 2009;40(1):13\u201324.","journal-title":"IEEE Trans Syst Man Cybern Part C (Appl Rev)"},{"issue":"7","key":"3708_CR8","first-page":"0126","volume":"12","author":"H Jung","year":"2018","unstructured":"Jung H, Song Y-E. Robotic remote control based on human motion via virtual collaboration system: a survey. J Adv Mech Design Syst Manuf. 2018;12(7):0126\u20130126.","journal-title":"J Adv Mech Design Syst Manuf"},{"issue":"3","key":"3708_CR9","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/s11390-017-1742-y","volume":"32","author":"S Xia","year":"2017","unstructured":"Xia S, Gao L, Lai Y-K, Yuan M-Z, Chai J. A survey on human performance capture and animation. J Comput Sci Technol. 2017;32(3):536\u201354.","journal-title":"J Comput Sci Technol"},{"key":"3708_CR10","doi-asserted-by":"publisher","first-page":"144","DOI":"10.25046\/aj050418","volume":"5","author":"V-h Le","year":"2020","unstructured":"Le V-h, Nguyen H-c. A survey on 3D hand skeleton and pose estimation by convolutional neural network. Adv Sci Technol Eng Syst J. 2020;5:144\u201359.","journal-title":"Adv Sci Technol Eng Syst J"},{"issue":"1","key":"3708_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-012-9356-9","volume":"43","author":"SS Rautaray","year":"2015","unstructured":"Rautaray SS, Agrawal A. Vision based hand gesture recognition for human computer interaction: a survey. Artif Intell Rev. 2015;43(1):1\u201354.","journal-title":"Artif Intell Rev"},{"key":"3708_CR12","unstructured":"Noroozi F, Kaminska D, Corneanu C, Sapinski T, Escalera S, Anbarjafari G. Survey on emotional body gesture recognition. IEEE Trans Affect Comput. 2018."},{"issue":"6","key":"3708_CR13","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe R. A survey on vision-based human action recognition. Image Vis Comput. 2010;28(6):976\u2013990.","journal-title":"Image Vis Comput"},{"issue":"3","key":"3708_CR14","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s00371-015-1066-2","volume":"32","author":"DD Dawn","year":"2016","unstructured":"Dawn DD, Shaikh SH. A comprehensive survey of human action recognition with spatio-temporal interest point (STIP) detector. Vis Comput. 2016;32(3):289\u2013306.","journal-title":"Vis Comput"},{"key":"3708_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","volume":"119","author":"J Wang","year":"2019","unstructured":"Wang J, Chen Y, Hao S, Peng X, Hu L. Deep learning for sensor-based activity recognition: a survey. Pattern Recogn Lett. 2019;119:3\u201311.","journal-title":"Pattern Recogn Lett"},{"issue":"1","key":"3708_CR16","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aa525f","volume":"14","author":"T Kawase","year":"2017","unstructured":"Kawase T, Sakurada T, Koike Y, Kansaku K. A hybrid BMI-based exoskeleton for paresis: EMG control for assisting arm movements. J Neural Eng. 2017;14(1): 016015.","journal-title":"J Neural Eng"},{"key":"3708_CR17","doi-asserted-by":"crossref","unstructured":"Dentamaro V, Impedovo D, Pirlo G. Fall detection by human pose estimation and kinematic theory. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE; 2021. p. 2328\u201335.","DOI":"10.1109\/ICPR48806.2021.9413331"},{"issue":"2","key":"3708_CR18","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1007\/s13369-022-06684-x","volume":"48","author":"AR Inturi","year":"2023","unstructured":"Inturi AR, Manikandan V, Garrapally V. A novel vision-based fall detection scheme using keypoints of human skeleton with long short-term memory network. Arab J Sci Eng. 2023;48(2):1143\u201355.","journal-title":"Arab J Sci Eng"},{"key":"3708_CR19","doi-asserted-by":"crossref","unstructured":"Song X, Mann K, Allison E, Yoon S-C, Hila H, Muller A, Gieder C. A quadcopter controlled by brain concentration and eye blink. In: 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB). IEEE; 2016. p. 1\u20134.","DOI":"10.1109\/SPMB.2016.7846875"},{"issue":"2","key":"3708_CR20","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/s11517-018-1868-2","volume":"57","author":"D Tan","year":"2019","unstructured":"Tan D, Pua Y-H, Balakrishnan S, Scully A, Bower KJ, Prakash KM, Tan E-K, Chew J-S, Poh E, Tan S-B, et al. Automated analysis of gait and modified timed up and go using the microsoft kinect in people with Parkinson\u2019s disease: associations with physical outcome measures. Med Biol Eng Comput. 2019;57(2):369\u201377.","journal-title":"Med Biol Eng Comput"},{"key":"3708_CR21","doi-asserted-by":"crossref","unstructured":"Zhou Y, Huang H, Yuan S, Zou H, Xie L, Yang J. MetaFi++: WiFi-enabled transformer-based human pose estimation for metaverse avatar simulation. IEEE Internet Things J. 2023.","DOI":"10.1109\/JIOT.2023.3262940"},{"issue":"11","key":"3708_CR22","doi-asserted-by":"publisher","first-page":"15361","DOI":"10.1007\/s12652-019-01554-1","volume":"14","author":"AA Minhas","year":"2023","unstructured":"Minhas AA, Jabbar S, Farhan M, Najamul Islam M. Smart methodology for safe life on roads with active drivers based on real-time risk and behavioral monitoring. J Ambient Intell Humaniz Comput. 2023;14(11):15361\u201373.","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"3708_CR23","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.cviu.2019.01.002","volume":"180","author":"M Ariz","year":"2019","unstructured":"Ariz M, Villanueva A, Cabeza R. Robust and accurate 2D-tracking-based 3D positioning method: application to head pose estimation. Comput Vis Image Underst. 2019;180:13\u201322.","journal-title":"Comput Vis Image Underst"},{"key":"3708_CR24","doi-asserted-by":"crossref","unstructured":"Kusuma S, Udayan JD, Sachdeva A. Driver distraction detection using deep learning and computer vision. In: 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), vol. 1. IEEE; 2019. p. 289\u201392.","DOI":"10.1109\/ICICICT46008.2019.8993260"},{"issue":"2","key":"3708_CR25","doi-asserted-by":"publisher","first-page":"289","DOI":"10.4271\/2016-01-1526","volume":"4","author":"DV McGehee","year":"2016","unstructured":"McGehee DV, Roe CA, Boyle LN, Wu Y, Ebe K, Foley J, Angell L. The wagging foot of uncertainty: data collection and reduction methods for examining foot pedal behavior in naturalistic driving. SAE Int J Transp Saf. 2016;4(2):289\u201394.","journal-title":"SAE Int J Transp Saf"},{"issue":"5","key":"3708_CR26","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/TCSVT.2017.2655624","volume":"28","author":"H-C Shih","year":"2017","unstructured":"Shih H-C. A survey of content-aware video analysis for sports. IEEE Trans Circuits Syst Video Technol. 2017;28(5):1212\u201331.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3708_CR27","doi-asserted-by":"crossref","unstructured":"Kulkarni KM, Shenoy S. Table tennis stroke recognition using two-dimensional human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, p. 4576\u201384.","DOI":"10.1109\/CVPRW53098.2021.00515"},{"key":"3708_CR28","doi-asserted-by":"crossref","unstructured":"Gupta T, Nunavath V, Roy S. CrowdVAS-Net: a deep-CNN based framework to detect abnormal crowd-motion behavior in videos for predicting crowd disaster. In: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE; 2019. p. 2877\u201382.","DOI":"10.1109\/SMC.2019.8914152"},{"key":"3708_CR29","unstructured":"Roggio F, Cappuccio G, Palma A, Musumeci G. Advancements in non-invasive screening techniques for human posture and musculoskeletal disorders. 2024."},{"issue":"1","key":"3708_CR30","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1186\/s13063-019-3468-3","volume":"20","author":"M Gerber","year":"2019","unstructured":"Gerber M, Beck J, Brand S, Cody R, Donath L, Eckert A, Faude O, Fischer X, Hatzinger M, Holsboer-Trachsler E, et al. The impact of lifestyle physical activity counselling in in-patients with major depressive disorders on physical activity, cardiorespiratory fitness, depression, and cardiovascular health risk markers: study protocol for a randomized controlled trial. Trials. 2019;20(1):367.","journal-title":"Trials"},{"issue":"24","key":"3708_CR31","doi-asserted-by":"publisher","first-page":"5451","DOI":"10.3390\/s19245451","volume":"19","author":"J Klenk","year":"2019","unstructured":"Klenk J, Wekenmann S, Schwickert L, Lindemann U, Becker C, Rapp K. Change of objectively-measured physical activity during geriatric rehabilitation. Sensors. 2019;19(24):5451.","journal-title":"Sensors"},{"key":"3708_CR32","doi-asserted-by":"crossref","unstructured":"Liu S, Ostadabbas S. Seeing under the cover: a physics guided learning approach for in-bed pose estimation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2019. p. 236\u201345.","DOI":"10.1007\/978-3-030-32239-7_27"},{"issue":"6","key":"3708_CR33","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1109\/JBHI.2019.2895855","volume":"23","author":"D Ahmedt-Aristizabal","year":"2019","unstructured":"Ahmedt-Aristizabal D, Denman S, Nguyen K, Sridharan S, Dionisio S, Fookes C. Understanding patients\u2019 behavior: vision-based analysis of seizure disorders. IEEE J Biomed Health Inform. 2019;23(6):2583\u201391.","journal-title":"IEEE J Biomed Health Inform"},{"key":"3708_CR34","doi-asserted-by":"crossref","unstructured":"Takahashi K, Mikami D, Isogawa M, Kimata H. Human pose as calibration pattern; 3D human pose estimation with multiple unsynchronized and uncalibrated cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, p. 1775\u201382.","DOI":"10.1109\/CVPRW.2018.00230"},{"key":"3708_CR35","doi-asserted-by":"crossref","unstructured":"Stoll C, Hasler N, Gall J, Seidel H-P, Theobalt C. Fast articulated motion tracking using a sums of gaussians body model. In: 2011 International Conference on Computer Vision. IEEE; 2011. p. 951\u20138.","DOI":"10.1109\/ICCV.2011.6126338"},{"key":"3708_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127125","volume":"570","author":"M Xu","year":"2024","unstructured":"Xu M, Wang Y, Xu B, Zhang J, Ren J, Huang Z, Poslad S, Xu P. A critical analysis of image-based camera pose estimation techniques. Neurocomputing. 2024;570: 127125.","journal-title":"Neurocomputing"},{"key":"3708_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.imavis.2017.02.002","volume":"61","author":"W Zhang","year":"2017","unstructured":"Zhang W, Liu Z, Zhou L, Leung H, Chan AB. Martial arts, dancing and sports dataset: a challenging stereo and multi-view dataset for 3D human pose estimation. Image Vis Comput. 2017;61:22\u201339.","journal-title":"Image Vis Comput"},{"key":"3708_CR38","doi-asserted-by":"crossref","unstructured":"Obdr\u017e\u00e1lek \u0160, Kurillo G, Ofli F, Bajcsy R, Seto E, Jimison H, Pavel M. Accuracy and robustness of kinect pose estimation in the context of coaching of elderly population. In: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE; 2012. p. 1188\u201393.","DOI":"10.1109\/EMBC.2012.6346149"},{"issue":"4","key":"3708_CR39","doi-asserted-by":"publisher","first-page":"305","DOI":"10.5573\/IEIESPC.2018.7.4.305","volume":"7","author":"M Shin","year":"2018","unstructured":"Shin M, Jang J, Paik J. Calibration of a surveillance camera using a pedestrian homology-based rectangular model. IEIE Trans Smart Process Comput. 2018;7(4):305\u201312.","journal-title":"IEIE Trans Smart Process Comput"},{"key":"3708_CR40","doi-asserted-by":"crossref","unstructured":"Pavlakos G, Zhou X, Derpanis KG, Daniilidis K. Harvesting multiple views for marker-less 3D human pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, p. 6988\u20137.","DOI":"10.1109\/CVPR.2017.138"},{"key":"3708_CR41","doi-asserted-by":"crossref","unstructured":"Simon T, Joo H, Matthews I, Sheikh Y. Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, p. 1145\u201353.","DOI":"10.1109\/CVPR.2017.494"},{"key":"3708_CR42","doi-asserted-by":"crossref","unstructured":"Rhodin H, Sp\u00f6rri J, Katircioglu I, Constantin V, Meyer F, M\u00fcller E, Salzmann M, Fua P. Learning monocular 3D human pose estimation from multi-view images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, p. 8437\u201346.","DOI":"10.1109\/CVPR.2018.00880"},{"key":"3708_CR43","doi-asserted-by":"crossref","unstructured":"Heda L, Sahare P. Performance evaluation of yolov3, yolov4 and yolov5 for real-time human detection. In: 2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS). IEEE; 2023. p. 1\u20136.","DOI":"10.1109\/PCEMS58491.2023.10136081"},{"key":"3708_CR44","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J. Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, p. 5693\u2013703.","DOI":"10.1109\/CVPR.2019.00584"},{"issue":"7","key":"3708_CR45","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1109\/TCSVT.2017.2672686","volume":"28","author":"S Wu","year":"2017","unstructured":"Wu S, Wong H-S, Wang S. Variant semiboost for improving human detection in application scenes. IEEE Trans Circuits Syst Video Technol. 2017;28(7):1595\u2013608.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3708_CR46","doi-asserted-by":"crossref","unstructured":"Aguilar WG, Luna MA, Moya JF, Abad V, Ruiz H, Parra H, Lopez W. Cascade classifiers and saliency maps based people detection. In: International Conference on Augmented Reality, Virtual Reality and Computer Graphics. Springer; 2017. p. 501\u201310.","DOI":"10.1007\/978-3-319-60928-7_42"},{"key":"3708_CR47","doi-asserted-by":"crossref","unstructured":"Gajjar V, Khandhediya Y, Gurnani A. Human detection and tracking for video surveillance: a cognitive science approach. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, p. 2805\u20139.","DOI":"10.1109\/ICCVW.2017.330"},{"key":"3708_CR48","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2017, p. 2961\u20139.","DOI":"10.1109\/ICCV.2017.322"},{"key":"3708_CR49","unstructured":"Liu Y, Liu L, Rezatofighi H, Do T-T, Shi Q, Reid I. Learning pairwise relationship for multi-object detection in crowded scenes. 2019. arXiv preprint arXiv:1901.03796."},{"key":"3708_CR50","doi-asserted-by":"crossref","unstructured":"Mashak SV, Hosseini B, Mokji M, Abu-Bakar SAR. Background subtraction for object detection under varying environments. In: 2010 International Conference of Soft Computing and Pattern Recognition, 2010, p. 123\u20136.","DOI":"10.1109\/SOCPAR.2010.5685960"},{"key":"3708_CR51","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1016\/j.proeng.2012.01.139","volume":"29","author":"R Zhang","year":"2012","unstructured":"Zhang R, Ding J. Object tracking and detecting based on adaptive background subtraction. Procedia Eng. 2012;29:1351\u20135.","journal-title":"Procedia Eng"},{"key":"3708_CR52","doi-asserted-by":"crossref","unstructured":"Guo J, Wang J, Bai R, Zhang Y, Li Y. A new moving object detection method based on frame-difference and background subtraction. In: IOP Conference Series: Materials Science and Engineering, vol. 242. IOP Publishing; 2017. p. 012115.","DOI":"10.1088\/1757-899X\/242\/1\/012115"},{"key":"3708_CR53","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.patcog.2017.09.040","volume":"76","author":"M Babaee","year":"2018","unstructured":"Babaee M, Dinh DT, Rigoll G. A deep convolutional neural network for video sequence background subtraction. Pattern Recogn. 2018;76:635\u201349.","journal-title":"Pattern Recogn"},{"key":"3708_CR54","doi-asserted-by":"crossref","unstructured":"Ma QDY, Ma Z, Ji C, Yin K, Zhu T, Bian C. Artificial object edge detection based on enhanced canny algorithm for high-speed railway apparatus identification. In: 2017 10th International Congress on Image and Signal Processing. BioMedical Engineering and Informatics (CISP-BMEI); 2017. p. 1\u20136.","DOI":"10.1109\/CISP-BMEI.2017.8301995"},{"key":"3708_CR55","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.procs.2018.04.209","volume":"131","author":"K Zhang","year":"2018","unstructured":"Zhang K, Zhang Y, Wang P, Tian Y, Yang J. An improved Sobel edge algorithm and FPGA implementation. Procedia Comput Sci. 2018;131:243\u20138.","journal-title":"Procedia Comput Sci"},{"issue":"C","key":"3708_CR56","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1016\/j.neucom.2017.11.046","volume":"275","author":"C Zhang","year":"2018","unstructured":"Zhang C, Yan J, Li C, Bie R. Contour detection via stacking random forest learning. Neurocomputing. 2018;275(C):2702\u201315. https:\/\/doi.org\/10.1016\/j.neucom.2017.11.046.","journal-title":"Neurocomputing"},{"issue":"11","key":"3708_CR57","doi-asserted-by":"publisher","first-page":"13075","DOI":"10.1007\/s11042-017-4933-1","volume":"77","author":"SK Choudhury","year":"2018","unstructured":"Choudhury SK, Sa PK, Padhy RP, Sharma S, Bakshi S. Improved pedestrian detection using motion segmentation and silhouette orientation. Multimed Tools Appl. 2018;77(11):13075\u2013114.","journal-title":"Multimed Tools Appl"},{"key":"3708_CR58","doi-asserted-by":"crossref","unstructured":"Ebadi F, Norouzi M. Road terrain detection and classification algorithm based on the color feature extraction. In: 2017 Artificial Intelligence and Robotics (IRANOPEN), 2017, p. 139\u201346.","DOI":"10.1109\/RIOS.2017.7956457"},{"key":"3708_CR59","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol 1. IEEE; 2005. p. 886\u201393.","DOI":"10.1109\/CVPR.2005.177"},{"key":"3708_CR60","doi-asserted-by":"crossref","unstructured":"Lowe DG. Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol 2. IEEE; 1999. p. 1150\u20137.","DOI":"10.1109\/ICCV.1999.790410"},{"key":"3708_CR61","doi-asserted-by":"crossref","unstructured":"Damen D, Bunnun P, Calway A, Mayol-Cuevas WW. Real-time learning and detection of 3D texture-less objects: a scalable approach. In: BMVC, 2012.","DOI":"10.5244\/C.26.23"},{"key":"3708_CR62","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.robot.2017.06.003","volume":"95","author":"H Zhang","year":"2017","unstructured":"Zhang H, Cao Q. Texture-less object detection and 6D pose estimation in RGB-D images. Robot Auton Syst. 2017;95:64\u201379.","journal-title":"Robot Auton Syst"},{"key":"3708_CR63","doi-asserted-by":"crossref","unstructured":"Wang S, Ai H, Yamashita T, Lao S. Combined top-down\/bottom-up human articulated pose estimation using AdaBoost learning. In: 2010 20th International Conference on Pattern Recognition. IEEE; 2010. p. 3670\u20133.","DOI":"10.1109\/ICPR.2010.895"},{"key":"3708_CR64","doi-asserted-by":"crossref","unstructured":"Yang J, Liang W, Jia Y. Face pose estimation with combined 2D and 3D hog features. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). IEEE; 2012. p. 2492\u20135.","DOI":"10.1109\/ICIG.2013.133"},{"key":"3708_CR65","unstructured":"Bhuvaneswari K, Rauf HA. Edgelet based human detection and tracking by combined segmentation and soft decision. In: 2009 International Conference on Control, Automation, Communication and Energy Conservation. IEEE; 2009. p. 1\u20136."},{"key":"3708_CR66","doi-asserted-by":"crossref","unstructured":"Wu B, Nevatia R. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: Tenth IEEE International Conference on Computer Vision (ICCV\u201905) Volume 1. IEEE; 2005. p. 90\u20137.","DOI":"10.1109\/ICCV.2005.74"},{"key":"3708_CR67","doi-asserted-by":"crossref","unstructured":"Sabzmeydani P, Mori G. Detecting pedestrians by learning shapelet features. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2007. p. 1\u20138.","DOI":"10.1109\/CVPR.2007.383134"},{"issue":"11","key":"3708_CR68","first-page":"2043","volume":"26","author":"S Chen","year":"2015","unstructured":"Chen S, Liang L, Liang W, Foroosh H. 3D pose tracking with multitemplate warping and sift correspondences. IEEE Trans Circuits Syst Video Technol. 2015;26(11):2043\u201355.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3708_CR69","doi-asserted-by":"crossref","unstructured":"Pfister T, Charles J, Zisserman A. Flowing convnets for human pose estimation in videos. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, p. 1913\u201321.","DOI":"10.1109\/ICCV.2015.222"},{"key":"3708_CR70","unstructured":"Ding Y, Wang C, Huang H, Liu J, Wang J, Wang L. Frame-recurrent video inpainting by robust optical flow inference. 2019. arXiv preprint arXiv:1905.02882."},{"key":"3708_CR71","doi-asserted-by":"crossref","unstructured":"Sminchisescu C, Triggs B. Covariance scaled sampling for monocular 3D body tracking. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol 1. IEEE; 2001.","DOI":"10.1109\/CVPR.2001.990509"},{"key":"3708_CR72","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.cviu.2017.12.005","volume":"169","author":"Y Kawana","year":"2018","unstructured":"Kawana Y, Ukita N, Huang J-B, Yang M-H. Ensemble convolutional neural networks for pose estimation. Comput Vis Image Underst. 2018;169:62\u201374.","journal-title":"Comput Vis Image Underst"},{"key":"3708_CR73","doi-asserted-by":"crossref","unstructured":"Jain A, Tompson J, LeCun Y, Bregler C. MoDeep: a deep learning framework using motion features for human pose estimation. In: Asian Conference on Computer Vision. Springer; 2014. p. 302\u201315.","DOI":"10.1007\/978-3-319-16808-1_21"},{"key":"3708_CR74","doi-asserted-by":"crossref","unstructured":"Lehrmann AM, Gehler PV, Nowozin S. A non-parametric Bayesian network prior of human pose. In: Proceedings of the IEEE International Conference on Computer Vision, 2013, p. 1281\u20138.","DOI":"10.1109\/ICCV.2013.162"},{"issue":"4","key":"3708_CR75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta D, Sridhar S, Sotnychenko O, Rhodin H, Shafiei M, Seidel H-P, Xu W, Casas D, Theobalt C. VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans Graph (TOG). 2017;36(4):1\u201314.","journal-title":"ACM Trans Graph (TOG)"},{"issue":"10","key":"3708_CR76","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1109\/TPAMI.2015.2509986","volume":"38","author":"V Belagiannis","year":"2015","unstructured":"Belagiannis V, Amin S, Andriluka M, Schiele B, Navab N, Ilic S. 3D pictorial structures revisited: multiple human pose estimation. IEEE Trans Pattern Anal Mach Intell. 2015;38(10):1929\u201342.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3708_CR77","doi-asserted-by":"crossref","unstructured":"Zuffi S, Freifeld O, Black MJ. From pictorial structures to deformable structures. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2012. p. 3546\u201353.","DOI":"10.1109\/CVPR.2012.6248098"},{"key":"3708_CR78","unstructured":"Chen X, Yuille AL. Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in Neural Information Processing Systems, 2014, p. 1736\u201344."},{"issue":"6","key":"3708_CR79","doi-asserted-by":"publisher","first-page":"5060","DOI":"10.1109\/TIE.2017.2739691","volume":"65","author":"J Yu","year":"2017","unstructured":"Yu J, Hong C, Rui Y, Tao D. Multitask autoencoder model for recovering human poses. IEEE Trans Ind Electron. 2017;65(6):5060\u20138.","journal-title":"IEEE Trans Ind Electron"},{"issue":"1","key":"3708_CR80","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1006\/cviu.1995.1004","volume":"61","author":"TF Cootes","year":"1995","unstructured":"Cootes TF, Taylor CJ, Cooper DH, Graham J. Active shape models-their training and application. Comput Vis Image Underst. 1995;61(1):38\u201359.","journal-title":"Comput Vis Image Underst"},{"key":"3708_CR81","doi-asserted-by":"crossref","unstructured":"Sidenbladh H, De\u00a0la Torre F, Black MJ. A framework for modeling the appearance of 3D articulated figures. In: Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580). IEEE; 2000. p. 368\u201375.","DOI":"10.1109\/AFGR.2000.840661"},{"key":"3708_CR82","doi-asserted-by":"crossref","unstructured":"Rhodin H, Robertini N, Casas D, Richardt C, Seidel H-P, Theobalt C. General automatic human shape and motion capture using volumetric contour cues. In: European Conference on Computer Vision. Springer; 2016. p. 509\u201326.","DOI":"10.1007\/978-3-319-46454-1_31"},{"issue":"1","key":"3708_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3203197","volume":"1","author":"J Delanoy","year":"2018","unstructured":"Delanoy J, Aubry M, Isola P, Efros AA, Bousseau A. 3D sketching using multi-view deep volumetric prediction. Proc ACM Comput Graph Interact Tech. 2018;1(1):1\u201322.","journal-title":"Proc ACM Comput Graph Interact Tech"},{"issue":"11","key":"3708_CR84","doi-asserted-by":"publisher","first-page":"2720","DOI":"10.1109\/TPAMI.2013.47","volume":"35","author":"Y Liu","year":"2013","unstructured":"Liu Y, Gall J, Stoll C, Dai Q, Seidel H-P, Theobalt C. Markerless motion capture of multiple characters using multiview image segmentation. IEEE Trans Pattern Anal Mach Intell. 2013;35(11):2720\u201335.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3708_CR85","doi-asserted-by":"crossref","unstructured":"Wei X, Chai J. VideoMocap: modeling physically realistic human motion from monocular video sequences. In: ACM SIGGRAPH 2010 Papers, 2010, p. 1\u201310.","DOI":"10.1145\/1833349.1778779"},{"key":"3708_CR86","doi-asserted-by":"crossref","unstructured":"Alldieck T, Magnor M, Xu W, Theobalt C, Pons-Moll G. Video based reconstruction of 3D people models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, p. 8387\u201397.","DOI":"10.1109\/CVPR.2018.00875"},{"issue":"6","key":"3708_CR87","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1177\/0278364903022006003","volume":"22","author":"C Sminchisescu","year":"2003","unstructured":"Sminchisescu C, Triggs B. Estimating articulated human motion with covariance scaled sampling. Int J Robot Res. 2003;22(6):371\u201391.","journal-title":"Int J Robot Res"},{"key":"3708_CR88","unstructured":"Cuzzolin F, Gong W. A belief-theoretical approach to example-based pose estimation. IEEE Trans Fuzzy Syst. 2012. (under revision)."},{"key":"3708_CR89","doi-asserted-by":"crossref","unstructured":"Sminchisescu C, Kanaujia A, Li Z, Metaxas D. Discriminative density propagation for 3D human motion estimation. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol 1. IEEE; 2005. p. 390\u20137.","DOI":"10.1109\/CVPR.2005.132"},{"key":"3708_CR90","unstructured":"Rosales R, Sclaroff S. Learning body pose via specialized maps. In: Advances in neural information processing systems. 2002. p. 1263\u201370."},{"key":"3708_CR91","doi-asserted-by":"crossref","unstructured":"Shakhnarovich G, Viola P, Darrell T. Fast pose estimation with parameter-sensitive hashing. In: Null. IEEE; 2003. p. 750.","DOI":"10.1109\/ICCV.2003.1238424"},{"key":"3708_CR92","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.cviu.2018.03.007","volume":"172","author":"U Iqbal","year":"2018","unstructured":"Iqbal U, Doering A, Yasin H, Kr\u00fcger B, Weber A, Gall J. A dual-source approach for 3D human pose estimation from single images. Comput Vis Image Underst. 2018;172:37\u201349.","journal-title":"Comput Vis Image Underst"},{"key":"3708_CR93","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neunet.2017.02.005","volume":"92","author":"P Witoonchart","year":"2017","unstructured":"Witoonchart P, Chongstitvatana P. Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation. Neural Netw. 2017;92:39\u201346.","journal-title":"Neural Netw"},{"key":"3708_CR94","doi-asserted-by":"crossref","unstructured":"Li S, Zhang W, Chan AB. Maximum-margin structured learning with deep networks for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, p. 2848\u201356.","DOI":"10.1109\/ICCV.2015.326"},{"issue":"1","key":"3708_CR95","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TPAMI.2006.21","volume":"28","author":"A Agarwal","year":"2005","unstructured":"Agarwal A, Triggs B. Recovering 3D human pose from monocular images. IEEE Trans Pattern Anal Mach Intell. 2005;28(1):44\u201358.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3708_CR96","doi-asserted-by":"crossref","unstructured":"Agarwal A, Triggs B. 3D human pose from silhouettes by relevance vector regression. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, vol 2. IEEE; 2004.","DOI":"10.1109\/CVPR.2004.1315258"},{"key":"3708_CR97","doi-asserted-by":"crossref","unstructured":"Verma P, Aggrawal V, Maggu J. Fexr. A-DCNN: facial emotion recognition with attention mechanism using deep convolution neural network. In: Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing, 2022, p. 196\u2013203.","DOI":"10.1145\/3549206.3549243"},{"key":"3708_CR98","doi-asserted-by":"crossref","unstructured":"Tekin B, Katircioglu I, Salzmann M, Lepetit V, Fua P. Structured prediction of 3d human pose with deep neural networks. 2016. arXiv preprint arXiv:1605.05180.","DOI":"10.5244\/C.30.130"},{"key":"3708_CR99","doi-asserted-by":"crossref","unstructured":"Xu J, Yu Z, Ni B, Yang J, Yang X, Zhang W. Deep kinematics analysis for monocular 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, p. 899\u2013908.","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"3708_CR100","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhu M, Leonardos S, Derpanis KG, Daniilidis K. Sparseness meets deepness: 3D human pose estimation from monocular video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, p. 4966\u201375.","DOI":"10.1109\/CVPR.2016.537"},{"key":"3708_CR101","doi-asserted-by":"crossref","unstructured":"Liu W, Bao Q, Sun Y, Mei T. Recent advances in monocular 2D and 3D human pose estimation: a deep learning perspective. 2021. arXiv preprint arXiv:2104.11536.","DOI":"10.1145\/3524497"},{"key":"3708_CR102","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C. DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, p. 1653\u201360.","DOI":"10.1109\/CVPR.2014.214"},{"key":"3708_CR103","doi-asserted-by":"crossref","unstructured":"Sun X, Shang J, Liang S, Wei Y. Compositional human pose regression. In: Proceedings of the IEEE International Conference on Computer Vision, 2017, p. 2602\u201311.","DOI":"10.1109\/ICCV.2017.284"},{"key":"3708_CR104","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.cag.2019.09.002","volume":"85","author":"DC Luvizon","year":"2019","unstructured":"Luvizon DC, Tabia H, Picard D. Human pose regression by combining indirect part detection and contextual information. Comput Graph. 2019;85:15\u201322.","journal-title":"Comput Graph"},{"key":"3708_CR105","doi-asserted-by":"crossref","unstructured":"Zhao L, Peng X, Tian Y, Kapadia M, Metaxas DN. Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, p. 3425\u201335.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"3708_CR106","unstructured":"Mao W, Ge Y, Shen C, Tian Z, Wang X, Wang Z. TFPose: direct human pose estimation with transformers. 2021. arXiv preprint arXiv:2103.15320."},{"key":"3708_CR107","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J. Stacked hourglass networks for human pose estimation. In: European Conference on Computer Vision. Springer; 2016. p. 483\u201399.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"3708_CR108","doi-asserted-by":"crossref","unstructured":"Chou C-J, Chien J-T, Chen H-T. Self adversarial training for human pose estimation. In: 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE; 2018. p. 17\u201330.","DOI":"10.23919\/APSIPA.2018.8659538"},{"key":"3708_CR109","doi-asserted-by":"crossref","unstructured":"Nibali A, He Z, Morgan S, Prendergast L. 3D human pose estimation with 2D marginal heatmaps. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE; 2019. p. 1477\u201385.","DOI":"10.1109\/WACV.2019.00162"},{"key":"3708_CR110","doi-asserted-by":"crossref","unstructured":"Martinez J, Hossain R, Romero J, Little JJ. A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 2017, p. 2640\u20139.","DOI":"10.1109\/ICCV.2017.288"},{"key":"3708_CR111","doi-asserted-by":"crossref","unstructured":"Ram\u00edrez I, Cuesta-Infante A, Schiavi E, Pantrigo JJ. Bayesian capsule networks for 3D human pose estimation from single 2D images. Neurocomputing. 2019.","DOI":"10.1016\/j.neucom.2019.09.101"},{"issue":"9","key":"3708_CR112","first-page":"261","volume":"3","author":"P Amitesh","year":"2017","unstructured":"Amitesh P, Verma P. Human detection using feature fusion set of LBP and HOG. Int J Future Revolut Comput Sci Commun Eng. 2017;3(9):261\u20135.","journal-title":"Int J Future Revolut Comput Sci Commun Eng"},{"key":"3708_CR113","doi-asserted-by":"crossref","unstructured":"F\u00fcrst M, Gupta ST, Schuster R, Wasenm\u00fcller O, Stricker D. HPERL: 3D human pose estimation from RGB and LiDAR. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE; 2021. p. 7321\u20137.","DOI":"10.1109\/ICPR48806.2021.9412785"},{"key":"3708_CR114","doi-asserted-by":"crossref","unstructured":"Mehraban S, Adeli V, Taati B. MotionAGFormer: enhancing 3D human pose estimation with a transformer-GCNFormer network. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, p. 6920\u201330.","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"3708_CR115","doi-asserted-by":"crossref","unstructured":"Einfalt M, Ludwig K, Lienhart R. Uplift and upsample: efficient 3D human pose estimation with uplifting transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, p. 2903\u201313.","DOI":"10.1109\/WACV56688.2023.00292"},{"issue":"6","key":"3708_CR116","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1080\/21681163.2021.1902400","volume":"9","author":"P Verma","year":"2021","unstructured":"Verma P, Srivastava R. Reconsideration of multi-stage deep network for human pose estimation. Comput Methods Biomech Biomed Eng Imaging Vis. 2021;9(6):600\u201312.","journal-title":"Comput Methods Biomech Biomed Eng Imaging Vis"},{"key":"3708_CR117","doi-asserted-by":"crossref","unstructured":"Chai W, Jiang Z, Hwang J-N, Wang G. Global adaptation meets local generalization: unsupervised domain adaptation for 3D human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, p. 14655\u201365.","DOI":"10.1109\/ICCV51070.2023.01347"},{"key":"3708_CR118","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109631","volume":"141","author":"W Li","year":"2023","unstructured":"Li W, Liu H, Tang H, Wang P. Multi-hypothesis representation learning for transformer-based 3D human pose estimation. Pattern Recogn. 2023;141: 109631.","journal-title":"Pattern Recogn"},{"key":"3708_CR119","doi-asserted-by":"crossref","unstructured":"Shan W, Liu Z, Zhang X, Wang Z, Han K, Wang S, Ma S, Gao W. Diffusion-based 3D human pose estimation with multi-hypothesis aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, p. 14761\u201371.","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"3708_CR120","doi-asserted-by":"crossref","unstructured":"Tang Z, Qiu Z, Hao Y, Hong R, Yao T. 3D human pose estimation with spatio-temporal criss-cross attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, p. 4790\u20139.","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"3708_CR121","doi-asserted-by":"crossref","unstructured":"Zhao Q, Zheng C, Liu M, Wang P, Chen C. PoseFormerV2: exploring frequency domain for efficient and robust 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, p. 8877\u201386.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"3708_CR122","unstructured":"A guide to convolutional neural network."},{"key":"3708_CR123","doi-asserted-by":"crossref","unstructured":"Flitti F, Bennamoun M, Huynh DQ, Owens RA. Probabilistic human pose recovery from 2D images. In: 2010 IEEE International Conference on Image Processing. IEEE; 2010. p. 1517\u201320.","DOI":"10.1109\/ICIP.2010.5652502"},{"issue":"1","key":"3708_CR124","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/TPAMI.2017.2665623","volume":"40","author":"A Tejani","year":"2017","unstructured":"Tejani A, Kouskouridas R, Doumanoglou A, Tang D, Kim T-K. Latent-class Hough forests for 6 DoF object pose estimation. IEEE Trans Pattern Anal Mach Intell. 2017;40(1):119\u201332.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3708_CR125","doi-asserted-by":"crossref","unstructured":"Li P, Ling H, Li X, Liao C. 3D hand pose estimation using randomized decision forest with segmentation index points. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, p. 819\u201327.","DOI":"10.1109\/ICCV.2015.100"},{"key":"3708_CR126","doi-asserted-by":"crossref","unstructured":"Dantone M, Gall J, Leistner C, Van\u00a0Gool L. Human pose estimation using body parts dependent joint regressors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, p. 3041\u20133048.","DOI":"10.1109\/CVPR.2013.391"},{"key":"3708_CR127","doi-asserted-by":"crossref","unstructured":"Fang H-S, Xie S, Tai Y-W, Lu C. RMPE: regional multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 2017, p. 2334\u201343.","DOI":"10.1109\/ICCV.2017.256"},{"key":"3708_CR128","doi-asserted-by":"crossref","unstructured":"G\u00e4rtner E, Pirinen A, Sminchisescu C. Deep reinforcement learning for active human pose estimation. 2020. arXiv preprint arXiv:2001.02024.","DOI":"10.1609\/aaai.v34i07.6714"},{"key":"3708_CR129","doi-asserted-by":"crossref","unstructured":"Alp\u00a0G\u00fcler R, Neverova N, Kokkinos I. DensePose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, p. 7297\u2013306.","DOI":"10.1109\/CVPR.2018.00762"},{"key":"3708_CR130","doi-asserted-by":"crossref","unstructured":"Pavllo D, Feichtenhofer C, Grangier D, Auli M. 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, p. 7753\u201362.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"3708_CR131","unstructured":"Eichner M, Marin-Jimenez M, Zisserman A, Ferrari V. Articulated human pose estimation and search in (almost) unconstrained still images. 2010."},{"key":"3708_CR132","doi-asserted-by":"crossref","unstructured":"Ramanan D. Learning to parse images of articulated bodies. In: Advances in neural information processing systems. 2007. p. 1129\u201336.","DOI":"10.7551\/mitpress\/7503.003.0146"},{"key":"3708_CR133","doi-asserted-by":"crossref","unstructured":"Johnson S, Everingham M. Learning effective human pose estimation from inaccurate annotation. In: CVPR 2011. 2011. p. 1465\u201372.","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"3708_CR134","doi-asserted-by":"crossref","unstructured":"Sapp B, Taskar B. MODEC: multimodal decomposable models for human pose estimation. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013, p. 3674\u201381.","DOI":"10.1109\/CVPR.2013.471"},{"issue":"2","key":"3708_CR135","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A. The pascal visual object classes (VOC) challenge. Int J Comput Vis. 2010;88(2):303\u201338.","journal-title":"Int J Comput Vis"},{"key":"3708_CR136","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B. 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, p. 3686\u201393.","DOI":"10.1109\/CVPR.2014.471"},{"key":"3708_CR137","doi-asserted-by":"crossref","unstructured":"Cherian A, Mairal J, Alahari K, Schmid C. Mixing body-part sequences for human pose estimation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014, p. 2361\u201368.","DOI":"10.1109\/CVPR.2014.302"},{"issue":"7","key":"3708_CR138","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu C, Papava D, Olaru V, Sminchisescu C. Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans Pattern Anal Mach Intell. 2014;36(7):1325\u201339.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"3708_CR139","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal L, Balan A, Black MJ. HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int J Comput Vis. 2010;87(1):4\u201327.","journal-title":"Int J Comput Vis"},{"issue":"2","key":"3708_CR140","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1109\/TIP.2018.2872628","volume":"28","author":"X Nie","year":"2018","unstructured":"Nie X, Feng J, Xing J, Xiao S, Yan S. Hierarchical contextual refinement networks for human pose estimation. IEEE Trans Image Process. 2018;28(2):924\u201336.","journal-title":"IEEE Trans Image Process"},{"key":"3708_CR141","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.imavis.2016.12.002","volume":"59","author":"N Jammalamadaka","year":"2017","unstructured":"Jammalamadaka N, Zisserman A, Jawahar C. Human pose search using deep networks. Image Vis Comput. 2017;59:31\u201343.","journal-title":"Image Vis Comput"},{"key":"3708_CR142","doi-asserted-by":"crossref","unstructured":"Ai B, Zhou Y, Yu Y, Du S. Human pose estimation using deep structure guided learning. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE; 2017. p. 1224\u201331.","DOI":"10.1109\/WACV.2017.141"},{"key":"3708_CR143","doi-asserted-by":"crossref","unstructured":"Marras I, Palasek P, Patras I. Deep refinement convolutional networks for human pose estimation. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). IEEE; 2017. p. 446\u201353.","DOI":"10.1109\/FG.2017.148"},{"key":"3708_CR144","doi-asserted-by":"crossref","unstructured":"Yang W, Ouyang W, Li H, Wang X. End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, p. 3073\u201382.","DOI":"10.1109\/CVPR.2016.335"},{"key":"3708_CR145","doi-asserted-by":"crossref","unstructured":"Bulat A, Tzimiropoulos G. Human pose estimation via convolutional part heatmap regression. In: European Conference on Computer Vision. Springer; 2016. p. 717\u201332.","DOI":"10.1007\/978-3-319-46478-7_44"},{"key":"3708_CR146","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.sigpro.2014.07.031","volume":"108","author":"L Zhao","year":"2015","unstructured":"Zhao L, Gao X, Tao D, Li X. A deep structure for human pose estimation. Signal Process. 2015;108:36\u201345.","journal-title":"Signal Process"},{"key":"3708_CR147","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.sigpro.2014.09.014","volume":"110","author":"K Duan","year":"2015","unstructured":"Duan K, Batra D, Crandall DJ. Human pose estimation via multi-layer composite models. Signal Process. 2015;110:15\u201326.","journal-title":"Signal Process"},{"key":"3708_CR148","doi-asserted-by":"crossref","unstructured":"Cherian A, Mairal J, Alahari K, Schmid C. Mixing body-part sequences for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, p. 2353\u201360.","DOI":"10.1109\/CVPR.2014.302"},{"key":"3708_CR149","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu Y, Zhang J, Zhang Q, Tao D. ViTPose: simple vision transformer baselines for human pose estimation. Adv Neural Inf Process Syst. 2022;35:38571\u201384.","journal-title":"Adv Neural Inf Process Syst"},{"key":"3708_CR150","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang S, Wang Z, Yang S, Yang W, Xia S-T, Zhou E. TokenPose: learning keypoint tokens for human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, p. 11313\u201322.","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"3708_CR151","doi-asserted-by":"crossref","unstructured":"Zhang F, Zhu X, Dai H, Ye M, Zhu C. Distribution-aware coordinate representation for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, p. 7093\u2013102.","DOI":"10.1109\/CVPR42600.2020.00712"},{"issue":"5","key":"3708_CR152","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1109\/TVCG.2020.2973076","volume":"26","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Hu L, Deng X, Xia S. Weakly supervised adversarial learning for 3D human pose estimation from point clouds. IEEE Trans Vis Comput Graph. 2020;26(5):1851\u20139.","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"3708_CR153","doi-asserted-by":"crossref","unstructured":"Kanazawa A, Black MJ, Jacobs DW, Malik J. End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, p. 7122\u201331.","DOI":"10.1109\/CVPR.2018.00744"},{"key":"3708_CR154","doi-asserted-by":"crossref","unstructured":"Huang Y, Bogo F, Lassner C, Kanazawa A, Gehler PV, Romero J, Akhter I, Black MJ. Towards accurate marker-less human shape and pose estimation over time. In: 2017 International Conference on 3D Vision (3DV). IEEE; 2017. p. 421\u201330.","DOI":"10.1109\/3DV.2017.00055"},{"key":"3708_CR155","doi-asserted-by":"crossref","unstructured":"Jahangiri E, Yuille AL. Generating multiple diverse hypotheses for human 3D pose consistent with 2D joint detections. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, p. 805\u201314.","DOI":"10.1109\/ICCVW.2017.100"},{"key":"3708_CR156","doi-asserted-by":"crossref","unstructured":"Rogez G, Weinzaepfel P, Schmid C. LCR-Net: localization-classification-regression for human pose. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, p. 1216\u201324.","DOI":"10.1109\/CVPR.2017.134"},{"key":"3708_CR157","doi-asserted-by":"crossref","unstructured":"Yasin H, Iqbal U, Kruger B, Weber A, Gall J. A dual-source approach for 3D pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, p. 4948\u201356.","DOI":"10.1109\/CVPR.2016.535"},{"key":"3708_CR158","doi-asserted-by":"crossref","unstructured":"Gong K, Zhang J, Feng J. Poseaug: A differentiable pose augmentation framework for 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, p. 8575\u201384.","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"3708_CR159","doi-asserted-by":"crossref","unstructured":"Zhang J, Tu Z, Yang J, Chen Y, Yuan J. MixSTE: Seq2seq mixed spatio-temporal encoder for 3D human pose estimation in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, p. 13232\u201342.","DOI":"10.1109\/CVPR52688.2022.01288"},{"issue":"7553","key":"3708_CR160","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436\u201344.","journal-title":"Nature"},{"issue":"6","key":"3708_CR161","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/s00530-020-00677-2","volume":"26","author":"P Verma","year":"2020","unstructured":"Verma P, Sah A, Srivastava R. Deep learning-based multi-modal approach using RGB and skeleton sequences for human activity recognition. Multimed Syst. 2020;26(6):671\u201385.","journal-title":"Multimed Syst"},{"issue":"6","key":"3708_CR162","doi-asserted-by":"publisher","first-page":"2675","DOI":"10.3390\/app11062675","volume":"11","author":"N Tasnim","year":"2021","unstructured":"Tasnim N, Islam MK, Baek J-H. Deep learning based human activity recognition using spatio-temporal image formation of skeleton joints. Appl Sci. 2021;11(6):2675.","journal-title":"Appl Sci"},{"issue":"9","key":"3708_CR163","doi-asserted-by":"publisher","first-page":"4153","DOI":"10.3390\/app11094153","volume":"11","author":"J Kim","year":"2021","unstructured":"Kim J, Lee D. Activity recognition with combination of deeply learned visual attention and pose estimation. Appl Sci. 2021;11(9):4153.","journal-title":"Appl Sci"},{"key":"3708_CR164","doi-asserted-by":"crossref","unstructured":"Atikuzzaman M, Rahman TR, Wazed E, Hossain MP, Islam MZ. Human activity recognition system from different poses with CNN. In: 2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI). IEEE; 2020. p. 1\u20135.","DOI":"10.1109\/STI50764.2020.9350508"},{"issue":"4","key":"3708_CR165","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.3390\/s18041055","volume":"18","author":"H Cho","year":"2018","unstructured":"Cho H, Yoon SM. Divide and conquer-based 1D CNN human activity recognition using test data sharpening. Sensors. 2018;18(4):1055.","journal-title":"Sensors"},{"key":"3708_CR166","doi-asserted-by":"crossref","unstructured":"Dua N, Singh SN, Semwal VB. Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing. 2021:1\u201318.","DOI":"10.1007\/s00607-021-00928-8"},{"issue":"2","key":"3708_CR167","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1007\/s11042-018-6273-1","volume":"78","author":"M Gnouma","year":"2019","unstructured":"Gnouma M, Ladjailia A, Ejbali R, Zaied M. Stacked sparse autoencoder and history of binary motion image for human activity recognition. Multimed Tools Appl. 2019;78(2):2157\u201379.","journal-title":"Multimed Tools Appl"},{"key":"3708_CR168","doi-asserted-by":"crossref","unstructured":"Tonmoy M, Mahmud S, Mahbubur\u00a0Rahman A, Ashraful\u00a0Amin M, Ali AA. Hierarchical self attention based autoencoder for open-set human activity recognition. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer; 2021. p. 351\u201363.","DOI":"10.1007\/978-3-030-75768-7_28"},{"issue":"4","key":"3708_CR169","first-page":"160","volume":"17","author":"B Almaslukh","year":"2017","unstructured":"Almaslukh B, AlMuhtadi J, Artoli A. An effective deep autoencoder approach for online smartphone-based human activity recognition. Int J Comput Sci Netw Secur. 2017;17(4):160\u20135.","journal-title":"Int J Comput Sci Netw Secur"},{"key":"3708_CR170","doi-asserted-by":"crossref","unstructured":"Balabka D. Semi-supervised learning for human activity recognition using adversarial autoencoders. In: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, 2019, p. 685\u20138.","DOI":"10.1145\/3341162.3344854"},{"key":"3708_CR171","doi-asserted-by":"crossref","unstructured":"Nale R, Sawarbandhe M, Chegogoju N, Satpute V. Suspicious human activity detection using pose estimation and LSTM. In: 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA). IEEE; 2021. p. 197\u2013202.","DOI":"10.1109\/IRIA53009.2021.9588719"},{"key":"3708_CR172","doi-asserted-by":"crossref","unstructured":"Singh D, Merdivan E, Psychoula I, Kropf J, Hanke S, Geist M, Holzinger A. Human activity recognition using recurrent neural networks. In: International Cross-domain Conference for Machine Learning and Knowledge Extraction. Springer; 2017. p. 267\u201374.","DOI":"10.1007\/978-3-319-66808-6_18"},{"key":"3708_CR173","doi-asserted-by":"publisher","unstructured":"Mutegeki R, Han DS. A CNN-LSTM approach to human activity recognition. In: 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 2020, p. 362\u20136. https:\/\/doi.org\/10.1109\/ICAIIC48513.2020.9065078.","DOI":"10.1109\/ICAIIC48513.2020.9065078"},{"key":"3708_CR174","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2019.06.084","volume":"365","author":"S ur Rehman","year":"2019","unstructured":"ur Rehman S, Tu S, Waqas M, Huang Y, ur Rehman O, Ahmad B, Ahmad S. Unsupervised pre-trained filter learning approach for efficient convolution neural network. Neurocomputing. 2019;365:171\u201390.","journal-title":"Neurocomputing"},{"key":"3708_CR175","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1007\/s00138-011-0344-x","volume":"22","author":"NR Howe","year":"2011","unstructured":"Howe NR. A recognition-based motion capture baseline on the HumanEva II test data. Mach Vis Appl. 2011;22:995\u20131008.","journal-title":"Mach Vis Appl"},{"key":"3708_CR176","doi-asserted-by":"crossref","unstructured":"Sun M, Savarese S. Articulated part-based model for joint object detection and pose estimation. In: 2011 International Conference on Computer Vision, 2011, p. 723\u201330.","DOI":"10.1109\/ICCV.2011.6126309"},{"key":"3708_CR177","doi-asserted-by":"crossref","unstructured":"Ferrari V, Marin-Jimenez M, Zisserman A. Progressive search space reduction for human pose estimation. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, p. 1\u20138.","DOI":"10.1109\/CVPR.2008.4587468"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03708-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-03708-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03708-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T04:04:58Z","timestamp":1739851498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-03708-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,17]]},"references-count":177,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["3708"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-03708-9","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,17]]},"assertion":[{"value":"8 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of this manuscript declare that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The author of this manuscript confirms that: (i) Informed, written consent has been obtained from the relevant sources wherever is required; (ii) All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and its later amendments.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"190"}}