{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:00:25Z","timestamp":1776834025578,"version":"3.51.2"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1C1C1011387"],"award-info":[{"award-number":["2021R1C1C1011387"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1C1C1011387"],"award-info":[{"award-number":["2021R1C1C1011387"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","award":["23ZD1140"],"award-info":[{"award-number":["23ZD1140"]}],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","award":["23ZD1140"],"award-info":[{"award-number":["23ZD1140"]}],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-04040-2","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T09:27:10Z","timestamp":1750411630000},"page":"10333-10345","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environments"],"prefix":"10.1007","volume":"41","author":[{"given":"Sanghyeon","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Taek","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"issue":"5","key":"4040_CR1","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"K Aouaidjia","year":"2019","unstructured":"Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-d joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51(5), 2774\u20132788 (2019)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"4040_CR2","doi-asserted-by":"crossref","unstructured":"Baptista, R., Ghorbel, E., Papadopoulos, K., Demisse, G.G., Aouada, D., Ottersten, B.: View-invariant action recognition from RGB data via 3d pose estimation. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2542\u20132546. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682904"},{"key":"4040_CR3","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S.: 3d pictorial structures for multiple human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1669\u20131676 (2014)","DOI":"10.1109\/CVPR.2014.216"},{"key":"4040_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"4040_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, H., Li, Y., Su, H., Wang, Z., Tu, C., Lischinski, D., Cohen-Or, D., Chen, B.: Synthesizing training images for boosting human 3d pose estimation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 479\u2013488. IEEE (2016)","DOI":"10.1109\/3DV.2016.58"},{"key":"4040_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Tan, R.T.: 3d human pose estimation using spatio-temporal networks with explicit occlusion training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 10631\u201310638 (2020)","DOI":"10.1609\/aaai.v34i07.6689"},{"key":"4040_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Yan, W., Tan, R.T.: Occlusion-aware networks for 3d human pose estimation in video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 723\u2013732 (2019)","DOI":"10.1109\/ICCV.2019.00081"},{"key":"4040_CR8","doi-asserted-by":"crossref","unstructured":"Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X.: Fast and robust multi-person 3d pose estimation from multiple views. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7792\u20137801 (2019)","DOI":"10.1109\/CVPR.2019.00798"},{"key":"4040_CR9","doi-asserted-by":"crossref","unstructured":"Fang, J., Zuo, X., Zhou, D., Jin, S., Wang, S., Zhang, L.: Lidar-aug: A general rendering-based augmentation framework for 3d object detection in 2021 IEEE. In: CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4708\u20134718 (2021)","DOI":"10.1109\/CVPR46437.2021.00468"},{"key":"4040_CR10","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, pp. 8575\u20138584 (2021)","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"4040_CR11","doi-asserted-by":"crossref","unstructured":"Gu, R., Wang, G., Hwang, J.N.: Exploring severe occlusion: multi-person 3d pose estimation with gated convolution. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 8243\u20138250. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412107"},{"key":"4040_CR12","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"key":"4040_CR13","doi-asserted-by":"crossref","unstructured":"Huang, L., Liang, J., Deng, W.: Dh-aug: Dh forward kinematics model driven augmentation for 3d human pose estimation. In: European Conference on Computer Vision, pp. 436\u2013453. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_25"},{"issue":"7","key":"4040_CR14","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","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. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4040_CR15","doi-asserted-by":"crossref","unstructured":"Joo, H., Liu, H., Tan, L., Gui, L., Nabbe, B., Matthews, I., Kanade, T., Nobuhara, S., Sheikh, Y.: Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3334\u20133342 (2015)","DOI":"10.1109\/ICCV.2015.381"},{"issue":"4\u20135","key":"4040_CR16","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3d human pose estimation for learning Tai Chi: a human factor perspective. Int. J. Hum. Comput. Interact. 35(4\u20135), 427\u2013439 (2019)","journal-title":"Int. J. Hum. Comput. Interact."},{"key":"4040_CR17","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2020","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimed. 23, 1330\u20131342 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"4040_CR18","first-page":"328","volume":"45","author":"A Karambakhsh","year":"2019","unstructured":"Karambakhsh, A., Kamel, A., Sheng, B., Li, P., Yang, P., Feng, D.D.: Deep gesture interaction for augmented anatomy learning. Int. J. Inf. Manag. 45, 328\u2013336 (2019)","journal-title":"Int. J. Inf. Manag."},{"key":"4040_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Ke, L., Pratama, K., Tai, Y.W., Tang, C.K., Cheng, K.T.: Cascaded deep monocular 3d human pose estimation with evolutionary training data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6173\u20136183 (2020)","DOI":"10.1109\/CVPR42600.2020.00621"},{"key":"4040_CR20","doi-asserted-by":"crossref","unstructured":"Lin, H.Y., Chen, T.W.: Augmented reality with human body interaction based on monocular 3d pose estimation. In: International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 321\u2013331. Springer (2010)","DOI":"10.1007\/978-3-642-17688-3_31"},{"key":"4040_CR21","doi-asserted-by":"crossref","unstructured":"Lin, J., Lee, G.H.: Multi-view multi-person 3d pose estimation with plane sweep stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11886\u201311895 (2021)","DOI":"10.1109\/CVPR46437.2021.01171"},{"key":"4040_CR22","doi-asserted-by":"crossref","unstructured":"Luvizon, D.C., Picard, D., Tabia, H.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00539"},{"key":"4040_CR23","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"4040_CR24","doi-asserted-by":"crossref","unstructured":"Mehta, D., Sotnychenko, O., Mueller, F., Xu, W., Sridhar, S., Pons-Moll, G., Theobalt, C.: Single-shot multi-person 3d pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV), pp. 120\u2013130. IEEE (2018)","DOI":"10.1109\/3DV.2018.00024"},{"issue":"4","key":"4040_CR25","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 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. TOG"},{"key":"4040_CR26","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: Camera distance-aware top-down approach for 3d multi-person pose estimation from a single RGB image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10133\u201310142 (2019)","DOI":"10.1109\/ICCV.2019.01023"},{"key":"4040_CR27","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6951\u20136960 (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"4040_CR28","doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2226\u20132234 (2018)","DOI":"10.1109\/CVPR.2018.00237"},{"key":"4040_CR29","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Huang, J., Abu-El-Haija, S., Gorban, A., Murphy, K., Fei-Fei, L.: Detecting events and key actors in multi-person videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3043\u20133053 (2016)","DOI":"10.1109\/CVPR.2016.332"},{"key":"4040_CR30","doi-asserted-by":"crossref","unstructured":"Reddy, N.D., Guigues, L., Pishchulin, L., Eledath, J., Narasimhan, S.G.: Tessetrack: end-to-end learnable multi-person articulated 3d pose tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15,190\u201315,200 (2021)","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"4040_CR31","unstructured":"Rogez, G., Schmid, C.: Mocap-guided data augmentation for 3d pose estimation in the wild. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"issue":"5","key":"4040_CR32","first-page":"1146","volume":"42","author":"G Rogez","year":"2019","unstructured":"Rogez, G., Weinzaepfel, P., Schmid, C.: Lcr-net++: multi-person 2d and 3d pose detection in natural images. IEEE Trans. Pattern Anal. Mach. Intell. 42(5), 1146\u20131161 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4040_CR33","unstructured":"S\u00e1r\u00e1ndi, I., Linder, T., Arras, K.O., Leibe, B.: How robust is 3d human pose estimation to occlusion? arXiv preprint arXiv:1808.09316 (2018)"},{"key":"4040_CR34","doi-asserted-by":"crossref","unstructured":"Scott, J., Collins, R., Funk, C., Liu, Y.: 4d model-based spatiotemporal alignment of scripted Taiji Quan sequences. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 795\u2013804 (2017)","DOI":"10.1109\/ICCVW.2017.99"},{"key":"4040_CR35","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"4040_CR36","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, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"4040_CR37","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3d pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2500\u20132509 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"4040_CR38","doi-asserted-by":"crossref","unstructured":"Tu, H., Wang, C., Zeng, W.: Voxelpose: Towards multi-camera 3d human pose estimation in wild environment. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, pp. 197\u2013212. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_12"},{"key":"4040_CR39","doi-asserted-by":"crossref","unstructured":"Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.J., Laptev, I., Schmid, C.: Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 109\u2013117 (2017)","DOI":"10.1109\/CVPR.2017.492"},{"issue":"7","key":"4040_CR40","doi-asserted-by":"publisher","first-page":"2417","DOI":"10.1007\/s00371-021-02120-7","volume":"38","author":"P Verma","year":"2022","unstructured":"Verma, P., Srivastava, R.: Two-stage multi-view deep network for 3d human pose reconstruction using images and its 2d joint heatmaps through enhanced stack-hourglass approach. Vis. Comput. 38(7), 2417\u20132430 (2022)","journal-title":"Vis. Comput."},{"key":"4040_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, Y., Yuille, A.L.: An approach to pose-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 915\u2013922 (2013)","DOI":"10.1109\/CVPR.2013.123"},{"key":"4040_CR42","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"4040_CR43","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3d human pose estimation in the wild by adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5255\u20135264 (2018)","DOI":"10.1109\/CVPR.2018.00551"},{"key":"4040_CR44","doi-asserted-by":"crossref","unstructured":"Yao, J., Chen, J., Niu, L., Sheng, B.: Scene-aware human pose generation using transformer. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2847\u20132855 (2023)","DOI":"10.1145\/3581783.3612439"},{"key":"4040_CR45","doi-asserted-by":"crossref","unstructured":"Ye, H., Zhu, W., Wang, C., Wu, R., Wang, Y.: Faster voxelpose: real-time 3d human pose estimation by orthographic projection. In: European Conference on Computer Vision, pp. 142\u2013159. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_9"},{"key":"4040_CR46","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yoon, J.S., Lee, I.K., Venkatesh, P., Park, J., Yu, J., Park, H.S.: Humbi: a large multiview dataset of human body expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2990\u20133000 (2020)","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"4040_CR47","first-page":"13153","volume":"34","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Cai, Y., Yan, S., Feng, J., et al.: Direct multi-view multi-person 3d pose estimation. Adv. Neural. Inf. Process. Syst. 34, 13153\u201313164 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4040_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, D., Liew, J.H., Nie, X., Feng, J.: Body meshes as points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 546\u2013556 (2021)","DOI":"10.1109\/CVPR46437.2021.00061"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04040-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04040-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04040-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:35:37Z","timestamp":1757928937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04040-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":48,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["4040"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04040-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3820469\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"29 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}