{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:48Z","timestamp":1740108048893,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873046"],"award-info":[{"award-number":["61873046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1708263"],"award-info":[{"award-number":["U1708263"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s10044-021-01048-x","type":"journal-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T06:02:46Z","timestamp":1643004166000},"page":"157-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["3D hand pose estimation from a single RGB image through semantic decomposition of VAE latent space"],"prefix":"10.1007","volume":"25","author":[{"given":"Xinru","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7232-9479","authenticated-orcid":false,"given":"Xiangbo","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,24]]},"reference":[{"key":"1048_CR1","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Brox T (2017) Learning to estimate 3d hand pose from single rgb images. In Proceedings of the IEEE International Conference on Computer Vision(ICCV), pp. 4903\u20134911","DOI":"10.1109\/ICCV.2017.525"},{"key":"1048_CR2","doi-asserted-by":"crossref","unstructured":"Iqbal U, Molchanov P, Gall TBJ, Kautz J (2018) Hand pose estimation via latent 2.5d heatmap regression. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 118\u2013134","DOI":"10.1007\/978-3-030-01252-6_8"},{"key":"1048_CR3","doi-asserted-by":"crossref","unstructured":"Cai Y, Ge L, Cai J, Yuan J (2018) Weakly-supervised 3d hand pose estimation from monocular rgb images. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 666\u2013682","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"1048_CR4","doi-asserted-by":"crossref","unstructured":"Boukhayma A, Bem R\u00a0de, Torr PHS (2019) 3d hand shape and pose from images in the wild. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10843\u201310852","DOI":"10.1109\/CVPR.2019.01110"},{"key":"1048_CR5","doi-asserted-by":"crossref","unstructured":"Ge L, Ren Z, Li Y, Xue Z, Wang Y, Cai J, Yuan J (2019) 3d hand shape and pose estimation from a single rgb image. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10833\u201310842","DOI":"10.1109\/CVPR.2019.01109"},{"key":"1048_CR6","doi-asserted-by":"crossref","unstructured":"Zhang X, Li Q, Mo H, Zhang W, Zheng W (2019) End-to-end hand mesh recovery from a monocular rgb image. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2354\u20132364","DOI":"10.1109\/ICCV.2019.00244"},{"key":"1048_CR7","doi-asserted-by":"crossref","unstructured":"Baek S, Kim KI, Kim TK (2019) Pushing the envelope for rgb-based dense 3d hand pose estimation via neural rendering. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1067\u20131076","DOI":"10.1109\/CVPR.2019.00116"},{"key":"1048_CR8","doi-asserted-by":"crossref","unstructured":"Cai Y, Ge L, Liu J, Cai J, Cham T-J, Yuan J, Thalmann NM (2019) Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2272\u20132281","DOI":"10.1109\/ICCV.2019.00236"},{"issue":"8","key":"1048_CR9","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798\u20131828","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1048_CR10","unstructured":"Ridgeway K (2016) A survey of inductive biases for factorial representation-learning. arXiv preprintarXiv:1612.05299, 2016"},{"key":"1048_CR11","unstructured":"Kingma DP, Welling M (2014) Auto-encoding variational bayes. In International Conference on Learning Representation (ICLR)"},{"key":"1048_CR12","unstructured":"Kulkarni TD, Whitney W, Kohli P, Tenenbaum JB (2015) Deep convolutional inverse graphics network. Advances in Neural Information Processing Systems (NIPS), pp 2539\u20132547"},{"key":"1048_CR13","unstructured":"Karaletsos T, Belongie S, Rtsch G (2016) Bayesian representation learning with oracle constraints. In International Conference on Learning Representations (ICLR)"},{"key":"1048_CR14","doi-asserted-by":"crossref","unstructured":"Kim M, Wang Y, Sahu P, Pavlovic V (2019) Bayes-factor-vae: Hierarchical bayesian deep auto-encoder models for factor disentanglement. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2979\u20132987","DOI":"10.1109\/ICCV.2019.00307"},{"key":"1048_CR15","unstructured":"Chen RTQ, Li X, Grosse R, Duvenaud D (2018) Isolating sources of disentanglement in variational autoencoders. arXiv preprintarXiv:1802.04942"},{"key":"1048_CR16","doi-asserted-by":"crossref","unstructured":"Yang L, Yao A (2019) Disentangling latent hands for image synthesis and pose estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9877\u20139886","DOI":"10.1109\/CVPR.2019.01011"},{"key":"1048_CR17","unstructured":"Locatello F, Bauer S, Lucic M, Raetsch G, Gelly S, Sch\u00f6lkopf B, Bachem O (2019) Challenging common assumptions in the unsupervised learning of disentangled representations. In International Conference on Machine Learning (ICML), pp. 4114\u20134124"},{"key":"1048_CR18","unstructured":"Vahdat A, Kautz J (2020) Nvae: a deep hierarchical variational autoencoder. arXiv preprintarXiv:2007.03898"},{"key":"1048_CR19","unstructured":"Zhang J, Jiao J, Chen M, Qu L, Xu X, Yang Q (2016) 3d hand pose tracking and estimation using stereo matching. arXiv preprintarXiv:1610.07214"},{"key":"1048_CR20","unstructured":"Higgins I, Matthey L, Pal A, Burgess C, Glorot X, Botvinick M, Mohamed S, Lerchner A (2017) $$\\beta$$-vae: learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations (ICLR)"},{"key":"1048_CR21","unstructured":"Burgess CP, Higgins I, Pal A, Matthey L, Watters N, Desjardins G, Lerchner A (2018) Understanding disentangling in $$\\beta$$-vae. arXiv preprintarXiv:1804.03599"},{"key":"1048_CR22","unstructured":"Kim H, Mnih A (2018) Disentangling by factorising. In International Conference on Machine Learning, pp. 2649\u20132658"},{"key":"1048_CR23","unstructured":"Kumar A, Sattigeri P, Balakrishnan A (2017) Variational inference of disentangled latent concepts from unlabeled observations. In International Conference on Learning Representations (ICLR)"},{"key":"1048_CR24","unstructured":"Dupont E (2018) Learning disentangled joint continuous and discrete representations. Adv Neural Inf Process Syst (NIPS), pp. 710\u2013720"},{"key":"1048_CR25","doi-asserted-by":"crossref","unstructured":"Lee W, Kim D, Hong S, Lee H (2020) High-fidelity synthesis with disentangled representation. In European Conference on Computer Vision (ECCV), pp. 157\u2013174","DOI":"10.1007\/978-3-030-58574-7_10"},{"key":"1048_CR26","first-page":"5925","volume":"30","author":"N Siddharth","year":"2017","unstructured":"Siddharth N, Paige B, van de Meent J-W, Desmaison A, Goodman N, Kohli P, Wood F, Torr P (2017) Learning disentangled representations with semi-supervised deep generative models. Adv Neural Inf Process Syst (NIPS) 30:5925\u20135935","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"1048_CR27","unstructured":"Ruiz A, Martinez O, Binefa X, Verbeek J (2019) Learning disentangled representations with reference-based variational autoencoders. arXiv preprintarXiv:1901.08534"},{"key":"1048_CR28","first-page":"3495","volume":"34","author":"J Chen","year":"2020","unstructured":"Chen J, Batmanghelich K (2020) Weakly supervised disentanglement by pairwise similarities. Proce AAAI Conf Artif Intell 34:3495\u20133502","journal-title":"Proce AAAI Conf Artif Intell"},{"key":"1048_CR29","unstructured":"Locatello F, Tschannen M, Bauer S, R\u00e4tsch G, Sch\u00f6lkopf B, Bachem O (2019) Disentangling factors of variation using few labels. arXiv preprintarXiv:1905.01258"},{"key":"1048_CR30","doi-asserted-by":"crossref","unstructured":"Wan C, Probst T, Van\u00a0Gool L, Yao A (2017) Crossing nets: combining gans and vaes with a shared latent space for hand pose estimation. In Proc IEEE Conf Computer Vision Pattern Recogn (CVPR), pp. 680\u2013689","DOI":"10.1109\/CVPR.2017.132"},{"issue":"4","key":"1048_CR31","doi-asserted-by":"publisher","first-page":"4239","DOI":"10.1109\/LRA.2019.2930425","volume":"4","author":"Y Gao","year":"2019","unstructured":"Gao Y, Wang Y, Falco P, Navab N, Tombari F (2019) Variational object-aware 3-d hand pose from a single rgb image. IEEE Robot Autom Letts 4(4):4239\u20134246","journal-title":"IEEE Robot Autom Letts"},{"key":"1048_CR32","doi-asserted-by":"crossref","unstructured":"Spurr A, Song J, Park S, Hilliges O (2018) Cross-modal deep variational hand pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 89\u201398","DOI":"10.1109\/CVPR.2018.00017"},{"key":"1048_CR33","doi-asserted-by":"crossref","unstructured":"Yang L, Li S, Lee D, Yao A (2019) Aligning latent spaces for 3d hand pose estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2335\u20132343","DOI":"10.1109\/ICCV.2019.00242"},{"key":"1048_CR34","doi-asserted-by":"crossref","unstructured":"Kulon D, Guler RA, Kokkinos I, Bronstein MM, Zafeiriou S (2020) Weakly-supervised mesh-convolutional hand reconstruction in the wild. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4990\u20135000","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"1048_CR35","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778, 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"1048_CR36","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"key":"1048_CR37","doi-asserted-by":"crossref","unstructured":"Yang Y, Feng C, Shen Y, Tian D (2018) Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 206\u2013215","DOI":"10.1109\/CVPR.2018.00029"},{"key":"1048_CR38","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1048_CR39","doi-asserted-by":"crossref","unstructured":"Li S, Lee D (2019) Point-to-pose voting based hand pose estimation using residual permutation equivariant layer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11927\u201311936","DOI":"10.1109\/CVPR.2019.01220"},{"issue":"6","key":"1048_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3130800.3130883","volume":"36","author":"J Romero","year":"2017","unstructured":"Romero J, Tzionas D, Black MJ (2017) Embodied hands: modeling and capturing hands and bodies together. ACM Trans Graph (ToG) 36(6):1\u201317","journal-title":"ACM Trans Graph (ToG)"},{"key":"1048_CR41","unstructured":"Yang L, Li J, Xu W, Diao Y, Lu C (2020) Bihand: Recovering hand mesh with multi-stage bisected hourglass networks. arXiv preprintarXiv:2008.05079"},{"key":"1048_CR42","doi-asserted-by":"crossref","unstructured":"Zhou Y, Habermann M, Xu W, Habibie I, Theobalt C, Xu F (2020) Monocular real-time hand shape and motion capture using multi-modal data. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5346\u20135355","DOI":"10.1109\/CVPR42600.2020.00539"},{"key":"1048_CR43","doi-asserted-by":"crossref","unstructured":"Zhao L, Peng X, Chen Y, Kapadia M, Metaxas DN (2020) Knowledge as priors: cross-modal knowledge generalization for datasets without superior knowledge. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6528\u20136537","DOI":"10.1109\/CVPR42600.2020.00656"},{"key":"1048_CR44","doi-asserted-by":"crossref","unstructured":"Mueller F, Bernard F, Sotnychenko O, Mehta D, Sridhar S, Casas D, Theobalt C (2018) Ganerated hands for real-time 3d hand tracking from monocular rgb. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 49\u201359","DOI":"10.1109\/CVPR.2018.00013"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-021-01048-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-021-01048-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-021-01048-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T01:09:27Z","timestamp":1643936967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-021-01048-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,24]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1048"],"URL":"https:\/\/doi.org\/10.1007\/s10044-021-01048-x","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"type":"print","value":"1433-7541"},{"type":"electronic","value":"1433-755X"}],"subject":[],"published":{"date-parts":[[2022,1,24]]},"assertion":[{"value":"25 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}