{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T18:06:50Z","timestamp":1758305210180,"version":"3.44.0"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["No. 2022JM-348"],"award-info":[{"award-number":["No. 2022JM-348"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61971339"],"award-info":[{"award-number":["No. 61971339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10489-025-06585-0","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T05:37:58Z","timestamp":1745905078000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LiteSpiralGCN: Lightweight 3D hand mesh reconstruction via spiral graph convolution"],"prefix":"10.1007","volume":"55","author":[{"given":"Yiteng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Minqi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kaibing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"6585_CR1","doi-asserted-by":"crossref","unstructured":"Joo H, Simon T, Cikara M, Sheikh Y (2019) Towards social artificial intelligence: Nonverbal social signal prediction in a triadic interaction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10873\u201310883","DOI":"10.1109\/CVPR.2019.01113"},{"issue":"4","key":"6585_CR2","first-page":"87","volume":"39","author":"S Han","year":"2020","unstructured":"Han S, Liu B, Cabezas R, Twigg CD, Zhang P, Petkau J, Yu T-H, Tai C-J, Akbay M, Wang Z, Nitzan A, Dong G, Ye Y, Tao L, Wan C, Wang R (2020) Megatrack: monochrome egocentric articulated hand-tracking for virtual reality. ACM Trans Grap (ToG) 39(4):87\u201318713","journal-title":"ACM Trans Grap (ToG)"},{"key":"6585_CR3","doi-asserted-by":"crossref","unstructured":"Ng E, Ginosar S, Darrell T, Joo H (2021) Body2hands: Learning to infer 3d hands from conversational gesture body dynamics. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 11865\u201311874","DOI":"10.1109\/CVPR46437.2021.01169"},{"key":"6585_CR4","doi-asserted-by":"crossref","unstructured":"Moon G, Lee KM (2020) I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image. In: Proceedings of the european conference on computer vision (ECCV), pp 752\u2013768","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"6585_CR5","doi-asserted-by":"crossref","unstructured":"Yang L, Li J, Xu W, Diao Y, Lu C (2020) Bihand: Recovering hand mesh with multi-stage bisected hourglass networks. In: Proceedings of the british machine vision conference (BMVC)","DOI":"10.5244\/C.34.71"},{"key":"6585_CR6","doi-asserted-by":"crossref","unstructured":"Cho J, Youwang K, Oh T-H (2022) Cross-attention of disentangled modalities for 3d human mesh recovery with transformers. In: Proceedings of the european conference on computer vision (ECCV), pp 342\u2013359","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"6585_CR7","doi-asserted-by":"crossref","unstructured":"Lin K, Wang L, Liu Z (2021) End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1954\u20131963","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"6585_CR8","doi-asserted-by":"crossref","unstructured":"Lin K, Wang L, Liu Z (2021) Mesh graphormer. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 12939\u201312948","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"6585_CR9","doi-asserted-by":"crossref","unstructured":"Lim I, Dielen A, Campen M, Kobbelt L (2018) A simple approach to intrinsic correspondence learning on unstructured 3d meshes. In: Proceedings of the european conference on computer vision (ECCV) Workshops, pp. 349\u2013362","DOI":"10.1007\/978-3-030-11015-4_26"},{"key":"6585_CR10","doi-asserted-by":"crossref","unstructured":"Chen X, Liu Y, Dong Y, Zhang X, Ma C, Xiong Y, Zhang Y, Guo X (2022) Mobrecon: Mobile-friendly hand mesh reconstruction from monocular image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 20544\u201320554","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"6585_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Liu Y, Ma C, Chang J, Wang H, Chen T, Guo X, Wan P, Zheng W (2021) Camera-space hand mesh recovery via semantic aggregation and adaptive 2d-1d registration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 13274\u201313283","DOI":"10.1109\/CVPR46437.2021.01307"},{"key":"6585_CR12","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":"6585_CR13","doi-asserted-by":"crossref","unstructured":"Saito S, Huang Z, Natsume R, Morishima S, Kanazawa A, Li H (2019) Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 2304\u20132314","DOI":"10.1109\/ICCV.2019.00239"},{"key":"6585_CR14","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A.N, Kaiser L.u, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 2017 conference on neural information processing systems (NeurIPS), pp 6000\u20136010"},{"key":"6585_CR15","doi-asserted-by":"crossref","unstructured":"Zheng X, Ren P, Sun H, Wang J, Qi Q, Liao J (2021) Sar: Spatial-aware regression for 3d hand pose and mesh reconstruction from a monocular rgb image. In: Proceedings of the 2021 IEEE international symposium on mixed and augmented reality (ISMAR), pp 99\u2013108","DOI":"10.1109\/ISMAR52148.2021.00024"},{"key":"6585_CR16","doi-asserted-by":"crossref","unstructured":"Li R, Wang S, Zhu F, Huang J (2018) Adaptive graph convolutional neural networks. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), pp 3546\u20133553","DOI":"10.1609\/aaai.v32i1.11691"},{"key":"6585_CR17","doi-asserted-by":"crossref","unstructured":"Brau E, Jiang H (2016) 3d human pose estimation via deep learning from 2d annotations. In: Proceedings of the 2016 fourth international conference on 3d vision (3DV), pp 582\u2013591","DOI":"10.1109\/3DV.2016.84"},{"key":"6585_CR18","doi-asserted-by":"crossref","unstructured":"Wandt B, Rosenhahn B (2019) Repnet: Weakly supervised training of an adversarial reprojection network for 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7782\u20137791","DOI":"10.1109\/CVPR.2019.00797"},{"key":"6585_CR19","doi-asserted-by":"crossref","unstructured":"Pavllo D, Feichtenhofer C, Grangier D, Auli M (2019) 3d human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7753\u20137762","DOI":"10.1109\/CVPR.2019.00794"},{"issue":"6","key":"6585_CR20","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.1007\/s10489-022-03764-1","volume":"53","author":"Z Chen","year":"2023","unstructured":"Chen Z, Sun Y (2023) Joint-wise 2d to 3d lifting for hand pose estimation from a single rgb image. Appl Intell (APIN) 53(6):6421\u20136431","journal-title":"Appl Intell (APIN)"},{"key":"6585_CR21","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the international conference on learning representations (ICLR)"},{"key":"6585_CR22","doi-asserted-by":"crossref","unstructured":"Xu T, Takano W (2021) Graph stacked hourglass networks for 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 16105\u201316114","DOI":"10.1109\/CVPR46437.2021.01584"},{"issue":"4","key":"6585_CR23","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1109\/TPAMI.2018.2827052","volume":"41","author":"L Ge","year":"2018","unstructured":"Ge L, Liang H, Yuan J, Thalmann D (2018) Real-time 3d hand pose estimation with 3d convolutional neural networks. IEEE Trans Pattern Anal Mach Intell 41(4):956\u2013970","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6585_CR24","doi-asserted-by":"crossref","unstructured":"Ci H, Wang C, Ma X, Wang Y (2019) Optimizing network structure for 3d human pose estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 2262\u20132271","DOI":"10.1109\/ICCV.2019.00235"},{"key":"6585_CR25","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6585_CR26","doi-asserted-by":"crossref","unstructured":"Zhao L, Peng X, Tian Y, Kapadia M, Metaxas DN (2019) Semantic graph convolutional networks for 3d human pose regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3425\u20133435","DOI":"10.1109\/CVPR.2019.00354"},{"key":"6585_CR27","doi-asserted-by":"crossref","unstructured":"Liu K, Ding R, Zou Z, Wang L, Tang W (2020) A comprehensive study of weight sharing in graph networks for 3d human pose estimation. In: Proceedings of the european conference on computer vision (ECCV), pp 318\u2013334","DOI":"10.1007\/978-3-030-58607-2_19"},{"key":"6585_CR28","doi-asserted-by":"crossref","unstructured":"Zhao W, Wang W, Tian Y (2022) Graformer: Graph-oriented transformer for 3d pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 20438\u201320447","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"6585_CR29","unstructured":"He M, Wei Z, Wen J-R (2022) Convolutional neural networks on graphs with chebyshev approximation, revisited. In: Proceedings of the 2022 Conference on Neural Information Processing Systems (NeurIPS), pp 7264\u20137276"},{"key":"6585_CR30","doi-asserted-by":"crossref","unstructured":"Chang L-J, Liao Y-C, Lin C-H, Yang-Mao S-F, Chen H-T (2023) Mask2hand: Learning to predict the 3d hand pose and shape from shadow. In: Proceedings of the 2023 asia pacific signal and information processing association annual summit and conference (APSIPA ASC), pp 591\u2013598","DOI":"10.1109\/APSIPAASC58517.2023.10317159"},{"key":"6585_CR31","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Argus M, Brox T (2021) Contrastive representation learning for hand shape estimation. In: Proceedings of the DAGM german conference on pattern recognition (DAGM), pp 250\u2013264","DOI":"10.1007\/978-3-030-92659-5_16"},{"key":"6585_CR32","doi-asserted-by":"crossref","unstructured":"Li J, Xu C, Chen Z, Bian S, Yang L, Lu C (2021) Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3383\u20133393","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"6585_CR33","doi-asserted-by":"crossref","unstructured":"Moon G, Shiratori T, Lee KM (2020) Deephandmesh: A weakly-supervised deep encoder-decoder framework for high-fidelity hand mesh modeling. In: Proceedings of the european conference on computer vision (ECCV), pp 440\u2013455","DOI":"10.1007\/978-3-030-58536-5_26"},{"key":"6585_CR34","doi-asserted-by":"crossref","unstructured":"Seeber M, Poranne R, Polleyfeys M, Oswald MR (2021) Realistichands: a hybrid model for 3d hand reconstruction. In: Proceedings of the 2021 international conference on 3D vision (3DV), pp 22\u201331","DOI":"10.1109\/3DV53792.2021.00013"},{"key":"6585_CR35","doi-asserted-by":"crossref","unstructured":"Yu Z, Li C, Yang L, Zheng X, Mi MB, Lee GH, Yao A (2023) Overcoming the trade-off between accuracy and plausibility in 3d hand shape reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 544\u2013553","DOI":"10.1109\/CVPR52729.2023.00060"},{"issue":"20","key":"6585_CR36","doi-asserted-by":"publisher","first-page":"9565","DOI":"10.1007\/s10489-024-05665-x","volume":"54","author":"J Lee","year":"2024","unstructured":"Lee J, Kim J, Kim SH, Choi S-I (2024) Enhancing 3d hand pose estimation using shaf: synthetic hand dataset including a forearm. Appl Intell (APIN) 54(20):9565\u20139578","journal-title":"Appl Intell (APIN)"},{"issue":"14","key":"6585_CR37","doi-asserted-by":"publisher","first-page":"16667","DOI":"10.1007\/s10489-022-03390-x","volume":"52","author":"I Kourbane","year":"2022","unstructured":"Kourbane I, Genc Y (2022) A graph-based approach for absolute 3d hand pose estimation using a single rgb image. Appl Intell (APIN) 52(14):16667\u201316682","journal-title":"Appl Intell (APIN)"},{"issue":"12","key":"6585_CR38","doi-asserted-by":"publisher","first-page":"14491","DOI":"10.1007\/s10489-022-03341-6","volume":"52","author":"S Liu","year":"2022","unstructured":"Liu S, Sehgal N, Ostadabbas S (2022) Adapted human pose: monocular 3d human pose estimation with zero real 3d pose data. Appl Intell (APIN) 52(12):14491\u201314506","journal-title":"Appl Intell (APIN)"},{"issue":"13","key":"6585_CR39","doi-asserted-by":"publisher","first-page":"15690","DOI":"10.1007\/s10489-022-03312-x","volume":"52","author":"W Wu","year":"2022","unstructured":"Wu W, Zhou D, Zhang Q, Dong J, Wei X (2022) High-order local connection network for 3d human pose estimation based on gcn. Appl Intell (APIN) 52(13):15690\u201315702","journal-title":"Appl Intell (APIN)"},{"key":"6585_CR40","doi-asserted-by":"crossref","unstructured":"Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C (2015) Efficient object localization using convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 648\u2013656","DOI":"10.1109\/CVPR.2015.7298664"},{"issue":"5","key":"6585_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2629500","volume":"33","author":"J Tompson","year":"2014","unstructured":"Tompson J, Stein M, Lecun Y, Perlin K (2014) Real-time continuous pose recovery of human hands using convolutional networks. ACM Transactions on Graphics (ToG) 33(5):1\u201310","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"6585_CR42","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"6585_CR43","doi-asserted-by":"crossref","unstructured":"Ge L, Liang H, Yuan J, Thalmann D (2016) Robust 3d hand pose estimation in single depth images: from single-view cnn to multi-view cnns. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3593\u20133601","DOI":"10.1109\/CVPR.2016.391"},{"key":"6585_CR44","doi-asserted-by":"crossref","unstructured":"Choi H, Moon G, Lee KM (2020) Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In: Proceedings of the european conference on computer vision (ECCV), pp 769\u2013787. Springer","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"6585_CR45","unstructured":"Bruna J, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and locally connected networks on graphs. In: Proceedings of the international conference on learning representations (ICLR)"},{"issue":"3","key":"6585_CR46","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/MSP.2012.2235192","volume":"30","author":"DI Shuman","year":"2013","unstructured":"Shuman DI, Narang SK, Frossard P, Ortega A, Vandergheynst P (2013) The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine 30(3):83\u201398","journal-title":"IEEE Signal Processing Magazine"},{"key":"6585_CR47","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":"6585_CR48","doi-asserted-by":"crossref","unstructured":"Tang X, Wang T, Fu C-W (2021) Towards accurate alignment in real-time 3d hand-mesh reconstruction. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 11698\u201311707","DOI":"10.1109\/ICCV48922.2021.01149"},{"key":"6585_CR49","doi-asserted-by":"crossref","unstructured":"Luan T, Zhai Y, Meng J, Li Z, Chen Z, Xu Y, Yuan J (2023) High fidelity 3d hand shape reconstruction via scalable graph frequency decomposition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 16795\u201316804","DOI":"10.1109\/CVPR52729.2023.01611"},{"key":"6585_CR50","doi-asserted-by":"crossref","unstructured":"Li M, Zhang H, Zhang Y, Shao R, Yu T, Liu Y (2024) Hhmr: Holistic hand mesh recovery by enhancing the multimodal controllability of graph diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 645\u2013654","DOI":"10.1109\/CVPR52733.2024.00068"},{"key":"6585_CR51","doi-asserted-by":"crossref","unstructured":"Park J, Oh Y, Moon G, Choi H, Lee KM (2022) Handoccnet: Occlusion-robust 3d hand mesh estimation network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1496\u20131505","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"6585_CR52","doi-asserted-by":"crossref","unstructured":"Dwivedi SK, Sun Y, Patel P, Feng Y, Black MJ (2024) Tokenhmr: Advancing human mesh recovery with a tokenized pose representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1323\u20131333","DOI":"10.1109\/CVPR52733.2024.00132"},{"key":"6585_CR53","unstructured":"Xingyu C, Song Z, Jiang X, Hu Y, Yu J, Zhang L (2024) Handos: 3d hand reconstruction in one stage. arXiv:2412.01537"},{"key":"6585_CR54","doi-asserted-by":"crossref","unstructured":"Zhou Z, Zhou S, Lv Z, Zou M, Tang Y, Liang J (2024) A simple baseline for efficient hand mesh reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1367\u20131376","DOI":"10.1109\/CVPR52733.2024.00136"},{"key":"6585_CR55","doi-asserted-by":"crossref","unstructured":"Pavlakos G, Shan D, Radosavovic I, Kanazawa A, Fouhey D, Malik J (2024) Reconstructing hands in 3d with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9826\u20139836","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"6585_CR56","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies (NAACL HLT), pp 4171\u20134186"},{"key":"6585_CR57","doi-asserted-by":"crossref","unstructured":"Kim J, Gwon M.-G, Park H, Kwon H, Um G.-M, Kim W (2023) Sampling is matter: Point-guided 3d human mesh reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 12880\u201312889","DOI":"10.1109\/CVPR52729.2023.01238"},{"key":"6585_CR58","doi-asserted-by":"crossref","unstructured":"Cheng W, Kim E, Ko JH (2025) Handdagt: A denoising adaptive graph transformer for 3d hand pose estimation. In: Proceedings of the european conference on computer vision (ECCV), pp 35\u201352","DOI":"10.1007\/978-3-031-73223-2_3"},{"issue":"5","key":"6585_CR59","doi-asserted-by":"publisher","first-page":"3275","DOI":"10.1109\/TPAMI.2023.3341630","volume":"46","author":"X Xu","year":"2024","unstructured":"Xu X, Liu L, Yan S (2024) Smpler: Taming transformers for monocular 3d human shape and pose estimation. IEEE Trans Pattern Anal Mach Intell (TPAMI) 46(5):3275\u20133289","journal-title":"IEEE Trans Pattern Anal Mach Intell (TPAMI)"},{"key":"6585_CR60","unstructured":"Haoye D, Chharia A, Gou W, Carrasco FV, la Torre FD (2024) Hamba: Single-view 3d hand reconstruction with graph-guided bi-scanning mamba. ArXiv arXiv:2407.09646"},{"key":"6585_CR61","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":"6585_CR62","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\/CVF international conference on computer vision (ICCV), pp 4903\u20134911","DOI":"10.1109\/ICCV.2017.525"},{"key":"6585_CR63","doi-asserted-by":"crossref","unstructured":"Zhang X, Huang H, Tan J, Xu H, Yang C, Peng G, Wang L, Liu J: Hand image understanding via deep multi-task learning. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 11281\u201311292 (2021)","DOI":"10.1109\/ICCV48922.2021.01109"},{"key":"6585_CR64","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"6585_CR65","doi-asserted-by":"crossref","unstructured":"G\u00fcler R.A, Neverova N, Kokkinos I (2018) Densepose: Dense human pose estimation in the wild. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7297\u20137306","DOI":"10.1109\/CVPR.2018.00762"},{"issue":"6","key":"6585_CR66","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 Transactions on Graphics (TOG) 36(6):1\u201317","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"6585_CR67","doi-asserted-by":"crossref","unstructured":"Gong S, Chen L, Bronstein M, Zafeiriou S (2019) Spiralnet++: A fast and highly efficient mesh convolution operator. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) workshops","DOI":"10.1109\/ICCVW.2019.00509"},{"key":"6585_CR68","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"6585_CR69","doi-asserted-by":"crossref","unstructured":"Wang N, Zhang Y, Li Z, Fu Y, Liu W, Jiang Y.-G (2018) Pixel2mesh: Generating 3d mesh models from single rgb images. In: Proceedings of the european conference on computer vision (ECCV), pp 52\u201367","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"6585_CR70","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Ceylan D, Yang J, Russell B, Argus M, Brox T (2019) Freihand: A dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 813\u2013822","DOI":"10.1109\/ICCV.2019.00090"},{"key":"6585_CR71","doi-asserted-by":"crossref","unstructured":"Hampali S, Rad M, Oberweger M, Lepetit V (2020) Honnotate: A method for 3d annotation of hand and object poses. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3196\u20133206","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"6585_CR72","doi-asserted-by":"crossref","unstructured":"Lim GM, Jatesiktat P, Ang WT (2020) Mobilehand: Real-time 3d hand shape and pose estimation from color image. In: Proceedings of the international conference on neural information processing (ICONIP), pp 450\u2013459","DOI":"10.1007\/978-3-030-63820-7_52"},{"key":"6585_CR73","doi-asserted-by":"crossref","unstructured":"Chen Y, Tu Z, Kang D, Bao L, Zhang Y, Zhe X, Chen R, Yuan J (2021) Model-based 3d hand reconstruction via self-supervised learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10451\u201310460","DOI":"10.1109\/CVPR46437.2021.01031"},{"key":"6585_CR74","doi-asserted-by":"crossref","unstructured":"Jiao Z, Wang X, Gao Q (2024) Handssca: 3d hand mesh reconstruction with state space channel attention from rgb images. arXiv:2405.01066","DOI":"10.1109\/ICASSP49660.2025.10887953"},{"key":"6585_CR75","doi-asserted-by":"crossref","unstructured":"Armando M, Galaaoui S, Baradel F, Lucas T, Leroy V, Br\u00e9gier R, Weinzaepfel P, Rogez G (2024) Cross-view and cross-pose completion for 3d human understanding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1512\u20131523","DOI":"10.1109\/CVPR52733.2024.00150"},{"key":"6585_CR76","doi-asserted-by":"crossref","unstructured":"Huang Z, Chen Y, Kang D, Zhang J, Tu Z (2023) Phrit: Parametric hand representation with implicit template. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 14974\u201314984","DOI":"10.1109\/ICCV51070.2023.01375"},{"key":"6585_CR77","doi-asserted-by":"crossref","unstructured":"Yu Z, Huang S, Fang C, Breckon T.P, Wang J (2023) Acr: Attention collaboration-based regressor for arbitrary two-hand reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 12955\u201312964","DOI":"10.1109\/CVPR52729.2023.01245"},{"key":"6585_CR78","unstructured":"Pang H.E, Cai Z, Yang L, Tao Q, Wu Z, Zhang T, Liu Z (2023) Towards robust and expressive whole-body human pose and shape estimation. In: Advances in neural information processing systems (NeurIPS), pp 17330\u201317344"},{"key":"6585_CR79","doi-asserted-by":"crossref","unstructured":"Chen P, Chen Y, Yang D, Wu F, Li Q, Xia Q, Tan Y (2021) I2uv-handnet: Image-to-uv prediction network for accurate and high-fidelity 3d hand mesh modeling. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 12929\u201312938","DOI":"10.1109\/ICCV48922.2021.01269"},{"key":"6585_CR80","unstructured":"Vasu PKA, Gabriel J, Zhu J, Tuzel O, Ranjan A (2023) Fastvit: A fast hybrid vision transformer using structural reparameterization. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 5785\u20135795"},{"key":"6585_CR81","doi-asserted-by":"crossref","unstructured":"Guo S, Cai Q, Qi L, Dong J (2023) Clip-hand3d: Exploiting 3d hand pose estimation via context-aware prompting. In: Proceedings of the 31st ACM international conference on multimedia (ACM MM), pp 4896\u20134907","DOI":"10.1145\/3581783.3612390"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06585-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06585-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06585-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T13:59:05Z","timestamp":1758290345000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06585-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":81,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6585"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06585-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"assertion":[{"value":"20 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 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 affirm that they have no known competing financial interests or personal relationships that might be perceived as influencing the findings and conclusions presented in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration of competing interest"}},{"value":"This work does not involve any research conducted by the authors on human participants or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"704"}}