{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:04:37Z","timestamp":1769634277630,"version":"3.49.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732225","type":"print"},{"value":"9783031732232","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73223-2_3","type":"book-chapter","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:48:27Z","timestamp":1731005307000},"page":"35-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["HandDAGT: A Denoising Adaptive Graph Transformer for\u00a03D Hand Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7996-0236","authenticated-orcid":false,"given":"Wencan","family":"Cheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6039-1853","authenticated-orcid":false,"given":"Eunji","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4434-4318","authenticated-orcid":false,"given":"Jong Hwan","family":"Ko","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., et\u00a0al.: DexYCB: a benchmark for capturing hand grasping of objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9044\u20139053 (2021)","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: DiffusionDet: diffusion model for object detection. arXiv preprint arXiv:2211.09788 (2022)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.neucom.2018.06.097","volume":"395","author":"X Chen","year":"2020","unstructured":"Chen, X., Wang, G., Guo, H., Zhang, C.: Pose guided structured region ensemble network for cascaded hand pose estimation. Neurocomputing 395, 138\u2013149 (2020)","journal-title":"Neurocomputing"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"43425","DOI":"10.1109\/ACCESS.2018.2863540","volume":"6","author":"X Chen","year":"2018","unstructured":"Chen, X., Wang, G., Zhang, C., Kim, T.K., Ji, X.: SHPR-Net: deep semantic hand pose regression from point clouds. IEEE Access 6, 43425\u201343439 (2018)","journal-title":"IEEE Access"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, W., Ko, J.H.: HandR2N2: iterative 3D hand pose estimation using a residual recurrent neural network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20904\u201320913 (2023)","DOI":"10.1109\/ICCV51070.2023.01911"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"Cheng, W., Lee, S.: Point auto-encoder and its application to 2D-3D transformation. In: International Symposium on Visual Computing, pp. 66\u201378. Springer (2019). https:\/\/doi.org\/10.1007\/978-3-030-33723-0_6","DOI":"10.1007\/978-3-030-33723-0_6"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, W., Park, J.H., Ko, J.H.: HandFoldingNet: a 3D hand pose estimation network using multiscale-feature guided folding of a 2D hand skeleton. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11260\u201311269 (2021)","DOI":"10.1109\/ICCV48922.2021.01107"},{"key":"3_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Du, K., Lin, X., Sun, Y., Ma, X.: CrossInfoNet: multi-task information sharing based hand pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9896\u20139905 (2019)","DOI":"10.1109\/CVPR.2019.01013"},{"key":"3_CR11","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-030-58539-6_8","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI","author":"L Fang","year":"2020","unstructured":"Fang, L., Liu, X., Liu, L., Xu, H., Kang, W.: JGR-P2O: joint graph reasoning based pixel-to-offset prediction network for 3D hand pose estimation from a single depth image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VI, pp. 120\u2013137. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_8"},{"issue":"2","key":"3_CR12","first-page":"2158","volume":"24","author":"Y Gao","year":"2022","unstructured":"Gao, Y., Liu, X., Li, J., Fang, Z., Jiang, X., Huq, K.M.S.: LFT-Net: local feature transformer network for point clouds analysis. IEEE Trans. Intell. Transp. Syst. 24(2), 2158\u20132168 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Ge, L., Cai, Y., Weng, J., Yuan, J.: Hand PointNet: 3D hand pose estimation using point sets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8417\u20138426 (2018)","DOI":"10.1109\/CVPR.2018.00878"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Ge, L., Liang, H., Yuan, J., Thalmann, D.: Robust 3D hand pose estimation in single depth images: from single-view CNN to multi-view CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3593\u20133601 (2016)","DOI":"10.1109\/CVPR.2016.391"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Ge, L., Liang, H., Yuan, J., Thalmann, D.: 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1991\u20132000 (2017)","DOI":"10.1109\/CVPR.2017.602"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Ge, L., Ren, Z., Yuan, J.: Point-to-Point regression PointNet for 3D hand pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 475\u2013491 (2018)","DOI":"10.1007\/978-3-030-01261-8_29"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, G., Chen, X., Zhang, C., Qiao, F., Yang, H.: Region ensemble network: improving convolutional network for hand pose estimation. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 4512\u20134516. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8297136"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: a method for 3D annotation of hand and object poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3196\u20133206 (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Hampali, S., Sarkar, S.D., Rad, M., Lepetit, V.: Keypoint Transformer: solving joint identification in challenging hands and object interactions for accurate 3D pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11090\u201311100 (2022)","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"3_CR20","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Huang, L., Tan, J., Liu, J., Yuan, J.: Hand-Transformer: non-autoregressive structured modeling for 3D hand pose estimation. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16, pp. 17\u201333. Springer (2020)","DOI":"10.1007\/978-3-030-58595-2_2"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: 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, pp. 3383\u20133393 (2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Interacting attention graph for single image two-hand reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2761\u20132770 (2022)","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Lee, D.: Point-to-pose voting based hand pose estimation using residual permutation equivariant layer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11927\u201311936 (2019)","DOI":"10.1109\/CVPR.2019.01220"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh Graphormer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12939\u201312948 (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Liu, X., Qi, C.R., Guibas, L.J.: FlowNet3D: learning scene flow in 3D point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 529\u2013537 (2019)","DOI":"10.1109\/CVPR.2019.00062"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"issue":"12","key":"3_CR30","doi-asserted-by":"publisher","first-page":"8962","DOI":"10.1109\/TPAMI.2021.3122874","volume":"44","author":"J Malik","year":"2021","unstructured":"Malik, J., et al.: HandVoxNet++: 3D hand shape and pose estimation using voxel-based neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8962\u20138974 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Moon, G., Yong\u00a0Chang, J., Mu\u00a0Lee, K.: V2V-PoseNet: voxel-to-voxel prediction network for accurate 3D hand and human pose estimation from a single depth map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5079\u20135088 (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Oberweger, M., Lepetit, V.: DeepPrior++: improving fast and accurate 3d hand pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 585\u2013594 (2017)","DOI":"10.1109\/ICCVW.2017.75"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Park, J., Oh, Y., Moon, G., Choi, H., Lee, K.M.: HandOccNet: occlusion-robust 3D hand mesh estimation network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1496\u20131505 (2022)","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"3_CR34","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5099\u20135108 (2017)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Ren, P., et al.: Two heads are better than one: image-point cloud network for depth-based 3D hand pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2163\u20132171 (2023)","DOI":"10.1609\/aaai.v37i2.25310"},{"key":"3_CR36","unstructured":"Ren, P., Sun, H., Hao, J., Qi, Q., Wang, J., Liao, J.: Pose-guided hierarchical graph reasoning for 3-D hand pose estimation from a single depth image. IEEE Trans. Cybern. (2021)"},{"key":"3_CR37","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neucom.2021.01.045","volume":"437","author":"P Ren","year":"2021","unstructured":"Ren, P., et al.: Spatial-aware stacked regression network for real-time 3D hand pose estimation. Neurocomputing 437, 42\u201357 (2021)","journal-title":"Neurocomputing"},{"key":"3_CR38","unstructured":"Ren, P., Sun, H., Qi, Q., Wang, J., Huang, W.: SRN: stacked regression network for real-time 3D hand pose estimation. In: BMVC, p.\u00a0112 (2019)"},{"key":"3_CR39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-58520-4_13","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVII","author":"A Spurr","year":"2020","unstructured":"Spurr, A., Iqbal, U., Molchanov, P., Hilliges, O., Kautz, J.: Weakly supervised 3D hand pose estimation via biomechanical constraints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVII, pp. 211\u2013228. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_13"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Tang, D., Jin\u00a0Chang, H., Tejani, A., Kim, T.K.: Latent regression forest: structured estimation of 3D articulated hand posture. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3786\u20133793 (2014)","DOI":"10.1109\/CVPR.2014.490"},{"issue":"5","key":"3_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.: Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans. Graph. (ToG) 33(5), 1\u201310 (2014)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Tse, T.H.E., Kim, K.I., Leonardis, A., Chang, H.J.: Collaborative learning for hand and object reconstruction with attention-guided graph convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1664\u20131674 (2022)","DOI":"10.1109\/CVPR52688.2022.00171"},{"key":"3_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Wan, C., Probst, T., Van\u00a0Gool, L., Yao, A.: Dense 3D regression for hand pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5147\u20135156 (2018)","DOI":"10.1109\/CVPR.2018.00540"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, L., Li, J., Zhang, X.: HandGCNFormer: a novel topology-aware transformer network for 3D hand pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5675\u20135684 (2023)","DOI":"10.1109\/WACV56688.2023.00563"},{"key":"3_CR46","unstructured":"Wu, L., Liu, X., Liu, Q.: Centroid Transformers: learning to abstract with attention. arXiv preprint arXiv:2102.08606 (2021)"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Xiong, F., et al.: A2J: anchor-to-joint regression network for 3D articulated pose estimation from a single depth image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 793\u2013802 (2019)","DOI":"10.1109\/ICCV.2019.00088"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: ArtiBoost: boosting articulated 3D hand-object pose estimation via online exploration and synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2750\u20132760 (2022)","DOI":"10.1109\/CVPR52688.2022.00277"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"3_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73223-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:02:52Z","timestamp":1731006172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73223-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"ISBN":["9783031732225","9783031732232"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73223-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"8 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}