{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:11:54Z","timestamp":1743084714870,"version":"3.40.3"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729829"},{"type":"electronic","value":"9783031729836"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72983-6_5","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"74-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Coarse-to-Fine Implicit Representation Learning for\u00a03D Hand-Object Reconstruction from\u00a0a\u00a0Single RGB-D Image"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4955-1934","authenticated-orcid":false,"given":"Xingyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1691-6457","authenticated-orcid":false,"given":"Pengfei","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2182-2228","authenticated-orcid":false,"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0829-4624","authenticated-orcid":false,"given":"Qi","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-7422","authenticated-orcid":false,"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3345-1732","authenticated-orcid":false,"given":"Zirui","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1486-0573","authenticated-orcid":false,"given":"Jianxin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Boukhayma, A., Bem, R.d., Torr, P.H.: 3D hand shape and pose from images in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","key":"5_CR1","DOI":"10.1109\/CVPR.2019.01110"},{"doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J.: Reconstructing hand-object interactions in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12417\u201312426 (2021)","key":"5_CR2","DOI":"10.1109\/ICCV48922.2021.01219"},{"unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)","key":"5_CR3"},{"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 (CVPR), pp. 9044\u20139053 (2021)","key":"5_CR4","DOI":"10.1109\/CVPR46437.2021.00893"},{"doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: 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 (2021)","key":"5_CR5","DOI":"10.1109\/ICCV48922.2021.01269"},{"key":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-58621-8_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., et al.: Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 561\u2013577. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_33"},{"doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: 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 (2021)","key":"5_CR7","DOI":"10.1109\/CVPR46437.2021.01307"},{"doi-asserted-by":"crossref","unstructured":"Chen, Y., Tu, Z., Ge, L., Zhang, D., Chen, R., Yuan, J.: So-HandNet: self-organizing network for 3D hand pose estimation with semi-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","key":"5_CR8","DOI":"10.1109\/ICCV.2019.00706"},{"doi-asserted-by":"crossref","unstructured":"Chen, Z., Chen, S., Schmid, C., Laptev, I.: gSDF: geometry-driven signed distance functions for 3D hand-object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12890\u201312900 (2023)","key":"5_CR9","DOI":"10.1109\/CVPR52729.2023.01239"},{"doi-asserted-by":"publisher","unstructured":"Chen, Z., Hasson, Y., Schmid, C., Laptev, I.: AlignSDF: pose-aligned signed distance fields for hand-object reconstruction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13661. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_14","key":"5_CR10","DOI":"10.1007\/978-3-031-19769-7_14"},{"doi-asserted-by":"crossref","unstructured":"Ge, L., et al.: 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 (2019)","key":"5_CR11","DOI":"10.1109\/CVPR.2019.01109"},{"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)","key":"5_CR12","DOI":"10.1109\/CVPR.2018.00878"},{"doi-asserted-by":"crossref","unstructured":"Grady, P., Tang, C., Twigg, C.D., Vo, M., Brahmbhatt, S., Kemp, C.C.: ContactOpt: optimizing contact to improve grasps. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1471\u20131481 (2021)","key":"5_CR13","DOI":"10.1109\/CVPR46437.2021.00152"},{"doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), pp. 216\u2013224 (2018)","key":"5_CR14","DOI":"10.1109\/CVPR.2018.00030"},{"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 (CVPR), pp. 11090\u201311100 (2022)","key":"5_CR15","DOI":"10.1109\/CVPR52688.2022.01081"},{"doi-asserted-by":"crossref","unstructured":"Hasson, Y., Tekin, B., Bogo, F., Laptev, I., Pollefeys, M., Schmid, C.: Leveraging photometric consistency over time for sparsely supervised hand-object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 571\u2013580 (2020)","key":"5_CR16","DOI":"10.1109\/CVPR42600.2020.00065"},{"doi-asserted-by":"crossref","unstructured":"Hasson, Y., Varol, G., Schmid, C., Laptev, I.: Towards unconstrained joint hand-object reconstruction from RGB videos. In: 2021 International Conference on 3D Vision (3DV), pp. 659\u2013668. IEEE (2021)","key":"5_CR17","DOI":"10.1109\/3DV53792.2021.00075"},{"doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11807\u201311816 (2019)","key":"5_CR18","DOI":"10.1109\/CVPR.2019.01208"},{"doi-asserted-by":"crossref","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: ACNET: attention based network to exploit complementary features for RGBD semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1440\u20131444. IEEE (2019)","key":"5_CR19","DOI":"10.1109\/ICIP.2019.8803025"},{"doi-asserted-by":"crossref","unstructured":"Huang, D., et al.: Reconstructing hand-held objects from monocular video. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20139 (2022)","key":"5_CR20","DOI":"10.1145\/3550469.3555401"},{"doi-asserted-by":"crossref","unstructured":"Huang, L., et al.: Neural voting field for camera-space 3D hand pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8969\u20138978 (2023)","key":"5_CR21","DOI":"10.1109\/CVPR52729.2023.00866"},{"doi-asserted-by":"crossref","unstructured":"Huang, W., Ren, P., Wang, J., Qi, Q., Sun, H.: AWR: adaptive weighting regression for 3D hand pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11061\u201311068 (2020)","key":"5_CR22","DOI":"10.1609\/aaai.v34i07.6761"},{"doi-asserted-by":"crossref","unstructured":"Huang, Z., Chen, Y., Kang, D., Zhang, J., Tu, Z.: PHRIT: parametric hand representation with implicit template. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14974\u201314984 (2023)","key":"5_CR23","DOI":"10.1109\/ICCV51070.2023.01375"},{"doi-asserted-by":"crossref","unstructured":"Iqbal, U., Molchanov, P., Gall, T.B.J., Kautz, J.: Hand pose estimation via latent 2.5D heatmap regression. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","key":"5_CR24","DOI":"10.1007\/978-3-030-01252-6_8"},{"doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: A2J-Transformer: anchor-to-joint transformer network for 3D interacting hand pose estimation from a single RGB image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8846\u20138855 (2023)","key":"5_CR25","DOI":"10.1109\/CVPR52729.2023.00854"},{"doi-asserted-by":"crossref","unstructured":"Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reasoning for human grasps generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11107\u201311116 (2021)","key":"5_CR26","DOI":"10.1109\/ICCV48922.2021.01092"},{"doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Yang, J., Zhang, Y., Black, M.J., Muandet, K., Tang, S.: Grasping field: learning implicit representations for human grasps. In: 2020 International Conference on 3D Vision (3DV), pp. 333\u2013344. IEEE (2020)","key":"5_CR27","DOI":"10.1109\/3DV50981.2020.00043"},{"doi-asserted-by":"publisher","unstructured":"Kong, D., et al.: Identity-aware hand mesh estimation and personalization from RGB images. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13665. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_31","key":"5_CR28","DOI":"10.1007\/978-3-031-20065-6_31"},{"unstructured":"Kulon, D., Wang, H., G\u00fcler, R.A., Bronstein, M., Zafeiriou, S.: Single image 3D hand reconstruction with mesh convolutions. arXiv preprint arXiv:1905.01326 (2019)","key":"5_CR29"},{"doi-asserted-by":"crossref","unstructured":"Leng, Z.,et al.: Dynamic hyperbolic attention network for fine hand-object reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14894\u201314904 (2023)","key":"5_CR30","DOI":"10.1109\/ICCV51070.2023.01368"},{"unstructured":"Li, L., Zhuo, L., Zhang, B., Bo, L., Chen, C.: DiffHand: end-to-end hand mesh reconstruction via diffusion models. arXiv preprint arXiv:2305.13705 (2023)","key":"5_CR31"},{"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 (CVPR), pp. 2761\u20132770 (2022)","key":"5_CR32","DOI":"10.1109\/CVPR52688.2022.00278"},{"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 (CVPR), pp. 1954\u20131963 (2021)","key":"5_CR33","DOI":"10.1109\/CVPR46437.2021.00199"},{"doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12939\u201312948 (2021)","key":"5_CR34","DOI":"10.1109\/ICCV48922.2021.01270"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: SA-Fusion: multimodal fusion approach for web-based human-computer interaction in the wild. In: Proceedings of the ACM Web Conference 2023, pp. 3883\u20133891 (2023)","key":"5_CR35","DOI":"10.1145\/3543507.3587429"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Sample-adapt fusion network for RGB-D hand detection in the wild. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135. IEEE (2023)","key":"5_CR36","DOI":"10.1109\/ICASSP49357.2023.10095106"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Keypoint fusion for RGB-D based 3D hand pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3756\u20133764 (2024)","key":"5_CR37","DOI":"10.1609\/aaai.v38i4.28166"},{"doi-asserted-by":"crossref","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: Seminal Graphics: Pioneering Efforts that Shaped the Field, pp. 347\u2013353 (1998)","key":"5_CR38","DOI":"10.1145\/280811.281026"},{"doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: 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 (CVPR) (2018)","key":"5_CR39","DOI":"10.1109\/CVPR.2018.00533"},{"key":"5_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-58571-6_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Lee, K.M.: I2L-MeshNet: image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 752\u2013768. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_44"},{"key":"5_CR41","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-030-58565-5_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Yu, S.-I., Wen, H., Shiratori, T., Lee, K.M.: InterHand2.6M: a dataset and baseline for 3D interacting hand pose estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020, pp. 548\u2013564. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_33"},{"key":"5_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","key":"5_CR43","DOI":"10.1109\/CVPR.2019.00025"},{"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 (CVPR), pp. 1496\u20131505 (2022)","key":"5_CR44","DOI":"10.1109\/CVPR52688.2022.00155"},{"unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)","key":"5_CR45"},{"unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","key":"5_CR46"},{"unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"5_CR47"},{"doi-asserted-by":"crossref","unstructured":"Ran, H., Liu, J., Wang, C.: Surface representation for point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18942\u201318952 (2022)","key":"5_CR48","DOI":"10.1109\/CVPR52688.2022.01837"},{"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 (2023)","key":"5_CR49","DOI":"10.1609\/aaai.v37i2.25310"},{"doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PiFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","key":"5_CR50","DOI":"10.1109\/ICCV.2019.00239"},{"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)","key":"5_CR51","DOI":"10.1109\/CVPR52688.2022.00171"},{"issue":"8","key":"5_CR52","doi-asserted-by":"publisher","first-page":"9469","DOI":"10.1109\/TPAMI.2023.3247907","volume":"45","author":"Z Tu","year":"2023","unstructured":"Tu, Z., et al.: Consistent 3D hand reconstruction in video via self-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9469\u20139485 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: PointPainting: sequential fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","key":"5_CR53","DOI":"10.1109\/CVPR42600.2020.00466"},{"doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","key":"5_CR54","DOI":"10.1007\/978-3-030-01234-2_1"},{"doi-asserted-by":"crossref","unstructured":"Xu, H., Wang, T., Tang, X., Fu, C.W.: H2ONET: hand-occlusion-and-orientation-aware network for real-time 3D hand mesh reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17048\u201317058 (2023)","key":"5_CR55","DOI":"10.1109\/CVPR52729.2023.01635"},{"doi-asserted-by":"crossref","unstructured":"Xu, S., Zhou, D., Fang, J., Yin, J., Bin, Z., Zhang, L.: FusionPainting: multimodal fusion with adaptive attention for 3D object detection. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 3047\u20133054. IEEE (2021)","key":"5_CR56","DOI":"10.1109\/ITSC48978.2021.9564951"},{"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 (CVPR), pp. 2750\u20132760 (2022)","key":"5_CR57","DOI":"10.1109\/CVPR52688.2022.00277"},{"doi-asserted-by":"crossref","unstructured":"Yang, L., Zhan, X., Li, K., Xu, W., Li, J., Lu, C.: CPF: learning a contact potential field to model the hand-object interaction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11097\u201311106 (2021)","key":"5_CR58","DOI":"10.1109\/ICCV48922.2021.01091"},{"doi-asserted-by":"crossref","unstructured":"Ye, Y., Gupta, A., Tulsiani, S.: What\u2019s in your hands? 3D reconstruction of generic objects in hands. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3895\u20133905 (2022)","key":"5_CR59","DOI":"10.1109\/CVPR52688.2022.00387"},{"doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: Interacting two-hand 3D pose and shape reconstruction from single color image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11354\u201311363 (2021)","key":"5_CR60","DOI":"10.1109\/ICCV48922.2021.01116"},{"unstructured":"Zhang, C., et al.: DDF-HO: hand-held object reconstruction via conditional directed distance field. arXiv preprint arXiv:2308.08231 (2023)","key":"5_CR61"},{"doi-asserted-by":"crossref","unstructured":"Zhang, X.,et al.: Hand image understanding via deep multi-task learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11281\u201311292 (2021)","key":"5_CR62","DOI":"10.1109\/ICCV48922.2021.01109"},{"doi-asserted-by":"crossref","unstructured":"Zheng, X., Ren, P., Sun, H., Wang, J., Qi, Q., Liao, J.: SAR: spatial-aware regression for 3D hand pose and mesh reconstruction from a monocular RGB image. In: 2021 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 99\u2013108. IEEE (2021)","key":"5_CR63","DOI":"10.1109\/ISMAR52148.2021.00024"},{"doi-asserted-by":"crossref","unstructured":"Zhou, Y., Habermann, M., Xu, W., Habibie, I., Theobalt, C., Xu, F.: 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) (2020)","key":"5_CR64","DOI":"10.1109\/CVPR42600.2020.00539"}],"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\/978-3-031-72983-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:54:28Z","timestamp":1730109268000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 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"}}]}}