{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:39Z","timestamp":1777656339950,"version":"3.51.4"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730061","type":"print"},{"value":"9783031730078","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-73007-8_17","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:02:40Z","timestamp":1727722960000},"page":"284-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Dense Hand-Object (HO) GraspNet with\u00a0Full Grasping Taxonomy and\u00a0Dynamics"],"prefix":"10.1007","author":[{"given":"Woojin","family":"Cho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihyun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjae","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minje","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taeyun","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taewook","family":"Ha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyokeun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Je-Hwan","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Woontack","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Kyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"issue":"4","key":"17_CR1","doi-asserted-by":"publisher","first-page":"6537","DOI":"10.1109\/LRA.2021.3094246","volume":"6","author":"V Arapi","year":"2021","unstructured":"Arapi, V., Della Santina, C., Averta, G., Bicchi, A., Bianchi, M.: Understanding human manipulation with the environment: a novel taxonomy for video labelling. IEEE Robot. Autom. Lett. 6(4), 6537\u20136544 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Behave: dataset and method for tracking human object interactions. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Ham, C., Kemp, C.C., Hays, J.: ContactDB: analyzing and predicting grasp contact via thermal imaging. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00891"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Tang, C., Twigg, C.D., Kemp, C.C., Hays, J.: ContactPose: a dataset of grasps with object contact and hand pose. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58601-0_22"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Calli, B., Singh, A., Walsman, A., Srinivasa, S., Abbeel, P., Dollar, A.M.: The YCB object and model set: towards common benchmarks for manipulation research. In: ICAR (2015)","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J.: Reconstructing hand-object interactions in the wild. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Caramalau, R., Bhattarai, B., Kim, T.K.: Active learning for Bayesian 3D hand pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3419\u20133428 (2021)","DOI":"10.1109\/WACV48630.2021.00346"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., et\u00a0al.: DexYCB: a benchmark for capturing hand grasping of objects. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"17_CR9","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Joint hand-object 3D reconstruction from a single image with cross-branch feature fusion. TIP (2021)","DOI":"10.1109\/TIP.2021.3068645"},{"key":"17_CR11","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Hasson, Y., Schmid, C., Laptev, I.: AlignSDF: pose-aligned signed distance fields for hand-object reconstruction. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19769-7_14"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Cho, W., Park, G., Woo, W.: Tracking an object-grabbing hand using occluded depth reconstruction. In: ISMAR-Adjunct (2018)","DOI":"10.1109\/ISMAR-Adjunct.2018.00074"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Cho, W., Park, G., Woo, W.: Bare-hand depth inpainting for 3D tracking of hand interacting with object. In: ISMAR (2020)","DOI":"10.1109\/ISMAR50242.2020.00048"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Cini, F., Ortenzi, V., Corke, P., Controzzi, M.: On the choice of grasp type and location when handing over an object. Sci. Robot. 4(27), eaau9757 (2019)","DOI":"10.1126\/scirobotics.aau9757"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Corona, E., Pumarola, A., Alenya, G., Moreno-Noguer, F., Rogez, G.: Ganhand: predicting human grasp affordances in multi-object scenes. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00508"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Damen, D., et\u00a0al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. IJCV (2022)","DOI":"10.1007\/s11263-021-01531-2"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Doosti, B., Naha, S., Mirbagheri, M., Crandall, D.J.: Hope-net: a graph-based model for hand-object pose estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00664"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: ARCTIC: a dataset for dexterous bimanual hand-object manipulation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01244"},{"issue":"1","key":"17_CR20","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/THMS.2015.2470657","volume":"46","author":"T Feix","year":"2015","unstructured":"Feix, T., Romero, J., Schmiedmayer, H.B., Dollar, A.M., Kragic, D.: The grasp taxonomy of human grasp types. IEEE Trans. Hum.-Mach. Syst. 46(1), 66\u201377 (2015)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Three-dimensional reconstruction of human interactions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Fu, Q., Liu, X., Xu, R., Niebles, J.C., Kitani, K.M.: Deformer: dynamic fusion transformer for robust hand pose estimation. arXiv preprint arXiv:2303.04991 (2023)","DOI":"10.1109\/ICCV51070.2023.02157"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando, G., Johns, E., Kim, T.K.: Physics-based dexterous manipulations with estimated hand poses and residual reinforcement learning. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9340947"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando, G., Yuan, S., Baek, S., Kim, T.K.: First-person hand action benchmark with RGB-D videos and 3d hand pose annotations. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00050"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Gomez-Donoso, F., Orts-Escolano, S., Cazorla, M.: Large-scale multiview 3D hand pose dataset. IVC (2019)","DOI":"10.1016\/j.imavis.2018.12.001"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Goyal, M., Modi, S., Goyal, R., Gupta, S.: Human hands as probes for interactive object understanding. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00329"},{"key":"17_CR27","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"17_CR28","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"17_CR29","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"17_CR31","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Hasson, Y., Varol, G., Schmid, C., Laptev, I.: Towards unconstrained joint hand-object reconstruction from RGB videos. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"17_CR33","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, pp. 11807\u201311816 (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Hu, H., Yi, X., Zhang, H., Yong, J.H., Xu, F.: Physical interaction: reconstructing hand-object interactions with physics. In: SIGGRAPH Asia (2022)","DOI":"10.1145\/3550469.3555421"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Huang, C.H.P., et al.: Capturing and inferring dense full-body human-scene contact. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Huang, Y., Taheri, O., Black, M.J., Tzionas, D.: InterCap: joint markerless 3D tracking of humans and objects in interaction from multi-view RGB-D images. IJCV (2024)","DOI":"10.1007\/s11263-024-01984-1"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Jiang, N., et al.: Full-body articulated human-object interaction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human pose fitting towards in-the-wild 3D human pose estimation. In: 3DV (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Spurr, A., Fan, Z., Hilliges, O., Tang, S.: A skeleton-driven neural occupancy representation for articulated hands. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00012"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., St\u00fchmer, J., Bogo, F., Pollefeys, M.: H2O: two hands manipulating objects for first person interaction recognition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Lee, J., Saito, S., Nam, G., Sung, M., Kim, T.K.: InterHandGen: two-hand interaction generation via cascaded reverse diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 527\u2013537 (2024)","DOI":"10.1109\/CVPR52733.2024.00057"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Lee, J., Sung, M., Choi, H., Kim, T.K.: Im2hands: learning attentive implicit representation of interacting two-hand shapes. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02028"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Leroy, V., Weinzaepfel, P., Br\u00e9gier, R., Combaluzier, H., Rogez, G.: SMPLy benchmarking 3D human pose estimation in the wild. In: 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00040"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Interacting attention graph for single image two-hand reconstruction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"17_CR47","unstructured":"Lin, P., et al.: HandDiffuse: generative controllers for two-hand interactions via diffusion models. In: CoRR, vol. abs\/2312.04867 (2023)"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Lin, Z., Ding, C., Yao, H., Kuang, Z., Huang, S.: Harmonious feature learning for interactive hand-object pose estimation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01248"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Liu, J., Feng, F., Nakamura, Y.C., Pollard, N.S.: A taxonomy of everyday grasps in action. In: 2014 IEEE-RAS International Conference on Humanoid Robots, pp. 573\u2013580. IEEE (2014)","DOI":"10.1109\/HUMANOIDS.2014.7041420"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Liu, S., Jiang, H., Xu, J., Liu, S., Wang, X.: Semi-supervised 3D hand-object poses estimation with interactions in time. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM TOG (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"17_CR52","unstructured":"Lugaresi, C., et\u00a0al.: MediaPipe: a framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)"},{"key":"17_CR53","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. (2008)"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"17_CR56","unstructured":"Moon, G., et\u00a0al.: A dataset of relighted 3d interacting hands. In: NeurIPS (2024)"},{"key":"17_CR57","doi-asserted-by":"crossref","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: ECCV (2020)","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., Theobalt, C.: Real-time hand tracking under occlusion from an egocentric RGB-D sensor. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.131"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Park, G., Kim, T.K., Woo, W.: 3D hand pose estimation with a single infrared camera via domain transfer learning. In: ISMAR (2020)","DOI":"10.1109\/ISMAR50242.2020.00086"},{"key":"17_CR60","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: AGORA: avatars in geography optimized for regression analysis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"17_CR61","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"17_CR62","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D., Malik, J.: Reconstructing hands in 3D with transformers. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Sanchez, J., Choi, G., Sanfeliu, A., Moreno-Noguer, F.: 3DPeople: modeling the geometry of dressed humans. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00233"},{"key":"17_CR64","doi-asserted-by":"crossref","unstructured":"Qian, C., Sun, X., Wei, Y., Tang, X., Sun, J.: Realtime and robust hand tracking from depth. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.145"},{"key":"17_CR65","doi-asserted-by":"crossref","unstructured":"Qu, W., et al.: Novel-view synthesis and pose estimation for hand-object interaction from sparse views. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01386"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Bolkart, T., Sanyal, S., Black, M.J.: Generating 3D faces using convolutional mesh autoencoders. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"17_CR67","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM TOG (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"17_CR68","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"17_CR69","doi-asserted-by":"crossref","unstructured":"Sridhar, S., Oulasvirta, A., Theobalt, C.: Interactive markerless articulated hand motion tracking using RGB and depth data. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.305"},{"key":"17_CR70","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-019-0488-x","volume":"16","author":"F Stival","year":"2019","unstructured":"Stival, F., Michieletto, S., Cognolato, M., Pagello, E., M\u00fcller, H., Atzori, M.: A quantitative taxonomy of human hand grasps. J. Neuroeng. Rehabil. 16, 1\u201317 (2019)","journal-title":"J. Neuroeng. Rehabil."},{"key":"17_CR71","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., Fu, Y., Mei, T., Black, M.J.: Putting people in their place: monocular regression of 3D people in depth. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"17_CR72","doi-asserted-by":"crossref","unstructured":"Swamy, A., et al.: SHOWMe: benchmarking object-agnostic hand-object 3D reconstruction. In: ICCV (2023)","DOI":"10.1016\/j.cviu.2024.104073"},{"key":"17_CR73","doi-asserted-by":"crossref","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: Grab: a dataset of whole-body human grasping of objects. In: ECCV 2020 (2020)","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"17_CR74","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.490"},{"key":"17_CR75","doi-asserted-by":"crossref","unstructured":"Tekin, B., Bogo, F., Pollefeys, M.: H+O: unified egocentric recognition of 3D hand-object poses and interactions. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00464"},{"key":"17_CR76","doi-asserted-by":"crossref","unstructured":"Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM TOG (2014)","DOI":"10.1145\/2629500"},{"key":"17_CR77","doi-asserted-by":"crossref","unstructured":"Tse, T.H.E., Zhang, Z., Kim, K.I., Leonardis, A., Zheng, F., Chang, H.J.: S2 contact: graph-based network for 3D hand-object contact estimation with semi-supervised learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19769-7_33"},{"key":"17_CR78","doi-asserted-by":"crossref","unstructured":"Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.: Capturing hands in action using discriminative salient points and physics simulation. IJCV (2016)","DOI":"10.1007\/s11263-016-0895-4"},{"key":"17_CR79","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: RGB2Hands: real-time tracking of 3D hand interactions from monocular RGB video. ACM TOG (2020)","DOI":"10.1145\/3414685.3417852"},{"key":"17_CR80","unstructured":"Wen, G., Xiaoyu, B., Xavier, A.P., Francesc, M.N.: Multi-person extreme motion prediction. In: CVPR (2022)"},{"key":"17_CR81","doi-asserted-by":"crossref","unstructured":"Xu, C., Cheng, L.: Efficient hand pose estimation from a single depth image. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.429"},{"key":"17_CR82","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01635"},{"key":"17_CR83","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: OakInk: a large-scale knowledge repository for understanding hand-object interaction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"17_CR84","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"17_CR85","doi-asserted-by":"crossref","unstructured":"Yin, Y., Guo, C., Kaufmann, M., Zarate, J., Song, J., Hilliges, O.: Hi4D: 4D instance segmentation of close human interaction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"17_CR86","unstructured":"Yu, Z., Yang, L., Chen, S., Yao, A.: Local and global point cloud reconstruction for 3D hand pose estimation. In: BMVC (2021)"},{"key":"17_CR87","doi-asserted-by":"crossref","unstructured":"Yuan, S., Ye, Q., Stenger, B., Jain, S., Kim, T.K.: BigHand2.2M benchmark: hand pose dataset and state of the art analysis. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.279"},{"key":"17_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: Interacting two-hand 3D pose and shape reconstruction from single color image. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01116"},{"key":"17_CR89","unstructured":"Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: 3D hand pose tracking and estimation using stereo matching. In: ICIP (2017)"},{"key":"17_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: EgoBody: human body shape and motion of interacting people from head-mounted devices. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"17_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Hand image understanding via deep multi-task learning. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01109"},{"key":"17_CR92","doi-asserted-by":"crossref","unstructured":"Zheng, X., Wen, C., Xue, Z., Ren, P., Wang, J.: HaMuCo: hand pose estimation via multiview collaborative self-supervised learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01898"},{"key":"17_CR93","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Deepmulticap: performance capture of multiple characters using sparse multiview cameras. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00618"},{"key":"17_CR94","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Argus, M., Brox, T.: Contrastive representation learning for hand shape estimation. In: GCPR (2021)","DOI":"10.1007\/978-3-030-92659-5_16"},{"key":"17_CR95","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"17_CR96","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00090"},{"key":"17_CR97","doi-asserted-by":"crossref","unstructured":"Zuo, B., Zhao, Z., Sun, W., Xie, W., Xue, Z., Wang, Y.: Reconstructing interacting hands with interaction prior from monocular images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00831"}],"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\/978-3-031-73007-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:10:28Z","timestamp":1727723428000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73007-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031730061","9783031730078"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73007-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 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"}}]}}