{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T07:55:33Z","timestamp":1770796533835,"version":"3.50.0"},"publisher-location":"Cham","reference-count":82,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200618","type":"print"},{"value":"9783031200625","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20062-5_1","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["TOCH: Spatio-Temporal Object-to-Hand Correspondence for\u00a0Motion Refinement"],"prefix":"10.1007","author":[{"given":"Keyang","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Bharat Lal","family":"Bhatnagar","sequence":"additional","affiliation":[]},{"given":"Jan Eric","family":"Lenssen","sequence":"additional","affiliation":[]},{"given":"Gerard","family":"Pons-Moll","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"1_CR1","unstructured":"https:\/\/virtualhumans.mpi-inf.mpg.de\/toch\/"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Aliakbarian, S., Saleh, F.S., Salzmann, M., Petersson, L., Gould, S.: A stochastic conditioning scheme for diverse human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5223\u20135232 (2020)","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3d human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3395\u20133404 (2019)","DOI":"10.1109\/CVPR.2019.00351"},{"key":"1_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-642-33783-3_46","volume-title":"Computer Vision","author":"L Ballan","year":"2012","unstructured":"Ballan, L., Taneja, A., Gall, J., Van Gool, L., Pollefeys, M.: Motion capture of hands in action using discriminative salient points. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 640\u2013653. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_46"},{"key":"1_CR5","first-page":"12909","volume":"33","author":"BL Bhatnagar","year":"2020","unstructured":"Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Loopreg: self-supervised learning of implicit surface correspondences, pose and shape for 3d human mesh registration. Adv. Neural Inf. Process. Syst. 33, 12909\u201312922 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1_CR6","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"1_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep It SMPL: automatic estimation of 3d human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"issue":"2","key":"1_CR8","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","volume":"30","author":"J Bohg","year":"2013","unstructured":"Bohg, J., Morales, A., Asfour, T., Kragic, D.: Data-driven grasp synthesis-a survey. IEEE Trans. Robot. 30(2), 289\u2013309 (2013)","journal-title":"IEEE Trans. Robot."},{"key":"1_CR9","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, pp. 10843\u201310852 (2019)","DOI":"10.1109\/CVPR.2019.01110"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Ham, C., Kemp, C.C., Hays, J.: ContactDB: analyzing and predicting grasp contact via thermal imaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8709\u20138719 (2019)","DOI":"10.1109\/CVPR.2019.00891"},{"key":"1_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-030-58601-0_22","volume-title":"Computer Vision","author":"S Brahmbhatt","year":"2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 361\u2013378. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_22"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: A unified 3d human motion synthesis model via conditional variational auto-encoder. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11645\u201311655 (2021)","DOI":"10.1109\/ICCV48922.2021.01144"},{"key":"1_CR13","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, pp. 12417\u201312426 (2021)","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Chen, L., Lin, S.Y., Xie, Y., Lin, Y.Y., Xie, X.: MVHM: a large-scale multi-view hand mesh benchmark for accurate 3d hand pose estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 836\u2013845 (2021)","DOI":"10.1109\/WACV48630.2021.00088"},{"key":"1_CR15","doi-asserted-by":"publisher","first-page":"4008","DOI":"10.1109\/TIP.2021.3068645","volume":"30","author":"Y Chen","year":"2021","unstructured":"Chen, Y., et al.: Joint hand-object 3d reconstruction from a single image with cross-branch feature fusion. IEEE Trans. Image Process. 30, 4008\u20134021 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"1_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5031\u20135041 (2020)","DOI":"10.1109\/CVPR42600.2020.00508"},{"key":"1_CR17","unstructured":"El-Khoury, S., Sahbani, A., Bidaud, P.: 3d objects grasps synthesis: a survey. In: 13th World Congress in Mechanism and Machine Science, pp. 573\u2013583 (2011)"},{"key":"1_CR18","doi-asserted-by":"publisher","unstructured":"Elgammal, A., Lee, C.S.: The Role of Manifold Learning in Human Motion Analysis. In: Rosenhahn, B., Klette, R., Metaxas, D. (eds.) Human Motion. Computational Imaging and Vision, vol. 36, pp. 25\u201356. Springer, Dordrecht (2008). https:\/\/doi.org\/10.1007\/978-1-4020-6693-1_2","DOI":"10.1007\/978-1-4020-6693-1_2"},{"key":"1_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 409\u2013419 (2018)","DOI":"10.1109\/CVPR.2018.00050"},{"key":"1_CR20","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, pp. 10833\u201310842 (2019)","DOI":"10.1109\/CVPR.2019.01109"},{"key":"1_CR21","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"1_CR22","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, pp. 1471\u20131481 (2021)","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"1_CR23","unstructured":"Guzov, V., Sattler, T., Pons-Moll, G.: Visually plausible human-object interaction capture from wearable sensors. In: arXiv (May 2022)"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Hamer, H., Gall, J., Weise, T., Van Gool, L.: An object-dependent hand pose prior from sparse training data. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 671\u2013678. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540150"},{"key":"1_CR25","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":"1_CR26","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, pp. 571\u2013580 (2020)","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Hasson, Y., Varol, G., Laptev, I., Schmid, C.: Towards unconstrained joint hand-object reconstruction from RGB videos. arXiv preprint arXiv:2108.07044 (2021)","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"1_CR29","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"},{"issue":"6","key":"1_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417836","volume":"39","author":"GE Henter","year":"2020","unstructured":"Henter, G.E., Alexanderson, S., Beskow, J.: MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. (TOG) 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"3","key":"1_CR31","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.vrih.2021.05.002","volume":"3","author":"L Huang","year":"2021","unstructured":"Huang, L., Zhang, B., Guo, Z., Xiao, Y., Cao, Z., Yuan, J.: Survey on depth and RGB image-based 3d hand shape and pose estimation. Virtual Reality Intell. Hardware 3(3), 207\u2013234 (2021)","journal-title":"Virtual Reality Intell. Hardware"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reasoning for human grasps generation. arXiv preprint arXiv:2104.03304 (2021)","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., Zhou, X., Daniilidis, K.: Coherent reconstruction of multiple humans from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zhu, Y., Svetlik, M., Fang, K., Zhu, Y.: Synergies between affordance and geometry: 6-DoF grasp detection via implicit representations. Robot. Sci. Syst. (2021)","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"1_CR35","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)","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"1_CR36","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014). http:\/\/arxiv.org\/abs\/1312.6114"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263 (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Babu, R.V.: BiHMP-GAN: bidirectional 3d human motion prediction GAN. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8553\u20138560 (2019)","DOI":"10.1609\/aaai.v33i01.33018553"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., Stuhmer, J., Bogo, F., Pollefeys, M.: H2o: two hands manipulating objects for first person interaction recognition. arXiv preprint arXiv:2104.11181 (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"1_CR40","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-642-17319-6_13","volume-title":"Simulation, Modeling, and Programming for Autonomous Robots","author":"B Le\u00f3n","year":"2010","unstructured":"Le\u00f3n, B., et al.: OpenGRASP: a toolkit for robot grasping simulation. In: Ando, N., Balakirsky, S., Hemker, T., Reggiani, M., von Stryk, O. (eds.) SIMPAR 2010. LNCS (LNAI), vol. 6472, pp. 109\u2013120. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-17319-6_13"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Task-generic hierarchical human motion prior using vaes. arXiv preprint arXiv:2106.04004 (2021)","DOI":"10.1109\/3DV53792.2021.00086"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Liu, C.K.: Dextrous manipulation from a grasping pose. In: ACM SIGGRAPH 2009 papers, pp. 1\u20136 (2009)","DOI":"10.1145\/1576246.1531365"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Luo, Z., Golestaneh, S.A., Kitani, K.M.: 3d human motion estimation via motion compression and refinement. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_20"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Malik, J., et al.: HandVoxNet: deep voxel-based network for 3d hand shape and pose estimation from a single depth map. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7113\u20137122 (2020)","DOI":"10.1109\/CVPR42600.2020.00714"},{"issue":"4","key":"1_CR45","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/MRA.2004.1371616","volume":"11","author":"AT Miller","year":"2004","unstructured":"Miller, A.T., Allen, P.K.: Graspit! a versatile simulator for robotic grasping. IEEE Robot. Autom. Mag. 11(4), 110\u2013122 (2004)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"1_CR46","unstructured":"Mordatch, I., Popovi\u0107, Z., Todorov, E.: Contact-invariant optimization for hand manipulation. In: Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation, pp. 137\u2013144 (2012)"},{"issue":"4","key":"1_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322958","volume":"38","author":"F Mueller","year":"2019","unstructured":"Mueller, F., et al.: Real-time pose and shape reconstruction of two interacting hands with a single depth camera. ACM Trans. Graph. (TOG) 38(4), 1\u201313 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Ng, E., Ginosar, S., Darrell, T., Joo, H.: Body2hands: learning to infer 3d hands from conversational gesture body dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11865\u201311874 (2021)","DOI":"10.1109\/CVPR46437.2021.01169"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints. In: 2011 International Conference on Computer Vision, pp. 2088\u20132095. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126483"},{"key":"1_CR50","unstructured":"Ormoneit, D., Sidenbladh, H., Black, M.J., Hastie, T.: Learning and tracking cyclic human motion. Adv. Neural Inf. Process. Syst. 894\u2013900 (2001)"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Panteleris, P., Argyros, A.: Back to RGB: 3d tracking of hands and hand-object interactions based on short-baseline stereo. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 575\u2013584 (2017)","DOI":"10.1109\/ICCVW.2017.74"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"1_CR53","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, pp. 652\u2013660 (2017)"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6) (2017)","DOI":"10.1145\/3130800.3130883"},{"issue":"3","key":"1_CR55","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/j.robot.2011.07.016","volume":"60","author":"A Sahbani","year":"2012","unstructured":"Sahbani, A., El-Khoury, S., Bidaud, P.: An overview of 3d object grasp synthesis algorithms. Robot. Auton. Syst. 60(3), 326\u2013336 (2012)","journal-title":"Robot. Auton. Syst."},{"issue":"6","key":"1_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417768","volume":"39","author":"B Smith","year":"2020","unstructured":"Smith, B., et al.: Constraining dense hand surface tracking with elasticity. ACM Trans. Graph. (TOG) 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-319-46475-6_19","volume-title":"Computer Vision","author":"S Sridhar","year":"2016","unstructured":"Sridhar, S., et al.: Real-time joint tracking of a hand manipulating an object from RGB-D input. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 294\u2013310. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_19"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Sridhar, S., Rhodin, H., Seidel, H.P., Oulasvirta, A., Theobalt, C.: Real-time hand tracking using a sum of anisotropic gaussians model. In: 2014 2nd International Conference on 3D Vision, vol. 1, pp. 319\u2013326. IEEE (2014)","DOI":"10.1109\/3DV.2014.37"},{"issue":"6","key":"1_CR59","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1145\/3355089.3356505","volume":"38","author":"S Starke","year":"2019","unstructured":"Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. ACM Trans. Graph. 38(6), 209\u2013210 (2019)","journal-title":"ACM Trans. Graph."},{"key":"1_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58548-8_34","volume-title":"Computer Vision","author":"O Taheri","year":"2020","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: GRAB: a dataset of whole-body human grasping of objects. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 581\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_34"},{"issue":"4","key":"1_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925965","volume":"35","author":"J Taylor","year":"2016","unstructured":"Taylor, J., et al.: Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Taylor, J., Shotton, J., Sharp, T., Fitzgibbon, A.: The vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 103\u2013110. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247664"},{"issue":"6","key":"1_CR63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3130800.3130853","volume":"36","author":"J Taylor","year":"2017","unstructured":"Taylor, J., et al.: Articulated distance fields for ultra-fast tracking of hands interacting. ACM Trans. Graph. (TOG) 36(6), 1\u201312 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Tiwari, G., Antic, D., Lenssen, J.E., Sarafianos, N., Tung, T., Pons-Moll, G.: Pose-NDF: modeling human pose manifolds with neural distance fields. In: European Conference on Computer Vision (ECCV), Springer, Cham October 2022","DOI":"10.1007\/978-3-031-20065-6_33"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Urtasun, R., Fleet, D.J., Fua, P.: 3d people tracking with gaussian process dynamical models. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 1, pp. 238\u2013245. IEEE (2006)","DOI":"10.1109\/CVPR.2006.15"},{"issue":"4","key":"1_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2461912.2462000","volume":"32","author":"Y Wang","year":"2013","unstructured":"Wang, Y., et al.: Video-based hand manipulation capture through composite motion control. ACM Trans. Graph. (TOG) 32(4), 1\u201314 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., Pons-Moll, G.: Chore: contact, human and object reconstruction from a single RGB image. In: European Conference on Computer Vision (ECCV). Springer, Cham, (October 2022","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"1_CR68","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, pp. 11097\u201311106 (2021)","DOI":"10.1109\/ICCV48922.2021.01091"},{"issue":"4","key":"1_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185537","volume":"31","author":"Y Ye","year":"2012","unstructured":"Ye, Y., Liu, C.K.: Synthesis of detailed hand manipulations using contact sampling. ACM Trans. Graph. (TOG) 31(4), 1\u201310 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Yi, H., et al.: Human-aware object placement for visual environment reconstruction. In: Computer Vision and Pattern Recognition (CVPR), pp. 3959\u20133970 (Jun 2022)","DOI":"10.1109\/CVPR52688.2022.00393"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q.: SmoothNet: a plug-and-play network for refining human poses in videos. In: European Conference on Computer Vision. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"1_CR72","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, pp. 11354\u201311363 (2021)","DOI":"10.1109\/ICCV48922.2021.01116"},{"issue":"4","key":"1_CR73","first-page":"1","volume":"38","author":"H Zhang","year":"2019","unstructured":"Zhang, H., Bo, Z.H., Yong, J.H., Xu, F.: InteractionFusion: real-time reconstruction of hand poses and deformable objects in hand-object interactions. ACM Trans. Graph. (TOG) 38(4), 1\u201311 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"3","key":"1_CR74","first-page":"1","volume":"40","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Zhou, Y., Tian, Y., Yong, J.H., Xu, F.: Single depth view based real-time reconstruction of hand-object interactions. ACM Trans. Graph. (TOG) 40(3), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"1_CR75","first-page":"1","volume":"40","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Ye, Y., Shiratori, T., Komura, T.: ManipNet: neural manipulation synthesis with a hand-object spatial representation. ACM Trans. Graph. (TOG) 40(4), 1\u201314 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Bogo, F., Pollefeys, M., Tang, S.: Learning motion priors for 4d human body capture in 3d scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11343\u201311353 (2021)","DOI":"10.1109\/ICCV48922.2021.01115"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, X., Bhatnagar, B.L., Guzov, V., Starke, S., Pons-Moll, G.: Couch: towards controllable human-chair interactions. In: European Conference on Computer Vision (ECCV). Springer, Cham, October 2022","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"1_CR78","doi-asserted-by":"crossref","unstructured":"Zhao, R., Su, H., Ji, Q.: Bayesian adversarial human motion synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6225\u20136234 (2020)","DOI":"10.1109\/CVPR42600.2020.00626"},{"issue":"6","key":"1_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2508363.2508412","volume":"32","author":"W Zhao","year":"2013","unstructured":"Zhao, W., Zhang, J., Min, J., Chai, J.: Robust realtime physics-based motion control for human grasping. ACM Trans. Graph. (TOG) 32(6), 1\u201312 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wang, T., Xia, S., Wang, Y.: Hand-3d-studio: a new multi-view system for 3d hand reconstruction. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2478\u20132482. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053321"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Zhu, T., Wu, R., Lin, X., Sun, Y.: Toward human-like grasp: dexterous grasping via semantic representation of object-hand. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15741\u201315751 (2021)","DOI":"10.1109\/ICCV48922.2021.01545"},{"key":"1_CR82","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20062-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T22:03:46Z","timestamp":1728338626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20062-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200618","9783031200625"],"references-count":82,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}