{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:44:12Z","timestamp":1777567452930,"version":"3.51.4"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"European Research Council","award":["336845"],"award-info":[{"award-number":["336845"]}]},{"name":"PRAIRIE 3IA Institute","award":["ANR-19-P3IA-0001"],"award-info":[{"award-number":["ANR-19-P3IA-0001"]}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000468"],"award-info":[{"award-number":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000468"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"H2020 Memmo project"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11263-021-01540-1","type":"journal-article","created":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T12:02:41Z","timestamp":1641297761000},"page":"363-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Estimating 3D Motion and Forces of Human\u2013Object Interactions from Internet Videos"],"prefix":"10.1007","volume":"130","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2864-0590","authenticated-orcid":false,"given":"Zongmian","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiri","family":"Sedlar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Carpentier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Mansard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,4]]},"reference":[{"key":"1540_CR1","unstructured":"Abdulla, W. (2017). Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow. https:\/\/github.com\/matterport\/Mask_RCNN"},{"key":"1540_CR2","unstructured":"Agarwal, S., Mierle, K., et al. (2012). Ceres solver. http:\/\/ceres-solver.org"},{"key":"1540_CR3","doi-asserted-by":"crossref","unstructured":"Akhter, I., & Black, M. J. (2015). Pose-conditioned joint angle limits for 3d human pose reconstruction. In CVPR","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"1540_CR4","doi-asserted-by":"crossref","unstructured":"Alayrac, J. B., Bojanowski, P., Agrawal, N., Laptev, I., Sivic, J., & Lacoste-Julien, S. (2016). Unsupervised learning from narrated instruction videos. In CVPR.","DOI":"10.1109\/CVPR.2016.495"},{"key":"1540_CR5","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014). 2d human pose estimation: New benchmark and state of the art analysis. In CVPR.","DOI":"10.1109\/CVPR.2014.471"},{"key":"1540_CR6","doi-asserted-by":"crossref","unstructured":"Biegler, L. T. (2010). Nonlinear programming: Concepts, algorithms, and applications to chemical processes (Vol.\u00a010, Chap\u00a010). SIAM.","DOI":"10.1137\/1.9780898719383"},{"key":"1540_CR7","doi-asserted-by":"crossref","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., & Black, M. J. (2016). Keep it SMPL: Automatic estimation of 3d human pose and shape from a single image. In ECCV.","DOI":"10.1007\/978-3-319-46454-1_34"},{"issue":"6","key":"1540_CR8","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/BF01901021","volume":"6","author":"R Boulic","year":"1990","unstructured":"Boulic, R., Thalmann, N. M., & Thalmann, D. (1990). A global human walking model with real-time kinematic personification. The Visual Computer, 6(6), 344\u2013358. https:\/\/doi.org\/10.1007\/BF01901021","journal-title":"The Visual Computer"},{"key":"1540_CR9","unstructured":"Bourdev, L., & Malik, J. (2011). The human annotation tool. https:\/\/www2.eecs.berkeley.edu\/Research\/Projects\/CS\/vision\/shape\/hat\/"},{"key":"1540_CR10","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Ying Yang, M., Gumhold, S., et al. (2016). Uncertainty-driven 6d pose estimation of objects and scenes from a single rgb image. In CVPR.","DOI":"10.1109\/CVPR.2016.366"},{"key":"1540_CR11","doi-asserted-by":"crossref","unstructured":"Brubaker, M. A., Fleet, D. J., & Hertzmann, A. (2007). Physics-based person tracking using simplified lower-body dynamics. In CVPR.","DOI":"10.1109\/CVPR.2007.383342"},{"key":"1540_CR12","doi-asserted-by":"crossref","unstructured":"Brubaker, M. A., Sigal, L., & Fleet, D. J. (2009). Estimating contact dynamics. In CVPR.","DOI":"10.1109\/ICCV.2009.5459407"},{"key":"1540_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S. E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In CVPR.","DOI":"10.1109\/CVPR.2017.143"},{"key":"1540_CR14","doi-asserted-by":"crossref","unstructured":"Carpentier, J., & Mansard, N. (2018a). Analytical derivatives of rigid body dynamics algorithms. In Robotics: Science and Systems.","DOI":"10.15607\/RSS.2018.XIV.038"},{"key":"1540_CR15","doi-asserted-by":"crossref","unstructured":"Carpentier, J., & Mansard, N. (2018b). Multi-contact locomotion of legged robots. IEEE Transactions on Robotics.","DOI":"10.1109\/TRO.2018.2862902"},{"key":"1540_CR16","unstructured":"Carpentier, J., Valenza, F., Mansard, N., et\u00a0al. (2015\u20132019). Pinocchio: Fast forward and inverse dynamics for poly-articulated systems. https:\/\/stack-of-tasks.github.io\/pinocchio"},{"key":"1540_CR17","unstructured":"Carpentier, J., Del Prete, A., Tonneau, S., Flayols, T., Forget, F., Mifsud, A., et al. (2017). Multi-contact locomotion of legged robots in complex environments-the loco3d project. In RSS workshop on challenges in dynamic legged locomotion (p.\u00a03p)."},{"key":"1540_CR18","doi-asserted-by":"crossref","unstructured":"Carpentier, J., Saurel, G., Buondonno, G., Mirabel, J., Lamiraux, F., Stasse, O., & Mansard, N. (2019). The pinocchio c++ library\u2014A fast and flexible implementation of rigid body dynamics algorithms and their analytical derivatives. In IEEE international symposium on system integrations (SII).","DOI":"10.1109\/SII.2019.8700380"},{"key":"1540_CR19","doi-asserted-by":"crossref","unstructured":"Chen, C. H., & Ramanan, D. (2017). 3d human pose estimation= 2d pose estimation+ matching. In CVPR.","DOI":"10.1109\/CVPR.2017.610"},{"key":"1540_CR20","unstructured":"Delaitre, V., Sivic, J., & Laptev, I. (2011). Learning person\u2013object interactions for action recognition in still images. In NIPS."},{"key":"1540_CR21","doi-asserted-by":"crossref","unstructured":"Diehl, M., Bock, H., Diedam, H., & Wieber, P. B. (2006). Fast direct multiple shooting algorithms for optimal robot control. In Fast motions in biomechanics and robotics. Springer.","DOI":"10.1007\/978-3-540-36119-0_4"},{"key":"1540_CR22","unstructured":"Doumanoglou, A., Kouskouridas, R., Malassiotis, S., & Kim, T. K. (2016). 6D object detection and next-best-view prediction in the crowd. In CVPR."},{"key":"1540_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7560-7","volume-title":"Rigid body dynamics algorithms","author":"R Featherstone","year":"2008","unstructured":"Featherstone, R. (2008). Rigid body dynamics algorithms. Berlin: Springer."},{"issue":"3","key":"1540_CR24","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/s11263-014-0710-z","volume":"110","author":"DF Fouhey","year":"2014","unstructured":"Fouhey, D. F., Delaitre, V., Gupta, A., Efros, A. A., Laptev, I., & Sivic, J. (2014). People watching: Human actions as a cue for single view geometry. IJCV, 110(3), 259\u2013274.","journal-title":"IJCV"},{"issue":"1\u20132","key":"1540_CR25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s11263-008-0173-1","volume":"87","author":"J Gall","year":"2010","unstructured":"Gall, J., Rosenhahn, B., Brox, T., & Seidel, H. P. (2010). Optimization and filtering for human motion capture. International Journal of Computer Vision, 87(1\u20132), 75.","journal-title":"International Journal of Computer Vision"},{"key":"1540_CR26","doi-asserted-by":"crossref","unstructured":"Gammeter, S., Ess, A., J\u00e4ggli, T., Schindler, K., Leibe, B., & Van Gool, L. (2008). Articulated multi-body tracking under egomotion. In ECCV.","DOI":"10.1007\/978-3-540-88688-4_60"},{"issue":"1","key":"1540_CR27","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/BF02291478","volume":"40","author":"JC Gower","year":"1975","unstructured":"Gower, J. C. (1975). Generalized procrustes analysis. Psychometrika, 40(1), 33\u201351.","journal-title":"Psychometrika"},{"key":"1540_CR28","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P. M., & Lepetit, V. (2018). 3D pose estimation and 3D model retrieval for objects in the wild. In CVPR.","DOI":"10.1109\/CVPR.2018.00319"},{"issue":"10","key":"1540_CR29","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta, A., Kembhavi, A., & Davis, L. S. (2009). Observing human\u2013object interactions: Using spatial and functional compatibility for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(10), 1775\u20131789.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1540_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1540_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. B. (2017). Mask R-CNN. CoRR. arXiv:1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"1540_CR32","doi-asserted-by":"publisher","unstructured":"Herdt, A., Perrin, N., & Wieber, P. B. (2010). Walking without thinking about it. In International Conference on Intelligent Robots and Systems (IROS). https:\/\/doi.org\/10.1109\/IROS.2010.5654429","DOI":"10.1109\/IROS.2010.5654429"},{"key":"1540_CR33","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., Lepetit, V., Rajkumar, N., & Konolige, K. (2016). Going further with point pair features. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_51"},{"key":"1540_CR34","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., & Schiele, B. (2016). Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In ECCV.","DOI":"10.1007\/978-3-319-46466-4_3"},{"issue":"7","key":"1540_CR35","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014). Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(7), 1325\u20131339.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1540_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Koppula, H., & Saxena, A. (2013). Hallucinated humans as the hidden context for labeling 3d scenes. In CVPR.","DOI":"10.1109\/CVPR.2013.385"},{"key":"1540_CR37","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M. J., Jacobs, D. W., & Malik, J. (2018). End-to-end recovery of human shape and pose. In CVPR.","DOI":"10.1109\/CVPR.2018.00744"},{"key":"1540_CR38","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J. Y., Felsen, P., & Malik, J. (2019). Learning 3d human dynamics from video. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5614\u20135623).","DOI":"10.1109\/CVPR.2019.00576"},{"key":"1540_CR39","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., & Black, M. J. (2020). 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).","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"1540_CR40","doi-asserted-by":"crossref","unstructured":"Kuffner, J., Nishiwaki, K., Kagami, S., Inaba, M., & Inoue, H. (2005). Motion planning for humanoid robots. In Robotics research. The eleventh international symposium.","DOI":"10.1007\/11008941_39"},{"key":"1540_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., & Fox, D. (2018). DeepIM: Deep iterative matching for 6D pose estimation. In ECCV.","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"1540_CR42","doi-asserted-by":"crossref","unstructured":"Li, Z., Sedlar, J., Carpentier, J., Laptev, I., Mansard, N., & Sivic, J. (2019). Estimating 3d motion and forces of person\u2013object interactions from monocular video. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00884"},{"key":"1540_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S. J., Bourdev, L. D., Girshick, R. B., Hays, J., et al. (2014). Microsoft COCO: common objects in context. CoRRarXiv:1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1540_CR44","doi-asserted-by":"publisher","unstructured":"Loing, V., Marlet, R., & Aubry, M. (2018). Virtual training for a real application: Accurate object-robot relative localization without calibration. In IJCV. https:\/\/doi.org\/10.1007\/s11263-018-1102-6","DOI":"10.1007\/s11263-018-1102-6"},{"issue":"6","key":"1540_CR45","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & Black, M. J. (2015). SMPL: A skinned multi-person linear model. ACM Transactions on Graphics (TOG), 34(6), 248.","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"6","key":"1540_CR46","doi-asserted-by":"publisher","first-page":"220:1","DOI":"10.1145\/2661229.2661273","volume":"33","author":"MM Loper","year":"2014","unstructured":"Loper, M. M., Mahmood, N., & Black, M. J. (2014). MoSh: Motion and shape capture from sparse markers. ACM Transactions on Graphics (Proc SIGGRAPH Asia), 33(6), 220:1-220:13. https:\/\/doi.org\/10.1145\/2661229.2661273","journal-title":"ACM Transactions on Graphics (Proc SIGGRAPH Asia)"},{"key":"1540_CR47","unstructured":"Maldonado, G. (2018). Some biomechanical and robotic models. https:\/\/github.com\/GaloMALDONADO\/Models"},{"key":"1540_CR48","doi-asserted-by":"publisher","unstructured":"Maldonado, G., Bailly, F., Sou\u00e8res, P., & Watier, B. (2017). Angular momentum regulation strategies for highly dynamic landing in Parkour. Computer Methods in Biomechanics and Biomedical Engineering, 20(sup1), 123\u2013124. https:\/\/doi.org\/10.1080\/10255842.2017.1382892, https:\/\/hal.archives-ouvertes.fr\/hal-01636353","DOI":"10.1080\/10255842.2017.1382892"},{"key":"1540_CR49","doi-asserted-by":"crossref","unstructured":"Malmaud, J., Huang, J., Rathod, V., Johnston, N., Rabinovich, A., & Murphy, K. (2015). What\u2019s cookin\u2019? interpreting cooking videos using text, speech and vision. arXiv preprint arXiv:1503.01558","DOI":"10.3115\/v1\/N15-1015"},{"key":"1540_CR50","doi-asserted-by":"crossref","unstructured":"Marinoiu, E., Papava, D., & Sminchisescu, C. (2013). Pictorial human spaces: How well do humans perceive a 3d articulated pose? In Proceedings of the IEEE International Conference on Computer Vision (pp. 1289\u20131296).","DOI":"10.1109\/ICCV.2013.163"},{"key":"1540_CR51","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., & Little, J. J. (2017). A simple yet effective baseline for 3d human pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2017.288"},{"issue":"4","key":"1540_CR52","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/2185520.2185539","volume":"31","author":"I Mordatch","year":"2012","unstructured":"Mordatch, I., Todorov, E., & Popovi\u0107, Z. (2012). Discovery of complex behaviors through contact-invariant optimization. ACM Transactions on Graphics (TOG), 31(4), 43.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1540_CR53","doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F. (2017). 3d human pose estimation from a single image via distance matrix regression. In CVPR.","DOI":"10.1109\/CVPR.2017.170"},{"key":"1540_CR54","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., & Deng, J. (2016). Stacked hourglass networks for human pose estimation. In ECCV.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1540_CR55","unstructured":"Newell, A., Huang, Z., & Deng, J. (2017). Associative embedding: End-to-end learning for joint detection and grouping. In NIPS."},{"key":"1540_CR56","doi-asserted-by":"crossref","unstructured":"Oberweger, M., Rad, M., & Lepetit, V. (2018). Making deep heatmaps robust to partial occlusions for 3D object pose estimation. In ECCV.","DOI":"10.1007\/978-3-030-01267-0_8"},{"key":"1540_CR57","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K. G., & Daniilidis, K. (2017). Coarse-to-fine volumetric prediction for single-image 3d human pose. In CVPR.","DOI":"10.1109\/CVPR.2017.139"},{"issue":"1","key":"1540_CR58","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1177\/0278364913506757","volume":"33","author":"M Posa","year":"2014","unstructured":"Posa, M., Cantu, C., & Tedrake, R. (2014). A direct method for trajectory optimization of rigid bodies through contact. The International Journal of Robotics Research, 33(1), 69\u201381.","journal-title":"The International Journal of Robotics Research"},{"issue":"4","key":"1540_CR59","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1109\/TPAMI.2012.175","volume":"35","author":"A Prest","year":"2013","unstructured":"Prest, A., Ferrari, V., & Schmid, C. (2013). Explicit modeling of human\u2013object interactions in realistic videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(4), 835\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1540_CR60","unstructured":"Project webpage. (2021). https:\/\/www.di.ens.fr\/willow\/research\/motionforcesfromvideo\/"},{"key":"1540_CR61","doi-asserted-by":"crossref","unstructured":"Rad, M., & Lepetit, V. (2017). Bb8: A scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth. In ICCV.","DOI":"10.1109\/ICCV.2017.413"},{"key":"1540_CR62","doi-asserted-by":"crossref","unstructured":"Rad, M., Oberweger, M., & Lepetit, V. (2018). Feature mapping for learning fast and accurate 3D pose inference from synthetic images. In CVPR.","DOI":"10.1109\/CVPR.2018.00490"},{"key":"1540_CR63","doi-asserted-by":"crossref","unstructured":"Rempe, D., Guibas, L. J., Hertzmann, A., Russell, B., Villegas, R., & Yang, J. (2020). Contact and human dynamics from monocular video. In European conference on computer vision (pp. 71\u201387). Springer.","DOI":"10.1007\/978-3-030-58558-7_5"},{"issue":"5","key":"1540_CR64","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1109\/TMECH.2009.2035112","volume":"15","author":"G Schultz","year":"2010","unstructured":"Schultz, G., & Mombaur, K. (2010). Modeling and optimal control of human-like running. IEEE\/ASME Transactions on Mechatronics, 15(5), 783\u2013792.","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"issue":"6","key":"1540_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417877","volume":"39","author":"S Shimada","year":"2020","unstructured":"Shimada, S., Golyanik, V., Xu, W., & Theobalt, C. (2020). Physcap: Physically plausible monocular 3d motion capture in real time. ACM Transactions on Graphics (TOG), 39(6), 1\u201316.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1540_CR66","doi-asserted-by":"crossref","unstructured":"Sidenbladh, H., Black, M. J., Fleet, D. J. (2000). Stochastic tracking of 3d human figures using 2d image motion. In ECCV.","DOI":"10.1007\/3-540-45053-X_45"},{"key":"1540_CR67","doi-asserted-by":"publisher","unstructured":"Tassa, Y., Erez, T., & Todorov, E. (2012). Synthesis and stabilization of complex behaviors through online trajectory optimization. In IEEE international conference on intelligent robots and systems (IROS). https:\/\/doi.org\/10.1109\/IROS.2012.6386025","DOI":"10.1109\/IROS.2012.6386025"},{"issue":"3","key":"1540_CR68","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1006\/cviu.2000.0878","volume":"80","author":"CJ Taylor","year":"2000","unstructured":"Taylor, C. J. (2000). Reconstruction of articulated objects from point correspondences in a single uncalibrated image. Computer Vision and Image Understanding, 80(3), 349\u2013363.","journal-title":"Computer Vision and Image Understanding"},{"key":"1540_CR69","doi-asserted-by":"crossref","unstructured":"Tejani, A., Tang, D., Kouskouridas, R., & Kim, T. K. (2014). Latent-class hough forests for 3d object detection and pose estimation. In ECCV.","DOI":"10.1007\/978-3-319-10599-4_30"},{"key":"1540_CR70","doi-asserted-by":"crossref","unstructured":"Tekin, B., Rozantsev, A., Lepetit, V., & Fua, P. (2016). Direct prediction of 3d body poses from motion compensated sequences. In CVPR.","DOI":"10.1109\/CVPR.2016.113"},{"key":"1540_CR71","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017). Domain randomization for transferring deep neural networks from simulation to the real world. CoRR. arXiv:1703.06907","DOI":"10.1109\/IROS.2017.8202133"},{"key":"1540_CR72","doi-asserted-by":"publisher","unstructured":"Tonneau, S., Del Prete, A., Pettr\u00e9, J., Park, C., Manocha, D., & Mansard, N. (2018a). An efficient acyclic contact planner for multiped robots. IEEE Transactions on Robotics (TRO). https:\/\/doi.org\/10.1109\/TRO.2018.2819658","DOI":"10.1109\/TRO.2018.2819658"},{"key":"1540_CR73","doi-asserted-by":"crossref","unstructured":"Tonneau, S., Del Prete, A., Pettr\u00e9, J., Park, C., Manocha, D., & Mansard, N. (2018b). An efficient acyclic contact planner for multiped robots. IEEE Transactions on Robotics, 34(3), 586\u2013601.","DOI":"10.1109\/TRO.2018.2819658"},{"key":"1540_CR74","doi-asserted-by":"crossref","unstructured":"Triggs, B., McLauchlan, P. F., Hartley, R. I., Fitzgibbon, A. W. (1999). Bundle adjustment\u2014A modern synthesis. In International workshop on vision algorithms.","DOI":"10.1007\/3-540-44480-7_21"},{"issue":"4","key":"1540_CR75","doi-asserted-by":"publisher","first-page":"42:1","DOI":"10.1145\/1778765.1778779","volume":"29","author":"X Wei","year":"2010","unstructured":"Wei, X., & Chai, J. (2010). Videomocap: Modeling physically realistic human motion from monocular video sequences. ACM Transactions on Graphics, 29(4), 42:1-42:10. https:\/\/doi.org\/10.1145\/1778765.1778779","journal-title":"ACM Transactions on Graphics"},{"issue":"1","key":"1540_CR76","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/TAC.2002.806653","volume":"48","author":"ER Westervelt","year":"2003","unstructured":"Westervelt, E. R., Grizzle, J. W., & Koditschek, D. E. (2003). Hybrid zero dynamics of planar biped walkers. IEEE Transactions on Automatic Control, 48(1), 42\u201356. https:\/\/doi.org\/10.1109\/TAC.2002.806653","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"3","key":"1540_CR77","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/LRA.2018.2798285","volume":"3","author":"AW Winkler","year":"2018","unstructured":"Winkler, A. W., Bellicoso, C. D., Hutter, M., & Buchli, J. (2018). Gait and trajectory optimization for legged systems through phase-based end-effector parameterization. IEEE Robotics and Automation Letters, 3(3), 1560\u20131567.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1540_CR78","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., & Sheikh, Y. (2019). Monocular total capture: Posing face, body, and hands in the wild. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10965\u201310974).","DOI":"10.1109\/CVPR.2019.01122"},{"key":"1540_CR79","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., & Fox, D. (2017). Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. CoRR. arXiv:1711.00199","DOI":"10.15607\/RSS.2018.XIV.019"},{"issue":"9","key":"1540_CR80","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","volume":"34","author":"B Yao","year":"2012","unstructured":"Yao, B., & Fei-Fei, L. (2012). Recognizing human\u2013object interactions in still images by modeling the mutual context of objects and human poses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1691\u20131703.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1540_CR81","doi-asserted-by":"crossref","unstructured":"Zanfir, A., Marinoiu, E., & Sminchisescu, C. (2018). Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2148\u20132157).","DOI":"10.1109\/CVPR.2018.00229"},{"key":"1540_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhu, M., Leonardos, S., Derpanis, K. G., & Daniilidis, K. (2016). Sparseness meets deepness: 3d human pose estimation from monocular video. In CVPR.","DOI":"10.1109\/CVPR.2016.537"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01540-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01540-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01540-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T10:20:13Z","timestamp":1645006813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01540-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,4]]},"references-count":82,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1540"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01540-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,4]]},"assertion":[{"value":"21 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}