{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:48:28Z","timestamp":1732042108049},"publisher-location":"Cham","reference-count":113,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200700"},{"type":"electronic","value":"9783031200717"}],"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\/978-3-031-20071-7_33","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T05:15:09Z","timestamp":1668230109000},"page":"557-577","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["HuMMan: Multi-modal 4D Human Dataset for\u00a0Versatile Sensing and\u00a0Modeling"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-1810-3855","authenticated-orcid":false,"given":"Zhongang","family":"Cai","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8449-3038","authenticated-orcid":false,"given":"Daxuan","family":"Ren","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3783-0679","authenticated-orcid":false,"given":"Ailing","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4173-9752","authenticated-orcid":false,"given":"Zhengyu","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3818-5069","authenticated-orcid":false,"given":"Tao","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0121-3852","authenticated-orcid":false,"given":"Wenjia","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3446-524X","authenticated-orcid":false,"given":"Xiangyu","family":"Fan","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6505-7081","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5290-8278","authenticated-orcid":false,"given":"Yifan","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1821-4296","authenticated-orcid":false,"given":"Liang","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2412-1141","authenticated-orcid":false,"given":"Fangzhou","family":"Hong","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8212-715X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-0571-5924","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,13]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1446\u20131455 (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Magnor, M., Xu, W., Theobalt, C., Pons-Moll, G.: Video based reconstruction of 3D people models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8387\u20138397 (2018)","DOI":"10.1109\/CVPR.2018.00875"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5167\u20135176 (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"33_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58536-5_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"BL Bhatnagar","year":"2020","unstructured":"Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Combining implicit function learning and parametric models for 3D human reconstruction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 311\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_19"},{"key":"33_CR6","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 \u2013 ECCV 2016","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"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Bogo, F., Romero, J., Pons-Moll, G., Black, M.J.: Dynamic FAUST: registering human bodies in motion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6233\u20136242 (2017)","DOI":"10.1109\/CVPR.2017.591"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"33_CR9","unstructured":"Cai, Z., et al.: Playing for 3D human recovery. arXiv preprint arXiv:2110.07588 (2021)"},{"key":"33_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58452-8_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Cao","year":"2020","unstructured":"Cao, Z., Gao, H., Mangalam, K., Cai, Q.-Z., Vo, M., Malik, J.: Long-term human motion prediction with scene context. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_23"},{"key":"33_CR11","unstructured":"Carreira, J., Noland, E., Hillier, C., Zisserman, A.: A short note on the kinetics-700 human action dataset. arXiv preprint arXiv:1907.06987 (2019)"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G.G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Lee, K.M.: Beyond static features for temporally consistent 3D human pose and shape from a video. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"33_CR14","unstructured":"Choi, S., Zhou, Q.Y., Koltun, V.: Robust reconstruction of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5556\u20135565 (2015)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Chung, J., Wuu, C.H., Yang, H.R., Tai, Y.W., Tang, C.K.: HAA500: human-centric atomic action dataset with curated videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13465\u201313474 (2021)","DOI":"10.1109\/ICCV48922.2021.01321"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"issue":"8","key":"33_CR18","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"Y Furukawa","year":"2010","unstructured":"Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1362\u20131376 (2010). https:\/\/doi.org\/10.1109\/TPAMI.2009.161","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR19","doi-asserted-by":"publisher","unstructured":"Gal, R., Wexler, Y., Ofek, E., Hoppe, H., Cohen-Or, D.: Seamless montage for texturing models. In: Computer Graphics Forum, vol. 29, no. 2, pp. 479\u2013486 (2010). https:\/\/doi.org\/10.1111\/j.1467-8659.2009.01617.x. https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/j.1467-8659.2009.01617.x","DOI":"10.1111\/j.1467-8659.2009.01617.x"},{"key":"33_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-030-58520-4_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Georgakis","year":"2020","unstructured":"Georgakis, G., Li, R., Karanam, S., Chen, T., Ko\u0161eck\u00e1, J., Wu, Z.: Hierarchical kinematic human mesh recovery. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 768\u2013784. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_45"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Guler, R.A., Kokkinos, I.: HoloPose: holistic 3D human reconstruction in-the-wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10884\u201310894 (2019)","DOI":"10.1109\/CVPR.2019.01114"},{"issue":"4","key":"33_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459749","volume":"40","author":"M Habermann","year":"2021","unstructured":"Habermann, M., Liu, L., Xu, W., Zollhoefer, M., Pons-Moll, G., Theobalt, C.: Real-time deep dynamic characters. ACM Trans. Graph. (TOG) 40(4), 1\u201316 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"2","key":"33_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3311970","volume":"38","author":"M Habermann","year":"2019","unstructured":"Habermann, M., Xu, W., Zollhoefer, M., Pons-Moll, G., Theobalt, C.: LiveCap: real-time human performance capture from monocular video. ACM Trans. Graph. (TOG) 38(2), 1\u201317 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Habermann, M., Xu, W., Zollhofer, M., Pons-Moll, G., Theobalt, C.: DeepCap: monocular human performance capture using weak supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5052\u20135063 (2020)","DOI":"10.1109\/CVPR42600.2020.00510"},{"issue":"2","key":"33_CR26","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1023\/B:AIRE.0000045502.10941.a9","volume":"22","author":"V Hodge","year":"2004","unstructured":"Hodge, V., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85\u2013126 (2004). https:\/\/doi.org\/10.1023\/B:AIRE.0000045502.10941.a9","journal-title":"Artif. Intell. Rev."},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Zhang, J.: Jointly learning heterogeneous features for RGB-D activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5344\u20135352 (2015)","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Huang, F., Zeng, A., Liu, M., Lai, Q., Xu, Q.: DeepFuse: an IMU-aware network for real-time 3D human pose estimation from multi-view image. arXiv preprint arXiv:1912.04071 (2019)","DOI":"10.1109\/WACV45572.2020.9093526"},{"issue":"7","key":"33_CR29","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7718\u20137727 (2019)","DOI":"10.1109\/ICCV.2019.00781"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Izadi, S., et al.: KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, pp. 559\u2013568 (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, H., Cai, J., Zheng, J.: Skeleton-aware 3D human shape reconstruction from point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5431\u20135441 (2019)","DOI":"10.1109\/ICCV.2019.00553"},{"key":"33_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-030-58545-7_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Whole-body human pose estimation in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 196\u2013214. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_12"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3334\u20133342 (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019)","DOI":"10.1109\/CVPR.2019.00576"},{"issue":"13","key":"33_CR38","doi-asserted-by":"publisher","first-page":"109730","DOI":"10.1016\/j.celrep.2021.109730","volume":"36","author":"P Karashchuk","year":"2021","unstructured":"Karashchuk, P., et al.: Anipose: a toolkit for robust markerless 3D pose estimation. Cell Rep. 36(13), 109730 (2021)","journal-title":"Cell Rep."},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"33_CR40","doi-asserted-by":"publisher","unstructured":"Kazhdan, M., Hoppe, H.: Screened Poisson surface reconstruction. ACM Trans. Graph. 32(3) (2013). https:\/\/doi.org\/10.1145\/2487228.2487237","DOI":"10.1145\/2487228.2487237"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Kazhdan, M., Chuang, M., Rusinkiewicz, S., Hoppe, H.: Poisson surface reconstruction with envelope constraints. In: Computer Graphics Forum (Proceedings of the Symposium on Geometry Processing), vol. 39, no. 5, July 2020","DOI":"10.1111\/cgf.14077"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Kazhdan, M., Chuang, M., Rusinkiewicz, S., Hoppe, H.: Poisson surface reconstruction with envelope constraints. In: Computer Graphics Forum, vol. 39, pp. 173\u2013182. Wiley Online Library (2020)","DOI":"10.1111\/cgf.14077"},{"key":"33_CR43","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":"33_CR44","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3D human body estimation. arXiv preprint arXiv:2104.08527 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"33_CR46","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"33_CR47","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Human pose regression with residual log-likelihood estimation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: HybrIK: a hybrid analytical-neural inverse kinematics solution for 3D human pose and shape estimation. In: CVPR, pp. 3383\u20133393. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13401\u201313412 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 9\u201314. IEEE (2010)","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"33_CR51","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: HAKE: a knowledge engine foundation for human activity understanding (2022)","DOI":"10.1109\/TPAMI.2022.3232797"},{"key":"33_CR52","doi-asserted-by":"publisher","unstructured":"Li, Z., Yu, T., Zheng, Z., Liu, Y.: Robust and accurate 3D self-portraits in seconds. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3113164","DOI":"10.1109\/TPAMI.2021.3113164"},{"key":"33_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"33_CR54","doi-asserted-by":"crossref","unstructured":"Liu, G., Rong, Y., Sheng, L.: VoteHMR: occlusion-aware voting network for robust 3D human mesh recovery from partial point clouds. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 955\u2013964 (2021)","DOI":"10.1145\/3474085.3475309"},{"issue":"10","key":"33_CR55","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR56","doi-asserted-by":"publisher","unstructured":"Lombardi, S., Saragih, J., Simon, T., Sheikh, Y.: Deep appearance models for face rendering 37(4) (2018). https:\/\/doi.org\/10.1145\/3197517.3201401","DOI":"10.1145\/3197517.3201401"},{"issue":"6","key":"33_CR57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2661229.2661273","volume":"33","author":"M Loper","year":"2014","unstructured":"Loper, M., Mahmood, N., Black, M.J.: MoSh: motion and shape capture from sparse markers. ACM Trans. Graph. (TOG) 33(6), 1\u201313 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"33_CR58","doi-asserted-by":"publisher","first-page":"1","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.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR59","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":"33_CR60","doi-asserted-by":"crossref","unstructured":"Ma, Q., et al.: Learning to dress 3D people in generative clothing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6469\u20136478 (2020)","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"33_CR61","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"33_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T von Marcard","year":"2018","unstructured":"von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 614\u2013631. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37"},{"key":"33_CR63","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"33_CR64","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"33_CR65","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: XNect: real-time multi-person 3D motion capture with a single RGB camera. ACM Trans. Graph. (TOG) 39(4), 82-1 (2020)","DOI":"10.1145\/3386569.3392410"},{"key":"33_CR66","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"issue":"2","key":"33_CR67","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2019","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 502\u2013508 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR68","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":"33_CR69","doi-asserted-by":"crossref","unstructured":"Muller, L., Osman, A.A., Tang, S., Huang, C.H.P., Black, M.J.: On self-contact and human pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9990\u20139999 (2021)","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"33_CR70","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Fox, D., Seitz, S.M.: DynamicFusion: reconstruction and tracking of non-rigid scenes in real-time. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 343\u2013352 (2015)","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"33_CR71","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"},{"key":"33_CR72","doi-asserted-by":"crossref","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., Schiele, B.: Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: 2018 International Conference on 3D Vision (3DV), pp. 484\u2013494. IEEE (2018)","DOI":"10.1109\/3DV.2018.00062"},{"key":"33_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-030-58539-6_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"AAA Osman","year":"2020","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598\u2013613. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36"},{"key":"33_CR74","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13468\u201313478 (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"33_CR75","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":"33_CR76","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"33_CR77","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"33_CR78","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Neural body: implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"33_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"key":"33_CR80","doi-asserted-by":"crossref","unstructured":"Qiu, H., Wang, C., Wang, J., Wang, N., Zeng, W.: Cross view fusion for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4342\u20134351 (2019)","DOI":"10.1109\/ICCV.2019.00444"},{"key":"33_CR81","doi-asserted-by":"crossref","unstructured":"Raj, A., Tanke, J., Hays, J., Vo, M., Stoll, C., Lassner, C.: ANR-articulated neural rendering for virtual avatars. arXiv:2012.12890 (2020)","DOI":"10.1109\/CVPR46437.2021.00372"},{"key":"33_CR82","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 International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"33_CR83","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"33_CR84","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"33_CR85","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. arXiv preprint arXiv:1912.06971 (2019)","DOI":"10.1109\/TIP.2020.3028207"},{"key":"33_CR86","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans. Image Process. 29, 9532\u20139545 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR87","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"33_CR88","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"33_CR89","doi-asserted-by":"crossref","unstructured":"Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T.: Human mesh recovery from monocular images via a skeleton-disentangled representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5349\u20135358 (2019)","DOI":"10.1109\/ICCV.2019.00545"},{"key":"33_CR90","doi-asserted-by":"publisher","unstructured":"Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. 38(4) (2019). https:\/\/doi.org\/10.1145\/3306346.3323035","DOI":"10.1145\/3306346.3323035"},{"key":"33_CR91","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"33_CR92","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"33_CR93","doi-asserted-by":"crossref","unstructured":"Trivedi, N., Thatipelli, A., Sarvadevabhatla, R.K.: NTU-X: an enhanced large-scale dataset for improving pose-based recognition of subtle human actions. arXiv preprint arXiv:2101.11529 (2021)","DOI":"10.1145\/3490035.3490270"},{"key":"33_CR94","doi-asserted-by":"crossref","unstructured":"Trumble, M., Gilbert, A., Malleson, C., Hilton, A., Collomosse, J.P.: Total capture: 3D human pose estimation fusing video and inertial sensors. In: BMVC, vol. 2, pp. 1\u201313 (2017)","DOI":"10.5244\/C.31.14"},{"key":"33_CR95","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"836","DOI":"10.1007\/978-3-319-10602-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Waechter","year":"2014","unstructured":"Waechter, M., Moehrle, N., Goesele, M.: Let there be color! Large-scale texturing of 3D reconstructions. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 836\u2013850. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_54"},{"key":"33_CR96","doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view action modeling, learning and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2649\u20132656 (2014)","DOI":"10.1109\/CVPR.2014.339"},{"key":"33_CR97","doi-asserted-by":"crossref","unstructured":"Wang, S., Geiger, A., Tang, S.: Locally aware piecewise transformation fields for 3D human mesh registration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7639\u20137648 (2021)","DOI":"10.1109\/CVPR46437.2021.00755"},{"key":"33_CR98","doi-asserted-by":"publisher","unstructured":"Xiang, D., et al.: Modeling clothing as a separate layer for an animatable human avatar. ACM Trans. Graph. 40(6) (2021). https:\/\/doi.org\/10.1145\/3478513.3480545","DOI":"10.1145\/3478513.3480545"},{"key":"33_CR99","doi-asserted-by":"crossref","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: GHUM & GHUML: generative 3D human shape and articulated pose models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6184\u20136193 (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"33_CR100","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1801.07455 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"33_CR101","doi-asserted-by":"crossref","unstructured":"Yu, T., Zheng, Z., Guo, K., Liu, P., Dai, Q., Liu, Y.: Function4D: real-time human volumetric capture from very sparse consumer RGBD sensors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021), June 2021","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"33_CR102","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: DoubleFusion: real-time capture of human performances with inner body shapes from a single depth sensor. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, pp. 7287\u20137296. IEEE, June 2018","DOI":"10.1109\/CVPR.2018.00761"},{"key":"33_CR103","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: HUMBI: a large multiview dataset of human body expressions. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2987\u20132997 (2020)","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"33_CR104","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/978-3-030-58568-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zeng","year":"2020","unstructured":"Zeng, A., Sun, X., Huang, F., Liu, M., Xu, Q., Lin, S.: SRNet: improving generalization in 3D human pose estimation with a split-and-recombine approach. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 507\u2013523. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_30"},{"key":"33_CR105","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Yang, L., Zhao, N., Liu, M., Xu, Q.: Learning skeletal graph neural networks for hard 3D pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"33_CR106","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. arXiv preprint arXiv:2112.13715 (2021)","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"33_CR107","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pujades, S., Black, M.J., Pons-Moll, G.: Detailed, accurate, human shape estimation from clothed 3D scan sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4191\u20134200 (2017)","DOI":"10.1109\/CVPR.2017.582"},{"key":"33_CR108","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., Derpanis, K.G.: From actemes to action: a strongly-supervised representation for detailed action understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2248\u20132255 (2013)","DOI":"10.1109\/ICCV.2013.280"},{"key":"33_CR109","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, Z., An, L., Li, M., Yu, T., Liu, Y.: Lightweight multi-person total motion capture using sparse multi-view cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5560\u20135569, October 2021","DOI":"10.1109\/ICCV48922.2021.00551"},{"issue":"11","key":"33_CR110","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330\u20131334 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR111","doi-asserted-by":"crossref","unstructured":"Zhao, H., Torralba, A., Torresani, L., Yan, Z.: HACS: human action clips and segments dataset for recognition and temporal localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8668\u20138678 (2019)","DOI":"10.1109\/ICCV.2019.00876"},{"key":"33_CR112","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"33_CR113","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: DeepHuman: 3D human reconstruction from a single image. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00783"}],"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\/978-3-031-20071-7_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T01:26:17Z","timestamp":1728350777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20071-7_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200700","9783031200717"],"references-count":113,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20071-7_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"13 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)"}}]}}