{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:57:14Z","timestamp":1777568234754,"version":"3.51.4"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198113","type":"print"},{"value":"9783031198120","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\/978-3-031-19812-0_25","type":"book-chapter","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T14:03:42Z","timestamp":1667052222000},"page":"425-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Pose2Room: Understanding 3D Scenes from\u00a0Human Activities"],"prefix":"10.1007","author":[{"given":"Yinyu","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angela","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,30]]},"reference":[{"key":"25_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3d point clouds. In: International Conference on Machine Learning. pp. 40\u201349. PMLR (2018)"},{"issue":"4","key":"25_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925893","volume":"35","author":"S Agrawal","year":"2016","unstructured":"Agrawal, S., van de Panne, M.: Task-based locomotion. ACM Trans. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR3","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":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chai, J., Hodgins, J.K.: Performance animation from low-dimensional control signals. In: ACM SIGGRAPH 2005 Papers, pp. 686\u2013696 (2005)","DOI":"10.1145\/1186822.1073248"},{"key":"25_CR5","unstructured":"Chao, Y.W., Yang, J., Chen, W., Deng, J.: Learning to sit: Synthesizing human-chair interactions via hierarchical control. arXiv preprint arXiv:1908.07423 (2019)"},{"key":"25_CR6","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":"25_CR7","doi-asserted-by":"crossref","unstructured":"Corona, E., Pumarola, A., Alenya, G., Moreno-Noguer, F.: Context-aware human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6992\u20137001 (2020)","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"25_CR8","unstructured":"Dahnert, M., Hou, J., Nie\u00dfner, M., Dai, A.: Panoptic 3d scene reconstruction from a single rgb image. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2021)"},{"issue":"4","key":"25_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3054739","volume":"36","author":"A Dai","year":"2017","unstructured":"Dai, A., Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Theobalt, C.: Bundlefusion: Real-time globally consistent 3d reconstruction using on-the-fly surface reintegration. ACM Trans. Graph. (ToG) 36(4), 1 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"25_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-642-33783-3_21","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Delaitre","year":"2012","unstructured":"Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.: Scene semantics from long-term observation of people. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 284\u2013298. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_21"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Deng, C., Litany, O., Duan, Y., Poulenard, A., Tagliasacchi, A., Guibas, L.: Vector neurons: a general framework for so(3)-equivariant networks. arXiv preprint arXiv:2104.12229 (2021)","DOI":"10.1109\/ICCV48922.2021.01198"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Deng, S., Xu, X., Wu, C., Chen, K., Jia, K.: 3d affordancenet: A benchmark for visual object affordance understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1778\u20131787 (2021)","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"25_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: Large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Rematas, K., Leibe, B., Ferrari, V.: From points to multi-object 3d reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4588\u20134597 (2021)","DOI":"10.1109\/CVPR46437.2021.00456"},{"issue":"6","key":"25_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818057","volume":"34","author":"M Fisher","year":"2015","unstructured":"Fisher, M., Savva, M., Li, Y., Hanrahan, P., Nie\u00dfner, M.: Activity-centric scene synthesis for functional 3d scene modeling. ACM Trans. Graph. (TOG) 34(6), 1\u201313 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-642-33715-4_53","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DF Fouhey","year":"2012","unstructured":"Fouhey, D.F., Delaitre, V., Gupta, A., Efros, A.A., Laptev, I., Sivic, J.: People watching: human actions as a cue for single view geometry. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 732\u2013745. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_53"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Fowler, S., Kim, H., Hilton, A.: Towards complete scene reconstruction from single-view depth and human motion. In: BMVC (2017)","DOI":"10.5244\/C.31.146"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Fowler, S., Kim, H., Hilton, A.: Human-centric scene understanding from single view 360 video. In: 2018 International Conference on 3D Vision (3DV), pp. 334\u2013342. IEEE (2018)","DOI":"10.1109\/3DV.2018.00046"},{"issue":"4","key":"25_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322957","volume":"38","author":"O Glauser","year":"2019","unstructured":"Glauser, O., Wu, S., Panozzo, D., Hilliges, O., Sorkine-Hornung, O.: Interactive hand pose estimation using a stretch-sensing soft glove. ACM Trans. Graph. (TOG) 38(4), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: CVPR 2011, pp. 1529\u20131536. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3d scene geometry to human workspace. In: CVPR 2011, pp. 1961\u20131968. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Guzov, V., Mir, A., Sattler, T., Pons-Moll, G.: Human poseitioning system (hps): 3d human pose estimation and self-localization in large scenes from body-mounted sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4318\u20134329 (2021)","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Hassan, M., et al.: Stochastic scene-aware motion prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11374\u201311384 (2021)","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3d human pose ambiguities with 3d scene constraints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2282\u20132292 (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3d scenes by learning human-scene interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14708\u201314718 (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"issue":"4","key":"25_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925870","volume":"35","author":"R Hu","year":"2016","unstructured":"Hu, R., van Kaick, O., Wu, B., Huang, H., Shamir, A., Zhang, H.: Learning how objects function via co-analysis of interactions. ACM Trans. Graph. (TOG) 35(4), 1\u201313 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-01234-2_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Huang","year":"2018","unstructured":"Huang, S., Qi, S., Zhu, Y., Xiao, Y., Xu, Y., Zhu, S.-C.: Holistic 3d scene parsing and reconstruction from a single RGB image. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 194\u2013211. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_12"},{"issue":"6","key":"25_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275108","volume":"37","author":"Y Huang","year":"2018","unstructured":"Huang, Y., Kaufmann, M., Aksan, E., Black, M.J., Hilliges, O., Pons-Moll, G.: Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time. ACM Trans. Graph. (TOG) 37(6), 1\u201315 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Koppula, H., Saxena, A.: Hallucinated humans as the hidden context for labeling 3d scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2993\u20133000 (2013)","DOI":"10.1109\/CVPR.2013.385"},{"issue":"10","key":"25_CR30","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1109\/TPAMI.2015.2501811","volume":"38","author":"Y Jiang","year":"2015","unstructured":"Jiang, Y., Koppula, H.S., Saxena, A.: Modeling 3d environments through hidden human context. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2040\u20132053 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR31","unstructured":"Jiang, Y., Lim, M., Saxena, A.: Learning object arrangements in 3d scenes using human context. arXiv preprint arXiv:1206.6462 (2012)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Kapadia, M., et al.: Precision: Precomputing environment semantics for contact-rich character animation. In: Proceedings of the 20th ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, pp. 29\u201337 (2016)","DOI":"10.1145\/2856400.2856404"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Kaufmann, M., et al.: Em-pose: 3d human pose estimation from sparse electromagnetic trackers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11510\u201311520 (2021)","DOI":"10.1109\/ICCV48922.2021.01131"},{"issue":"4","key":"25_CR34","first-page":"1","volume":"33","author":"VG Kim","year":"2014","unstructured":"Kim, V.G., Chaudhuri, S., Guibas, L., Funkhouser, T.: Shape2pose: Human-centric shape analysis. ACM Trans. Graph. (TOG) 33(4), 1\u201312 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-030-58580-8_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Kuo","year":"2020","unstructured":"Kuo, W., Angelova, A., Lin, T.-Y., Dai, A.: Mask2CAD: 3D shape prediction by learning to segment and retrieve. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 260\u2013277. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_16"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Kuo, W., Angelova, A., Lin, T.Y., Dai, A.: Patch2cad: Patchwise embedding learning for in-the-wild shape retrieval from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12589\u201312599 (2021)","DOI":"10.1109\/ICCV48922.2021.01236"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Lee, J., Chai, J., Reitsma, P.S., Hodgins, J.K., Pollard, N.S.: Interactive control of avatars animated with human motion data. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 491\u2013500 (2002)","DOI":"10.1145\/566570.566607"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Choi, M.G., Lee, J.: Motion patches: building blocks for virtual environments annotated with motion data. In: ACM SIGGRAPH 2006 Papers, pp. 898\u2013906 (2006)","DOI":"10.1145\/1141911.1141972"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Liu, H., Wei, X., Chai, J., Ha, I., Rhee, T.: Realtime human motion control with a small number of inertial sensors. In: Symposium on Interactive 3D Graphics and Games, pp. 133\u2013140 (2011)","DOI":"10.1145\/1944745.1944768"},{"key":"25_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-030-58568-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Mao","year":"2020","unstructured":"Mao, W., Liu, M., Salzmann, M.: History repeats itself: Human motion prediction via motion attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 474\u2013489. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_28"},{"issue":"4","key":"25_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386569.3392474","volume":"39","author":"J Merel","year":"2020","unstructured":"Merel, J., et al.: Catch & carry: reusable neural controllers for vision-guided whole-body tasks. ACM Trans. Graph. (TOG) 39(4), 1\u201339 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"25_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322961","volume":"38","author":"A Monszpart","year":"2019","unstructured":"Monszpart, A., Guerrero, P., Ceylan, D., Yumer, E., Mitra, N.J.: imapper: interaction-guided scene mapping from monocular videos. ACM Trans. Graph. (TOG) 38(4), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"5","key":"25_CR43","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Mura, C., Pajarola, R., Schindler, K., Mitra, N.: Walk2map: Extracting floor plans from indoor walk trajectories. In: Computer Graphics Forum, vol. 40, pp. 375\u2013388. Wiley Online Library (2021)","DOI":"10.1111\/cgf.142640"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., et alA.: Kinectfusion: Real-time dense surface mapping and tracking. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality, pp. 127\u2013136. IEEE (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J., Zhang, J.J.: Total3dunderstanding: Joint layout, object pose and mesh reconstruction for indoor scenes from a single image. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)","DOI":"10.1109\/CVPR42600.2020.00013"},{"issue":"6","key":"25_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2508363.2508374","volume":"32","author":"M Nie\u00dfner","year":"2013","unstructured":"Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Stamminger, M.: Real-time 3d reconstruction at scale using voxel hashing. ACM Trans. Graph. (ToG) 32(6), 1\u201311 (2013)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"25_CR48","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":"25_CR49","doi-asserted-by":"crossref","unstructured":"Pieropan, A., Ek, C.H., Kjellstr\u00f6m, H.: Functional object descriptors for human activity modeling. In: 2013 IEEE International Conference on Robotics and Automation, pp. 1282\u20131289. IEEE (2013)","DOI":"10.1109\/ICRA.2013.6630736"},{"key":"25_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/978-3-030-58536-5_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Popov","year":"2020","unstructured":"Popov, S., Bauszat, P., Ferrari, V.: CoReNet: coherent 3D scene reconstruction from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 366\u2013383. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_22"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Puig, X., et al.: Virtualhome: Simulating household activities via programs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8494\u20138502 (2018)","DOI":"10.1109\/CVPR.2018.00886"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3d object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"25_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-030-58555-6_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Qian","year":"2020","unstructured":"Qian, S., Jin, L., Fouhey, D.F.: Associative3D: Volumetric reconstruction from sparse views. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 140\u2013157. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_9"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Ruiz, E., Mayol-Cuevas, W.: Where can i do this? geometric affordances from a single example with the interaction tensor. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 2192\u20132199. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462835"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Runz, M., et al.: Frodo: From detections to 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14720\u201314729 (2020)","DOI":"10.1109\/CVPR42600.2020.01473"},{"issue":"6","key":"25_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2661229.2661230","volume":"33","author":"M Savva","year":"2014","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: Scenegrok: Inferring action maps in 3d environments. ACM Trans. Graph. (TOG) 33(6), 1\u201310 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"25_CR57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925867","volume":"35","author":"M Savva","year":"2016","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: Pigraphs: learning interaction snapshots from observations. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Srikantha, A., Gall, J.: Weakly supervised affordance detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2795\u20132804 (2017)","DOI":"10.1109\/CVPR.2017.552"},{"issue":"11","key":"25_CR59","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1016\/j.imavis.2014.07.003","volume":"32","author":"M Shoaib","year":"2014","unstructured":"Shoaib, M., Yang, M.Y., Rosenhahn, B., Ostermann, J.: Estimating layout of cluttered indoor scenes using trajectory-based priors. Image Vis. Comput. 32(11), 870\u2013883 (2014)","journal-title":"Image Vis. Comput."},{"issue":"5","key":"25_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1409060.1409067","volume":"27","author":"HP Shum","year":"2008","unstructured":"Shum, H.P., Komura, T., Shiraishi, M., Yamazaki, S.: Interaction patches for multi-character animation. ACM Trans. Graph. (TOG) 27(5), 1\u20138 (2008)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"25_CR61","doi-asserted-by":"publisher","first-page":"1","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), 1\u2013209 (2019)","journal-title":"ACM Trans. Graph."},{"key":"25_CR62","doi-asserted-by":"crossref","unstructured":"Von Marcard, T., Rosenhahn, B., Black, M.J., Pons-Moll, G.: Sparse inertial poser: Automatic 3d human pose estimation from sparse imus. In: Computer Graphics Forum, vol. 36, pp. 349\u2013360. Wiley Online Library (2017)","DOI":"10.1111\/cgf.13131"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, H., Xu, J., Liu, S., Wang, X.: Synthesizing long-term 3d human motion and interaction in 3d scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9401\u20139411 (2021)","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, L., Rathore, S., Shin, D., Fowlkes, C.: Geometric pose affordance: 3d human pose with scene constraints. arXiv preprint arXiv:1905.07718 (2019)","DOI":"10.1007\/978-3-031-25075-0_1"},{"issue":"6","key":"25_CR65","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1109\/TPAMI.2016.2574712","volume":"39","author":"P Wei","year":"2016","unstructured":"Wei, P., Zhao, Y., Zheng, N., Zhu, S.C.: Modeling 4d human-object interactions for joint event segmentation, recognition, and object localization. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1165\u20131179 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Whelan, T., Leutenegger, S., Salas-Moreno, R., Glocker, B., Davison, A.: Elasticfusion: Dense slam without a pose graph. Robotics: Science and Systems (2015)","DOI":"10.15607\/RSS.2015.XI.001"},{"key":"25_CR67","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., Tenenbaum, J.B.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 82\u201390 (2016)"},{"key":"25_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/978-3-030-58548-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Wu","year":"2020","unstructured":"Wu, R., Chen, X., Zhuang, Y., Chen, B.: Multimodal shape completion via conditional generative adversarial networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 281\u2013296. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_17"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"25_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) (2022)","DOI":"10.1109\/CVPR52688.2022.00393"},{"key":"25_CR71","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"25_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cui, Z., Zhang, Y., Zeng, B., Pollefeys, M., Liu, S.: Holistic 3d scene understanding from a single image with implicit representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8833\u20138842 (June 2021)","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"25_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Ma, Q., Black, M.J., Tang, S.: Place: Proximity learning of articulation and contact in 3d environments. In: 2020 International Conference on 3D Vision (3DV), pp. 642\u2013651. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"25_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hassan, M., Neumann, H., Black, M.J., Tang, S.: Generating 3d people in scenes without people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6194\u20136204 (2020)","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"25_CR75","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, Y., Chun Zhu, S.: Understanding tools: Task-oriented object modeling, learning and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2855\u20132864 (2015)","DOI":"10.1109\/CVPR.2015.7298903"}],"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\/978-3-031-19812-0_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T13:08:42Z","timestamp":1682600922000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19812-0_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198113","9783031198120"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19812-0_25","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":"30 October 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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}