{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:43:00Z","timestamp":1779295380493,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200670","type":"print"},{"value":"9783031200687","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\/978-3-031-20068-7_18","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:06:38Z","timestamp":1668067598000},"page":"311-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Compositional Human-Scene Interaction Synthesis with\u00a0Semantic Control"],"prefix":"10.1007","author":[{"given":"Kaifeng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaofei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thabo","family":"Beeler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2action: generative adversarial synthesis from language to action. In: Proceedings of ICRA. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2pose: natural language grounded pose forecasting. In: Proceedings of 3DV. IEEE (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3d human pose reconstruction. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Rematas, K., Leibe, B., Ferrari, V.: From points to multi-object 3D reconstruction. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00456"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., Van Gool, L.: What makes a chair a chair? In: Proceedings of CVPR. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"18_CR7","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.: Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1775\u20131789 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3d scene geometry to human workspace. In: Proceedings of CVPR. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Hassan, M., et al.: Stochastic scene-aware motion prediction. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"18_CR10","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 ICCV (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"18_CR11","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 CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"18_CR12","unstructured":"Hu, R., et al.: Predictive and generative neural networks for object functionality. arXiv preprint. arXiv:2006.15520 (2020)"},{"issue":"1","key":"18_CR13","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR14","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint. arXiv:1705.06950 (2017)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Kim, V.G., Chaudhuri, S., Guibas, L.J., Funkhouser, T.: Shape2pose: human-centric shape analysis. In: ACM Transactions on Graphics, (Proceedings SIGGRAPH) (2014)","DOI":"10.1145\/2601097.2601117"},{"key":"18_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint. arXiv:1312.6114 (2013)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, S., Kim, K., Wang, X., Yang, M.H., Kautz, J.: Putting humans in a scene: learning affordance in 3d indoor environments. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.01265"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Lieber, R., Stekauer, P.: The Oxford Handbook of Compounding (2011)","DOI":"10.1093\/oxfordhb\/9780199695720.001.0001"},{"key":"18_CR19","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 ICCV (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Mandery, C., Terlemez, O., Do, M., Vahrenkamp, N., Asfour, T.: The kit whole-body human motion database. In: Proceedings of ICAR (2015)","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Mineshima, K., Mart\u00ednez-G\u00f3mez, P., Miyao, Y., Bekki, D.: Higher-order logical inference with compositional semantics. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (2015)","DOI":"10.18653\/v1\/D15-1244"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Mitchell, J., Lapata, M.: Vector-based models of semantic composition. In: Proceedings of ACL (2008)","DOI":"10.3115\/1699510.1699567"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3d human motion synthesis with transformer vae. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"18_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/9781316771402","volume-title":"Word-formation in English","author":"I Plag","year":"2018","unstructured":"Plag, I.: Word-formation in English. Cambridge University Press, Cambridge (2018)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: BABEL: bodies, action and behavior with english labels. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"18_CR27","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv preprint. arXiv:1706.02413 (2017)"},{"key":"18_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/978-3-030-01219-9_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Ranjan","year":"2018","unstructured":"Ranjan, A., Bolkart, T., Sanyal, S., Black, M.J.: Generating 3D faces using convolutional mesh autoencoders. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 725\u2013741. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_43"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. California Univ San Diego La Jolla Inst for Cognitive Science. Technical report (1985)","DOI":"10.21236\/ADA164453"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: Scenegrok: inferring action maps in 3d environments. In: ACM Transactions on Graphics (TOG), (Proceedings SIGGRAPH), vol. 33, no. 6, pp. 1\u201310 (2014)","DOI":"10.1145\/2661229.2661230"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: PiGraphs: learning interaction snapshots from observations. In: ACM Transactions on Graphics, (Proceedings SIGGRAPH), vol. 35, no. 4 (2016)","DOI":"10.1145\/2897824.2925867"},{"key":"18_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of NeurIPS (2014)"},{"key":"18_CR33","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Proceedings of NeurIPS (2015)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. In: ACM Transactions Graphics (ACM SIGGRAPH Asia) (2019)","DOI":"10.1145\/3355089.3356505"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: exposing human motion generation to clip space. arXiv preprint. arXiv:2203.08063 (2022)","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"18_CR36","unstructured":"De la Torre, F., Hodgins, J., Bargteil, A., Martin, X., Macey, J., Collado, A., Beltran, P.: Guide to the carnegie mellon university multimodal activity (cmu-mmac) database (2009)"},{"key":"18_CR37","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 CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"18_CR38","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1167\/2.5.2","volume":"2","author":"NF Troje","year":"2002","unstructured":"Troje, N.F.: Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. J. Vis. 2, 371\u2013387 (2002)","journal-title":"J. Vis."},{"key":"18_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS (2017)"},{"key":"18_CR40","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 CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Wang, J., Rong, Y., Liu, J., Yan, S., Lin, D., Dai, B.: Towards diverse and natural scene-aware 3d human motion synthesis. In: Proceedings of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Yin, D., Meng, T., Chang, K.W.: Sentibert: a transferable transformer-based architecture for compositional sentiment semantics. arXiv preprint. arXiv:2005.04114 (2020)","DOI":"10.18653\/v1\/2020.acl-main.341"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Bogo, F., Marc, P., Tang, S.: Learning motion priors for 4d human body capture in 3d scenes. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01115"},{"key":"18_CR45","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: Proceedings of 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"18_CR46","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 CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00623"}],"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\/978-3-031-20068-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:14:50Z","timestamp":1668068090000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20068-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200670","9783031200687"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20068-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}