{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:29:38Z","timestamp":1750746578302,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198021"},{"type":"electronic","value":"9783031198038"}],"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\/978-3-031-19803-8_42","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T13:05:16Z","timestamp":1666443916000},"page":"716-732","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Learning Uncoupled-Modulation CVAE for\u00a03D Action-Conditioned Human Motion Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0020-1892","authenticated-orcid":false,"given":"Chongyang","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8938-5071","authenticated-orcid":false,"given":"Lei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-7518","authenticated-orcid":false,"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7228-9646","authenticated-orcid":false,"given":"Shihong","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"42_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: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5915\u20135920. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2Pose: natural language grounded pose forecasting. In: 2019 International Conference on 3D Vision (3DV), pp. 719\u2013728. IEEE (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via GAN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1418\u20131427 (2018)","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Brand, M., Hertzmann, A.: Style machines. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 183\u2013192 (2000)","DOI":"10.1145\/344779.344865"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, X., Xu, W., Wang, T., Chu, W.: Variational semi-supervised aspect-term sentiment analysis via transformer. arXiv preprint arXiv:1810.10437 (2018)","DOI":"10.18653\/v1\/K19-1090"},{"key":"42_CR6","unstructured":"Clavet, S.: Motion matching and the road to next-gen animation. In: Proceedings of the GDC (2016)"},{"key":"42_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":"42_CR8","doi-asserted-by":"crossref","unstructured":"Cui, Q., Sun, H., Yang, F.: Learning dynamic relationships for 3D human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6519\u20136527 (2020)","DOI":"10.1109\/CVPR42600.2020.00655"},{"key":"42_CR9","unstructured":"Fang, L., Zeng, T., Liu, C., Bo, L., Dong, W., Chen, C.: Transformer-based conditional variational autoencoder for controllable story generation. arXiv preprint arXiv:2101.00828 (2021)"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2Motion: conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Holden, D., Kanoun, O., Perepichka, M., Popa, T.: Learned motion matching. ACM Trans. Graph. 39(4), 53:1\u201353:12 (2020)","DOI":"10.1145\/3386569.3392440"},{"issue":"4","key":"42_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073663","volume":"36","author":"D Holden","year":"2017","unstructured":"Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. ACM Trans. Graph. 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"42_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925975","volume":"35","author":"D Holden","year":"2016","unstructured":"Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph."},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5308\u20135317 (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Ji, Y., Xu, F., Yang, Y., Shen, F., Shen, H.T., Zheng, W.S.: A large-scale RGB-D database for arbitrary-view human action recognition. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1510\u20131518 (2018)","DOI":"10.1145\/3240508.3240675"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, J., Xia, G.G., Carlton, D.B., Anderson, C.N., Miyakawa, R.H.: Transformer VAE: a hierarchical model for structure-aware and interpretable music representation learning. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 516\u2013520. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Babu, R.V.: BiHMP-GAN: bidirectional 3D human motion prediction GAN. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8553\u20138560 (2019)","DOI":"10.1609\/aaai.v33i01.33018553"},{"key":"42_CR18","unstructured":"Lee, H.Y., et al.: Dancing to music. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"42_CR19","unstructured":"Li, J., et al.: Learning to generate diverse dance motions with transformer. arXiv preprint arXiv:2008.08171 (2020)"},{"key":"42_CR20","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":"42_CR21","unstructured":"Lin, X., Amer, M.R.: Human motion modeling using DVGANs. arXiv preprint arXiv:1804.10652 (2018)"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Ling, H.Y., Zinno, F., Cheng, G., Van De Panne, M.: Character controllers using motion VAEs. ACM Trans. Graph. 39(4), 40:1\u201340:12 (2020)","DOI":"10.1145\/3386569.3392422"},{"issue":"6","key":"42_CR23","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. 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph."},{"key":"42_CR24","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"42_CR25","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":"42_CR26","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"},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2891\u20132900 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Mason, I., Starke, S., Komura, T.: Real-time style modelling of human locomotion via feature-wise transformations and local motion phases. arXiv preprint arXiv:2201.04439 (2022)","DOI":"10.1145\/3522618"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"42_CR31","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 the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 36(6) (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Sofianos, T., Sampieri, A., Franco, L., Galasso, F.: Space-time-separable graph convolutional network for pose forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11209\u201311218 (2021)","DOI":"10.1109\/ICCV48922.2021.01102"},{"key":"42_CR35","doi-asserted-by":"crossref","unstructured":"Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. ACM Trans. Graph. 38(6), 178:1\u2013178:14 (2019)","DOI":"10.1145\/3355089.3356505"},{"key":"42_CR36","doi-asserted-by":"crossref","unstructured":"Starke, S., Zhao, Y., Komura, T., Zaman, K.: Local motion phases for learning multi-contact character movements. ACM Trans. Graph. 39(4), 54:1\u201354:13 (2020)","DOI":"10.1145\/3386569.3392450"},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6924\u20136932 (2017)","DOI":"10.1109\/CVPR.2017.437"},{"key":"42_CR38","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3332\u20133341 (2017)","DOI":"10.1109\/ICCV.2017.361"},{"issue":"2","key":"42_CR39","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TPAMI.2007.1167","volume":"30","author":"JM Wang","year":"2007","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 283\u2013298 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"42_CR40","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TVCG.2019.2938520","volume":"27","author":"Z Wang","year":"2019","unstructured":"Wang, Z., Chai, J., Xia, S.: Combining recurrent neural networks and adversarial training for human motion synthesis and control. IEEE Trans. Visual Comput. Graphics 27(1), 14\u201328 (2019)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"issue":"4","key":"42_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2766999","volume":"34","author":"S Xia","year":"2015","unstructured":"Xia, S., Wang, C., Chai, J., Hodgins, J.: Realtime style transfer for unlabeled heterogeneous human motion. ACM Trans. Graph. 34(4), 1\u201310 (2015)","journal-title":"ACM Trans. Graph."},{"key":"42_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58545-7_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Kitani, K.: DLow: diversifying latent flows for diverse human motion prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 346\u2013364. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_20"},{"issue":"4","key":"42_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201366","volume":"37","author":"H Zhang","year":"2018","unstructured":"Zhang, H., Starke, S., Komura, T., Saito, J.: Mode-adaptive neural networks for quadruped motion control. ACM Trans. Graph. 37(4), 1\u201311 (2018)","journal-title":"ACM Trans. Graph."},{"key":"42_CR44","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2022.08.075","volume":"511","author":"C Zhong","year":"2022","unstructured":"Zhong, C., Hu, L., Xia, S.: Spatial\u2013temporal modeling for prediction of stylized human motion. Neurocomputing 511, 34\u201342 (2022)","journal-title":"Neurocomputing"},{"key":"42_CR45","doi-asserted-by":"crossref","unstructured":"Zhong, C., Hu, L., Zhang, Z., Ye, Y., Xia, S.: Spatio-temporal gating-adjacency GCN for human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6447\u20136456 (2022)","DOI":"10.1109\/CVPR52688.2022.00634"},{"key":"42_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/978-3-030-58568-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Zou","year":"2020","unstructured":"Zou, S., et al.: 3D human shape reconstruction from a polarization image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 351\u2013368. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_21"}],"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\/978-3-031-19803-8_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T14:11:42Z","timestamp":1682604702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19803-8_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198021","9783031198038"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19803-8_42","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":"23 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)"}}]}}