{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:51:39Z","timestamp":1784544699142,"version":"3.55.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200465","type":"print"},{"value":"9783031200472","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\/978-3-031-20047-2_28","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T10:02:55Z","timestamp":1666432975000},"page":"480-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":343,"title":["TEMOS: Generating Diverse Human Motions from\u00a0Textual Descriptions"],"prefix":"10.1007","author":[{"given":"Mathis","family":"Petrovich","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"28_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: International Conference on Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2Pose: natural language grounded pose forecasting. In: International Conference on 3D Vision (3DV) (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Hilliges, O.: Structured prediction helps 3D human motion modelling. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00724"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via GAN. In: Computer Vision and Pattern Recognition Workshops (CVPRW) (2018)","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Childs, E., Rewkowski, N., Manocha, D.: Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning (2021)","DOI":"10.1145\/3474085.3475223"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.: Capture, learning, and synthesis of 3D speaking styles. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"28_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (NAACL) (2019)"},{"key":"28_CR9","unstructured":"Duan, Y., et al.: Single-shot motion completion with transformer. arXiv preprint arXiv:2103.00776 (2021)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: FaceFormer: speech-driven 3D facial animation with transformers. In: Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Gao, T., Dontcheva, M., Adar, E., Liu, Z., Karahalios, K.G.: DataTone: managing ambiguity in natural language interfaces for data visualization. In: ACM Symposium on User Interface Software & Technology (2015)","DOI":"10.1145\/2807442.2807478"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2Motion: conditioned generation of 3D human motions. In: ACM International Conference on Multimedia (ACMMM) (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Habibie, I., Holden, D., Schwarz, J., Yearsley, J., Komura, T.: A recurrent variational autoencoder for human motion synthesis. In: British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.119"},{"key":"28_CR16","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1145\/3386569.3392480","volume":"39","author":"FG Harvey","year":"2020","unstructured":"Harvey, F.G., Yurick, M., Nowrouzezahrai, D., Pal, C.: Robust motion in-betweening. ACM Trans. Graph. (TOG) 39, 60\u201361 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417836","volume":"39","author":"GE Henter","year":"2020","unstructured":"Henter, G.E., Alexanderson, S., Beskow, J.: MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. (TOG) 39, 1\u201314 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR18","unstructured":"Hill, I.: Natural language versus computer language. In: Designing for Human-Computer Communication (1983)"},{"key":"28_CR19","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. (TOG) 35, 1\u201314 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. In: International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"28_CR21","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human36M: large scale datasets and predictive methods for 3D human sensing in natural environments. Trans. Pattern Anal. Mach. Intell. (TPAMI). 36, 1325\u20131349 (2014)","journal-title":"Trans. Pattern Anal. Mach. Intell. (TPAMI)."},{"key":"28_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073658","volume":"36","author":"T Karras","year":"2017","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A., Lehtinen, J.: Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans. Graph. (TOG) 36, 1\u20132 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"28_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"28_CR25","unstructured":"Lee, H.Y., et al.: Dancing to music. In: Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"28_CR26","unstructured":"Li, J., et al.: Learning to generate diverse dance motions with transformer. arXiv preprint arXiv:2008.08171 (2020)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: Music conditioned 3D dance generation with AIST++. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"28_CR28","unstructured":"Lin, A.S., Wu, L., Corona, R., Tai, K., Huang, Q., Mooney, R.J.: Generating animated videos of human activities from natural language descriptions. In: Visually Grounded Interaction and Language (ViGIL) NeurIPS Workshop (2018)"},{"key":"28_CR29","unstructured":"Lin, X., Amer, M.: Human motion modeling using DVGANs. arXiv preprint arXiv:1804.10652 (2018)"},{"key":"28_CR30","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, 1\u20136 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"28_CR32","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: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Mandery, C., Terlemez, O., Do, M., Vahrenkamp, N., Asfour, T.: The kit whole-body human motion database. In: International Conference on Advanced Robotics (ICAR) (2015)","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"28_CR35","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Neural Information Processing Systems (NeurIPS) (2013)"},{"key":"28_CR36","unstructured":"Pavllo, D., Grangier, D., Auli, M.: QuaterNet: A quaternion-based recurrent model for human motion. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"28_CR37","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS project page: generating diverse human motions from textual descriptions. https:\/\/mathis.petrovich.fr\/temos\/"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"28_CR39","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1089\/big.2016.0028","volume":"4","author":"M Plappert","year":"2016","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The KIT motion-language dataset. Big Data. 4, 236\u2013252 (2016)","journal-title":"Big Data."},{"key":"28_CR40","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.robot.2018.07.006","volume":"109","author":"M Plappert","year":"2018","unstructured":"Plappert, M., Mandery, C., Asfour, T.: Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks. Robot. Auton. Syst. 109, 13\u201326 (2018)","journal-title":"Robot. Auton. Syst."},{"key":"28_CR41","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., de la Torre, F., Sheikh, Y.: Meshtalk: 3D face animation from speech using cross-modality disentanglement. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"28_CR43","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R.: Mixed SIGNals: sign language production via a mixture of motion primitives. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Terlemez, O., Ulbrich, S., Mandery, C., Do, M., Vahrenkamp, N., Asfour, T.: Master motor map (MMM) - framework and toolkit for capturing, representing, and reproducing human motion on humanoid robots. In: International Conference on Humanoid Robots (2014)","DOI":"10.1109\/HUMANOIDS.2014.7041470"},{"key":"28_CR46","unstructured":"University, C.M.: CMU MoCap Dataset"},{"key":"28_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"28_CR49","first-page":"441","volume":"3","author":"T Yamada","year":"2018","unstructured":"Yamada, T., Matsunaga, H., Ogata, T.: Paired recurrent autoencoders for bidirectional translation between robot actions and linguistic descriptions. Robot. Autom. Lett. 3, 441\u2013448 (2018)","journal-title":"Robot. Autom. Lett."},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00449"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Unified contrastive learning in image-text-label space. In: Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"28_CR52","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"28_CR53","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"},{"key":"28_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-030-58539-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zanfir","year":"2020","unstructured":"Zanfir, A., Bazavan, E.G., Xu, H., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Weakly supervised 3d human pose and shape reconstruction with normalizing flows. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 465\u2013481. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_28"},{"key":"28_CR55","unstructured":"Zhang, Y., Black, M.J., Tang, S.: Perpetual motion: generating unbounded human motion. arXiv preprint arXiv:2007.13886 (2020)"},{"key":"28_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Black, M.J., Tang, S.: We are more than our joints: predicting how 3D bodies move. In: Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"28_CR57","doi-asserted-by":"crossref","unstructured":"Zhao, R., Su, H., Ji, Q.: Bayesian adversarial human motion synthesis. In: Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00626"},{"key":"28_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"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\/978-3-031-20047-2_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T23:12:49Z","timestamp":1666739569000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20047-2_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","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":"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)"}}]}}