{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:02Z","timestamp":1784268602459,"version":"3.55.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730351","type":"print"},{"value":"9783031730368","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73036-8_23","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:07:25Z","timestamp":1732093645000},"page":"398-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Text Motion Translator: A Bi-directional Model for\u00a0Enhanced 3D Human Motion Generation from\u00a0Open-Vocabulary Descriptions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9440-9744","authenticated-orcid":false,"given":"Yijun","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Urbanek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2123-0684","authenticated-orcid":false,"given":"Alexander","family":"Hauptmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5510-6425","authenticated-orcid":false,"given":"Jungdam","family":"Won","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"23_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.\u00a01\u20135 (2017)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"23_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 (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: Teach: temporal action composition for 3D humans. In: 2022 International Conference on 3D Vision (3DV), pp. 414\u2013423 (2022)","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: SINC: spatial composition of 3D human motions for simultaneous action generation. ArXiv preprint arxiv: abs\/2304.10417 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258236650","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"23_CR5","unstructured":"Bie, X., Guo, W., Leglaive, S., Girin, L., Moreno-Noguer, F., Alameda-Pineda, X.: HiT-DVAE: human motion generation via hierarchical transformer dynamical VAE. arXiv preprint arXiv:2204.01565 (2022)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., Yu, G.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"23_CR7","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: GPT-3: its nature, scope, limits, and consequences. Mind. Mach. 30, 681\u2013694 (2020)","journal-title":"Mind. Mach."},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12046\u201312055 (2019)","DOI":"10.1109\/CVPR.2019.01232"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1376\u20131386 (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"issue":"11","key":"23_CR10","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161 (June 2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating diverse and natural 3D human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: TM2T: stochastic and tokenized modeling for the reciprocal generation of 3D human motions and texts. In: European Conference on Computer Vision, pp. 580\u2013597. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_34","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"23_CR14","unstructured":"Ho, J., et al.: Imagen video: high definition video generation with diffusion models. ArXiv preprint arxiv: abs\/2210.02303 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252715883"},{"key":"23_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR16","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. ArXiv preprint arxiv: abs\/2204.03458 (2022)"},{"key":"23_CR17","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR18","unstructured":"Kim, J., Kim, J., Choi, S.: Flame: free-form language-based motion synthesis & editing. arXiv preprint arXiv:2209.00349 (2022)"},{"key":"23_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Lee, T., Moon, G., Lee, K.M.: Multiact: long-term 3D human motion generation from multiple action labels. arXiv preprint arXiv:2212.05897 (2022)","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: Hybrik: a hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3383\u20133393 (2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"23_CR22","unstructured":"Lin, A.S., Wu, L., Corona, R., Tai, K.W.H., Huang, Q., Mooney, R.J.: Generating animated videos of human activities from natural language descriptions (2018)"},{"key":"23_CR23","unstructured":"Lin, J., et al.: OhMG: zero-shot open-vocabulary human motion generation. arXiv preprint arXiv:2210.15929 (2022)"},{"key":"23_CR24","unstructured":"Lin, X., Amer, M.R.: Human motion modeling using DVGANs. ArXiv preprint arxiv:abs\/1804.10652 (2018)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., yu\u00a0Duan, L., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3d human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2684\u20132701 (2019). https:\/\/api.semanticscholar.org\/CorpusID:152282878","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"23_CR26","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: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5441\u20135450 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10965\u201310975 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: generating diverse human motions from textual descriptions. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 480\u2013497. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The kit motion-language dataset. Big data 4(4), 236\u2013252 (2016)","DOI":"10.1089\/big.2016.0028"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., for Intelligent\u00a0Systems, M.J.B.M.P.I., Konstanz, U.: Babel: Bodies, action and behavior with english labels. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Qian, Y., Urbanek, J., Hauptmann, A.G., Won, J.: Breaking the limits of text-conditioned 3d motion synthesis with elaborative descriptions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2306\u20132316 (2023)","DOI":"10.1109\/ICCV51070.2023.00219"},{"issue":"1","key":"23_CR33","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR34","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, arXiv: abs\/2204.06125 (2022), https:\/\/api.semanticscholar.org\/CorpusID:248097655"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: Humor: 3d human motion model for robust pose estimation. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11468\u201311479 (2021)","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"23_CR36","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior, arXiv: abs\/2303.01418 (2023), https:\/\/api.semanticscholar.org\/CorpusID:257279944"},{"key":"23_CR37","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"23_CR38","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models., arXiv: abs\/2302.13971 (2023)"},{"key":"23_CR39","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"23_CR40","unstructured":"Wang, W., et al.: Neural marionette: A transformer-based multi-action human motion synthesis system. arXiv preprint arXiv:2209.13204 (2022)"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Xu, H., Durme, B.V., Murray, K.: Bert, mbert, or bibert? a study on contextualized embeddings for neural machine translation. arXiv: abs\/2109.04588 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.534"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: T2m-gpt: generating human motion from textual descriptions with discrete representations. arXiv preprint arXiv:2301.06052 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, M., Lin, X., Dang, R., Liu, C., Chen, Q.: Fine-grained spatiotemporal motion alignment for contrastive video representation learning. Proceedings of the 31st ACM International Conference on Multimedia (2023). https:\/\/api.semanticscholar.org\/CorpusID:261493823","DOI":"10.1145\/3581783.3611932"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73036-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:57:31Z","timestamp":1732096651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73036-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730351","9783031730368"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73036-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}