{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:51:40Z","timestamp":1784544700056,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272019"],"award-info":[{"award-number":["62272019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11263-025-02392-9","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T13:52:47Z","timestamp":1740750767000},"page":"4277-4293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation"],"prefix":"10.1007","volume":"133","author":[{"given":"Yin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiapeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiying","family":"Leng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederick W. B.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6351-2538","authenticated-orcid":false,"given":"Xiaohui","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"2392_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, FL., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S., et\u00a0al. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"2392_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., & Morency, LP. (2019). Language2pose: Natural language grounded pose forecasting. In 2019 International conference on 3D vision (3DV) (pp. 719\u2013728). IEEE.","DOI":"10.1109\/3DV.2019.00084"},{"key":"2392_CR3","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, MJ., & Varol, G. (2023). Sinc: Spatial composition of 3d human motions for simultaneous action generation. arXiv preprint arXiv:2304.10417","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"2392_CR4","doi-asserted-by":"crossref","unstructured":"Cervantes, P., Sekikawa, Y., Sato, I., & Shinoda, K. (2022). Implicit neural representations for variable length human motion generation. InEuropean conference on computer vision Springer (pp. 356\u2013372)","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"2392_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., & Yu, G. (2023). 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)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"2392_CR6","unstructured":"Devlin, J., Chang, MW., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"2392_CR7","doi-asserted-by":"crossref","unstructured":"Ghosh ,A., Cheema, N., Oguz, C., Theobalt, C., & Slusallek P. (2021). Synthesis of compositional animations from textual descriptions. In  Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1396\u20131406)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"2392_CR8","doi-asserted-by":"crossref","unstructured":"Gilardi, F., Alizadeh, M., & Kubli, M. (2023). Chatgpt outperforms crowd-workers for text-annotation tasks. arXiv preprint arXiv:2303.15056","DOI":"10.1073\/pnas.2305016120"},{"key":"2392_CR9","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., & Cheng, L. (2020). Action2motion: Conditioned generation of 3d human motions. In Proceedings of the 28th ACM international conference on multimedia (pp. 2021\u20132029)","DOI":"10.1145\/3394171.3413635"},{"key":"2392_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., & Cheng, L. (2022a). 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)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"2392_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., & Cheng, L. (2022b). Tm2t: Stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts. In European conference on computer vision Springer (pp. 580\u2013597)","DOI":"10.1007\/978-3-031-19833-5_34"},{"issue":"2","key":"2392_CR12","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s11263-021-01550-z","volume":"130","author":"C Guo","year":"2022","unstructured":"Guo, C., Zuo, X., Wang, S., Liu, X., Zou, S., Gong, M., & Cheng, L. (2022). Action2video: Generating videos of human 3d actions. International Journal of Computer Vision, 130(2), 285\u2013315.","journal-title":"International Journal of Computer Vision"},{"key":"2392_CR13","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598"},{"key":"2392_CR14","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"2392_CR15","first-page":"411","volume":"7","author":"M Honnibal","year":"2017","unstructured":"Honnibal, M., & Montani, I. (2017). spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To appear, 7(1), 411\u2013420.","journal-title":"To appear"},{"key":"2392_CR16","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., & Chen, T. (2024). Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36"},{"key":"2392_CR17","unstructured":"Jin, P., Wu, Y., Fan, Y., Sun, Z., Yang, W., & Yuan, L. (2024). Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs. Advances in Neural Information Processing Systems 36"},{"key":"2392_CR18","doi-asserted-by":"crossref","unstructured":"Kalakonda, SS., Maheshwari, S., & Sarvadevabhatla, RK. (2023). Action-gpt: Leveraging large-scale language models for improved and generalized action generation. In 2023 IEEE international conference on multimedia and expo (ICME) (pp. 31\u201336). IEEE.","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"2392_CR19","doi-asserted-by":"crossref","unstructured":"Kao, HK., & Su, L. (2020). Temporally guided music-to-body-movement generation. In Proceedings of the 28th ACM international conference on multimedia (pp. 147\u2013155)","DOI":"10.1145\/3394171.3413848"},{"key":"2392_CR20","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., & Tang, S. (2023). Guided motion diffusion for controllable human motion synthesis. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2151\u20132162)","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"2392_CR21","doi-asserted-by":"publisher","first-page":"8255","DOI":"10.1609\/aaai.v37i7.25996","volume":"37","author":"J Kim","year":"2023","unstructured":"Kim, J., Kim, J., & Choi, S. (2023). Flame: Free-form language-based motion synthesis & editing. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 8255\u20138263.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2392_CR22","unstructured":"Kochurov, M., Karimov, R., & Kozlukov, S. (2020). Geoopt: Riemannian optimization in pytorch. arXiv preprint arXiv:2005.02819"},{"key":"2392_CR23","doi-asserted-by":"crossref","unstructured":"Leng, Z., Wu, SC., Saleh, M., Montanaro, A., Yu, H., Wang, Y., Navab, N., Liang, X., & Tombari, F .(2023). Dynamic hyperbolic attention network for fine hand-object reconstruction. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 14894\u201314904)","DOI":"10.1109\/ICCV51070.2023.01368"},{"key":"2392_CR24","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, DA., & Kanazawa, A. (2021). Ai choreographer: Music conditioned 3d dance generation with aist++. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13401\u201313412)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"2392_CR25","unstructured":"Liu, Q., Nickel, M., & Kiela, D. (2019). Hyperbolic graph neural networks. Advances in Neural Information Processing Systems 32"},{"key":"2392_CR26","first-page":"851","volume":"2","author":"M Loper","year":"2023","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & Black, M. J. (2023). Smpl: A skinned multi-person linear model. Seminal Graphics Papers: Pushing the Boundaries, 2, 851\u2013866.","journal-title":"Seminal Graphics Papers: Pushing the Boundaries"},{"key":"2392_CR27","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, NF., Pons-Moll, G., & Black, MJ. (2019). Amass: Archive of motion capture as surface shapes. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5442\u20135451)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"2392_CR28","unstructured":"Nickel, M., & Kiela, D. (2017). Poincar\u00e9 embeddings for learning hierarchical representations. Advances in Neural Information Processing Systems 30"},{"key":"2392_CR29","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, MJ., & Varol, G. (2021). Action-conditioned 3d human motion synthesis with transformer vae. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10985\u201310995)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"2392_CR30","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, MJ., & Varol, G. (2022). Temos: Generating diverse human motions from textual descriptions. In European conference on computer vision Springer (pp. 480\u2013497)","DOI":"10.1007\/978-3-031-20047-2_28"},{"issue":"4","key":"2392_CR31","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. (2016). The kit motion-language dataset. Big Data, 4(4), 236\u2013252.","journal-title":"Big Data"},{"key":"2392_CR32","doi-asserted-by":"crossref","unstructured":"Punnakkal, AR., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., & Black, MJ. (2021). Babel: Bodies, action and behavior with english labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 722\u2013731)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"2392_CR33","unstructured":"Radford, A., Kim, JW., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell A., Mishkin, P., Clark, J., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In International conference on machine learning, PMLR (pp. 8748\u20138763)"},{"issue":"1","key":"2392_CR34","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1), 5485\u20135551.","journal-title":"The Journal of Machine Learning Research"},{"key":"2392_CR35","doi-asserted-by":"crossref","unstructured":"Ren, X., Li, H., Huang, Z., & Chen, Q. (2020). Self-supervised dance video synthesis conditioned on music. In Proceedings of the 28th ACM international conference on multimedia (pp. 46\u201354)","DOI":"10.1145\/3394171.3413932"},{"key":"2392_CR36","unstructured":"Shafir, Y., Tevet, G., Kapon, R., & Bermano, AH. (2023). Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418"},{"key":"2392_CR37","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., & Li, H. (2021). Efficient attention: Attention with linear complexities. In textitProceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV) (pp. 3531\u20133539)"},{"issue":"4","key":"2392_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530178","volume":"41","author":"S Starke","year":"2022","unstructured":"Starke, S., Mason, I., & Komura, T. (2022). Deepphase: Periodic autoencoders for learning motion phase manifolds. ACM Transactions on Graphics (TOG), 41(4), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2392_CR39","doi-asserted-by":"crossref","unstructured":"Terlemez, \u00d6., Ulbrich, S., Mandery, C., Do, M., Vahrenkamp, N., & Asfour, T. (2014). Master motor map (mmm)-framework and toolkit for capturing, representing, and reproducing human motion on humanoid robots. In 2014 IEEE-RAS international conference on humanoid robots (pp. 894\u2013901). IEEE.","DOI":"10.1109\/HUMANOIDS.2014.7041470"},{"key":"2392_CR40","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, AH., Cohen-Or, D. (2022). Motionclip: Exposing human motion generation to clip space. In European conference on computer vision Springer (pp. 358\u2013374)","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"2392_CR41","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., & Bermano, AH. (2023). Human motion diffusion model. In The eleventh international conference on learning representations, https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"2392_CR42","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., & Liu, K. (2023). Edge: Editable dance generation from music. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 448\u2013458)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"2392_CR43","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, AN., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems 30"},{"key":"2392_CR44","doi-asserted-by":"crossref","unstructured":"Wan, W., Dou, Z., Komura, T., Wang, W., Jayaraman, D., & Liu, L. (2023). Tlcontrol: Trajectory and language control for human motion synthesis. arXiv preprint arXiv:2311.17135","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"2392_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Leng, Z., Li, FW., Wu, SC., & Liang, X. (2023). Fg-t2m: Fine-grained text-driven human motion generation via diffusion model. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22035\u201322044)","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"2392_CR46","unstructured":"Yang, M., Zhou, M., Li, Z., Liu, J., Pan, L., Xiong, H., & King, I. (2022). Hyperbolic graph neural networks: a review of methods and applications. arXiv preprint arXiv:2202.13852"},{"key":"2392_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., Zhang, Y., Zhao, H., Lu, H., Shen, X., & Shan, Y. (2023a). Generating human motion from textual descriptions with discrete representations. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14730\u201314740)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"2392_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, M., Guo, X., Pan, L., Cai, Z., Hong, F., Li, H., Yang, L., & Liu, Z. (2023b). Remodiffuse: Retrieval-augmented motion diffusion model. arXiv preprint arXiv:2304.01116","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"2392_CR49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2024). Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2024.3355414","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2392_CR50","unstructured":"Zhang, M., Li, H., Cai, Z., Ren, J., Yang, L., & Liu, Z. (2024b). Finemogen: Fine-grained spatio-temporal motion generation and editing. Advances in Neural Information Processing Systems 36"},{"key":"2392_CR51","doi-asserted-by":"crossref","unstructured":"Zhong, C., Hu, L., Zhang, Z., & Xia, S. (2023). Attt2m: Text-driven human motion generation with multi-perspective attention mechanism. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 509\u2013519)","DOI":"10.1109\/ICCV51070.2023.00053"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02392-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02392-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02392-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T06:05:17Z","timestamp":1749276317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02392-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["2392"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02392-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"22 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}