{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:23:30Z","timestamp":1791566610518,"version":"4.3.4"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37335-9_19","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:06:51Z","timestamp":1789204011000},"page":"343-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["VersatileMotion: A Unified Framework for\u00a0Motion Synthesis and\u00a0Comprehension"],"prefix":"10.1007","author":[{"given":"Zeyu","family":"Ling","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jikang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongdeng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqing","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"issue":"4","key":"19_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592458","volume":"42","author":"S Alexanderson","year":"2023","unstructured":"Alexanderson, S., Nagy, R., Beskow, J., Henter, G.E.: Listen, denoise, action! audio-driven motion synthesis with diffusion models. ACM Trans. Graph. 42(4), 1\u201320 (2023)","journal-title":"ACM Trans. Graph."},{"key":"19_CR2","doi-asserted-by":"publisher","unstructured":"Aristidou, A., Shamir, A., Chrysanthou, Y.: Digital dance ethnography: Organizing large dance collections. J. Comput. Cult. Herit. 12(4) (Nov 2019). https:\/\/doi.org\/10.1145\/3344383","DOI":"10.1145\/3344383"},{"key":"19_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: Seamless human motion composition with blended positional encodings. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"19_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR6","doi-asserted-by":"publisher","first-page":"11454","DOI":"10.52202\/075280-0506","volume":"36","author":"Z Cai","year":"2023","unstructured":"Cai, Z., et al.: Smpler-x: scaling up expressive human pose and shape estimation. Adv. Neural. Inf. Process. Syst. 36, 11454\u201311468 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR7","doi-asserted-by":"publisher","first-page":"176241","DOI":"10.1109\/ACCESS.2020.3026276","volume":"8","author":"A Chatzitofis","year":"2020","unstructured":"Chatzitofis, A., et al.: Human4d: a human-centric multimodal dataset for motions and immersive media. IEEE Access 8, 176241\u2013176262 (2020)","journal-title":"IEEE Access"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhang, J., Lakshmikanth, S.K.: The language of motion: unifying verbal and non-verbal language of 3d human motion. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00581"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.H., Lu, S., Zeng, A.: Motionllm: understanding human behaviors from human motions and videos (2024). arXiv preprint arXiv:2405.20340","DOI":"10.1109\/TPAMI.2025.3627546"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W.: Executing your commands via motion diffusion in latent space. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Cho, J., et al.: Discord: discrete tokens to continuous motion via rectified flow decoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14602\u201314612, October 2025","DOI":"10.1109\/ICCV51701.2025.01355"},{"key":"19_CR12","unstructured":"Contributors, M.: MMEngine: openmmlab foundational library for training deep learning models (2022). https:\/\/github.com\/open-mmlab\/mmengine"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Di, S., Jiang, Z., Liu, S.: Video background music generation with controllable music transformer. In: ACM Multimedia (2021)","DOI":"10.1145\/3474085.3475195"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Fan, K., et al.: Go to zero: towards zero-shot motion generation with million-scale data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13336\u201313348 (2025)","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Learning complex 3d human self-contact. In: AAAI, vol. 35, pp. 1343\u20131351 (2021)","DOI":"10.1609\/aaai.v35i2.16223"},{"key":"19_CR16","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Reconstructing three-dimensional models of interacting humans (2023). arXiv preprint arXiv:2308.01854"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Pirlea, S.C., Olaru, V., Sminchisescu, C.: Aifit: automatic 3d human-interpretable feedback models for fitness training. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00979"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Chen, P.: Foley music: learning to generate music from videos. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Ghorbani, N., Black, M.J.: SOMA: Solving optical marker-based mocap automatically. In: Proc. International Conference on Computer Vision (ICCV), pp. 11117\u201311126 (2021)","DOI":"10.1109\/ICCV48922.2021.01093"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Gong, K., et al.: Tm2d: bimodality driven 3d dance generation via music-text integration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9942\u20139952 (2023)","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"19_CR21","unstructured":"Gopinath, D., Won, J.: Fairmotion-tools to load, process and visualize motion capture data (2020). https:\/\/github.com\/facebookresearch\/fairmotion"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G.: Momask: generative masked modeling of 3d human motions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X.: Generating diverse and natural 3d human motions from text. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"19_CR24","doi-asserted-by":"crossref","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: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_34"},{"issue":"4","key":"19_CR25","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s41095-024-0417-1","volume":"10","author":"B Han","year":"2024","unstructured":"Han, B., Li, Y., Shen, Y., et al.: Dance2midi: dance-driven multi-instrument music generation. Comput. Visual Media 10(4), 791\u2013802 (2024)","journal-title":"Comput. Visual Media"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Han, B., Peng, H., Dong, M.: Amd: autoregressive motion diffusion. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i3.27973"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"19_CR28","unstructured":"Javed, M.G., Guo, C., Cheng, L., Li, X.: Intermask: 3d human interaction generation via collaborative masked modeling (2024). arXiv preprintarXiv:2410.10010"},{"key":"19_CR29","unstructured":"Ji, S., Jiang, Z., Cheng, X., et\u00a0al.: Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling. arXiv preprint arXiv:2408.16532 (2024)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Ji, Y., Xu, F., Yang, Y., Shen, F., Shen, H.T., Zheng, W.S.: A large-scale varying-view rgb-d action dataset for arbitrary-view human action recognition. arXiv preprint arXiv:1904.10681 (2019)","DOI":"10.1145\/3240508.3240675"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, B., Chen, X., Liu, W.: Motiongpt: Human motion as a foreign language. In: NeurIPS (2023)","DOI":"10.52202\/075280-0880"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, N., et al.: Scaling up dynamic human-scene interaction modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1737\u20131747 (2024)","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Kim, B., et\u00a0al.: Personabooth: Personalized text-to-motion generation. arXiv preprint arXiv:2503.07390 (2025)","DOI":"10.1109\/CVPR52734.2025.02119"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Krebs, F., Meixner, A., Patzer, I., Asfour, T.: The KIT bimanual manipulation dataset. In: IEEE\/RAS International Conference on Humanoid Robots (Humanoids), pp. 499\u2013506 (2021)","DOI":"10.1109\/HUMANOIDS47582.2021.9555788"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Li, B., Zhao, Y., Zhelun, S., Sheng, L.: Danceformer: music conditioned 3d dance generation with parametric motion transformer. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Lodge: a coarse to fine diffusion network for long dance generation guided by the characteristic dance primitives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1524\u20131534 (2024)","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Li, R., Zhao, J., Zhang, Y.: Finedance: a fine-grained choreography dataset for 3d full body dance generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: Ai choreographer: music conditioned 3d dance generation with aist. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Dance-to-music generation with encoder-based textual inversion. In: SIGGRAPH Asia (2024)","DOI":"10.1145\/3680528.3687562"},{"key":"19_CR40","first-page":"1","volume":"1","author":"H Liang","year":"2024","unstructured":"Liang, H., Zhang, W., Li, W., et al.: Intergen: diffusion-based multi-human motion generation under complex interactions. IJCV 1, 1\u201321 (2024)","journal-title":"IJCV"},{"key":"19_CR41","unstructured":"Liao, Y., Fu, Y., Cheng, Z., Wang, J.: Animationgpt: an aigc tool for generating game combat motion assets. https:\/\/github.com\/fyyakaxyy\/AnimationGPT (2024), combatMotion dataset and code"},{"key":"19_CR42","unstructured":"Lin, J., et al..: The quest for generalizable motion generation: Data, model, and evaluation. arXiv preprint arXiv:2510.26794 (2025)"},{"key":"19_CR43","doi-asserted-by":"publisher","first-page":"25268","DOI":"10.52202\/075280-1099","volume":"36","author":"J Lin","year":"2023","unstructured":"Lin, J., Zeng, A., Lu, S., et al.: Motion-x: a large-scale 3d expressive whole-body human motion dataset. Adv. Neural. Inf. Process. Syst. 36, 25268\u201325280 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part v 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19_CR45","unstructured":"Ling, Z., Han, B., Wong, Y.: Mcm: multi-condition motion synthesis framework. In: IJCAI (2024)"},{"key":"19_CR46","unstructured":"Ling, Z.: Hy-motion: A hybrid diffusion framework for versatile motion generation (2025). Techinal Report"},{"key":"19_CR47","unstructured":"Liu, A., et al.: Deepseek-v3 technical report (2024). arXiv preprint arXiv:2412.19437"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhu, Z., Becherini, G.: Emage: towards unified holistic co-speech gesture generation via expressive masked audio gesture modeling. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhu, Z., Iwamoto, N.: Beat: a large-scale semantic and emotional multi-modal dataset for conversational gestures synthesis. In: ECCV, pp. 612\u2013630. Springer (2022)","DOI":"10.1007\/978-3-031-20071-7_36"},{"issue":"10","key":"19_CR50","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: Ntu rgb+ d 120: a large-scale benchmark for 3d human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Learning hierarchical cross-modal association for co-speech gesture generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10462\u201310472 (2022)","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"19_CR52","doi-asserted-by":"crossref","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) (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"19_CR53","unstructured":"Lu, S., Chen, L.H., Zeng, A.: Humantomato: text-aligned whole-body motion generation. In: ICML (2024)"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Lu, S., Wang, J., Lu, Z., et\u00a0al.: Scamo: exploring the scaling law in autoregressive motion generation model. arXiv preprint arXiv:2412.14559 (2024)","DOI":"10.1109\/CVPR52734.2025.02595"},{"key":"19_CR55","unstructured":"Luo, M., Hou, R., Chang, H.: An advanced multimodal, multitask framework for motion comprehension and generation (2024). arXiv preprintarXiv:2405.16273"},{"key":"19_CR56","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), pp. 329\u2013336 (2015)","DOI":"10.1109\/ICAR.2015.7251476"},{"issue":"4","key":"19_CR57","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TRO.2016.2572685","volume":"32","author":"C Mandery","year":"2016","unstructured":"Mandery, C., Terlemez, O., Do, M., Vahrenkamp, N., Asfour, T.: Unifying representations and large-scale whole-body motion databases for studying human motion. IEEE Trans. Rob. 32(4), 796\u2013809 (2016)","journal-title":"IEEE Trans. Rob."},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"McFee, B., Raffel, C., Liang, D., et\u00a0al.: librosa: audio and music signal analysis in python. In: SciPy (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"19_CR59","unstructured":"Mentzer, F., Minnen, D., Agustsson, E., Tschannen, M.: Finite scalar quantization: Vq-vae made simple. In: ICLR (2023)"},{"key":"19_CR60","unstructured":"Paszke, A.: Pytorch: an imperative style, high-performance deep learning library (2019). arXiv:1912.01703 arXiv preprint"},{"key":"19_CR61","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":"19_CR62","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Tmr: text-to-motion retrieval using contrastive 3d human motion synthesis. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"19_CR63","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Wang, P., Lee, M., Chen, C.: Mmm: generative masked motion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1546\u20131555 (2024)","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"19_CR64","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"19_CR65","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior (2023). arXiv:2303.01418 arXiv preprint"},{"key":"19_CR66","doi-asserted-by":"crossref","unstructured":"Shen, Z., et al.: World-grounded human motion recovery via gravity-view coordinates. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687565"},{"key":"19_CR67","doi-asserted-by":"crossref","unstructured":"Siyao, L., Yu, W., Gu, T.: Bailando: 3d dance generation by actor-critic gpt with choreographic memory. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"19_CR68","doi-asserted-by":"crossref","unstructured":"Sun, Q., et\u00a0al.: Aios: all-in-one-stage expressive human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1834\u20131843 (2024)","DOI":"10.1109\/CVPR52733.2024.00180"},{"key":"19_CR69","unstructured":"Team, C.: Chameleon: Mixed-modal early-fusion foundation models (2024). arXiv preprintarXiv:2405.09818"},{"key":"19_CR70","unstructured":"Tevet, G., Raab, S., Gordon, B.: Human motion diffusion model. In: ICLR (2023)"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, K.: EDGE: editable dance generation from music. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"19_CR72","unstructured":"Wang, Y., Huang, D., Zhang, Y.: Motiongpt-2: a general-purpose motion-language model for motion generation and understanding (2024). arXiv preprint arXiv:2410.21747"},{"key":"19_CR73","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, J., Li, Y., Lin, D., Dai, B.: Intercontrol: zero-shot human interaction generation by controlling every joint. In: NeurIPS (2024)","DOI":"10.52202\/079017-3345"},{"key":"19_CR74","unstructured":"Wu, Q., Zhao, Y., Wang, Y., Liu, X., Tai, Y.W., Tang, C.K.: Motion-agent: a conversational framework for human motion generation with llms (2024). arXiv preprint arXiv:2405.17013"},{"key":"19_CR75","doi-asserted-by":"crossref","unstructured":"Xiao, L., et al.: Motionstreamer: streaming motion generation via diffusion-based autoregressive model in causal latent space. arXiv preprint arXiv:2503.15451 (2025)","DOI":"10.1109\/ICCV51701.2025.00940"},{"key":"19_CR76","doi-asserted-by":"crossref","unstructured":"Xu, L., Lv, X., Yan, Y.: Inter-x: towards versatile human-human interaction analysis. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"19_CR77","unstructured":"Yang, H., Su, K., Zhang, Y.: Unimumo: unified text, music and motion generation (2024). arXiv preprint arXiv:2410.04534"},{"key":"19_CR78","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Diffusestylegesture: Stylized audio-driven co-speech gesture generation with diffusion models (2023). arXiv preprintarXiv:2305.04919","DOI":"10.24963\/ijcai.2023\/650"},{"key":"19_CR79","doi-asserted-by":"crossref","unstructured":"Yi, H., Liang, H., Liu, Y.: Generating holistic 3d human motion from speech. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"19_CR80","unstructured":"Yin, W., et\u00a0al.: Smplest-x: ultimate scaling for expressive human pose and shape estimation. arXiv preprint arXiv:2501.09782 (2025)"},{"key":"19_CR81","doi-asserted-by":"crossref","unstructured":"Yin, Y., Guo, C., Kaufmann, M., Zarate, J.J., Song, J., Hilliges, O.: Hi4d: 4d instance segmentation of close human interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17016\u201317027 (2023)","DOI":"10.1109\/CVPR52729.2023.01632"},{"issue":"6","key":"19_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417838","volume":"39","author":"Y Yoon","year":"2020","unstructured":"Yoon, Y., Cha, B., Lee, J.H., Jang, M., Lee, J., Kim, J., Lee, G.: Speech gesture generation from the trimodal context of text, audio, and speaker identity. ACM Trans. Graph. (TOG) 39(6), 1\u201316 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"19_CR83","unstructured":"Yu, J., Wang, Y., Chen, X.: Long-term rhythmic video soundtracker. In: ICML (2023)"},{"key":"19_CR84","doi-asserted-by":"crossref","unstructured":"Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q.: Smoothnet: a plug-and-play network for refining human poses in videos. In: European Conference on Computer Vision, pp. 625\u2013642. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"19_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., et\u00a0al.: Generating human motion from textual descriptions with discrete representations. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"issue":"6","key":"19_CR86","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Cai, Z., Pan, L., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: retrieval-augmented motion diffusion model. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"19_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, M., Jin, D., Gu, C.: Large motion model for unified multi-modal motion generation (2024). arXiv preprint arXiv:2404.01284","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"19_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, M., Li, H., Cai, Z.: Finemogen: Fine-grained spatio-temporal motion generation and editing. In: NeurIPS (2023)","DOI":"10.52202\/075280-0616"},{"key":"19_CR90","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. In: ICLR (2020)"},{"key":"19_CR91","unstructured":"Zhang, Y., Lin, J., Zeng, A., et\u00a0al.: Motion-x++: a large-scale multimodal 3d whole-body human motion dataset. arXiv preprint arXiv:2501.05098 (2025)"},{"key":"19_CR92","unstructured":"Zhou, Z., Wan, Y., Wang, B.: A unified framework for multimodal, multi-part human motion synthesis. arXiv preprint arXiv:2311.16471 (2023)"},{"key":"19_CR93","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, B.: Ude: a unified driving engine for human motion generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5632\u20135641 (2023)","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"19_CR94","unstructured":"Zhu, B., et al.: Motiongpt3: human motion as a second modality. arXiv preprint arXiv:2506.24086 (2025)"},{"key":"19_CR95","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Olszewski, K., Wu, Y.: Quantized gan for complex music generation from dance videos. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19836-6_11"},{"key":"19_CR96","unstructured":"Zhu, Y., Wu, Y., Olszewski, K.: Discrete contrastive diffusion for cross-modal music and image generation. In: ICLR (2023)"},{"key":"19_CR97","unstructured":"Zou, S., et al.: Polarization human shape and pose dataset (2020). arXiv preprintarXiv:2004.14899"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:07:12Z","timestamp":1789204032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}