{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T06:57:12Z","timestamp":1764831432808,"version":"3.46.0"},"reference-count":26,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61862041"],"award-info":[{"award-number":["61862041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"publisher","award":["21JR7RA120"],"award-info":[{"award-number":["21JR7RA120"]}],"id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>As a vital carrier of human intangible culture, dance plays an important role in cultural transmission through digital generation. However, existing dance generation methods rely heavily on high-precision motion capture and manually annotated datasets, and they fail to effectively model the culturally distinctive movements of Chinese ethnic folk dance, resulting in semantic distortion and cross-modal mismatch. Building on the Chinese traditional ethnic Helou Dance, this paper proposes a culture-aware Chinese ethnic folk dance generation framework, CAFE-Dance, which dispenses with manual annotation and automatically generates dance sequences that achieve high cultural fidelity, precise music synchronization, and natural, fluent motion. To address the high cost and poor scalability of cultural annotation, we introduce a Zero-Manual-Label Cultural Data Construction Module (ZDCM) that performs self-supervised cultural learning from raw dance videos, using cross-modal semantic alignment and a knowledge-base-guided automatic annotation mechanism to construct a high-quality dataset of Chinese ethnic folk dance covering 108 classes of curated cultural attributes without any frame-level manual labels. To address the difficulty of modeling cultural semantics and the weak interpretability, we propose a Culture-Aware Attention Mechanism (CAAM) that incorporates cultural gating and co-attention to adaptively enhance culturally key movements. To address the challenge of aligning the music\u2013motion\u2013culture tri-modalities, we propose a Tri-Modal Alignment Network (TMA-Net) that achieves dynamic coupling and temporal synchronization of tri-modal semantics under weak supervision. Experimental results show that our framework improves Beat Alignment and Cultural Accuracy by 4.0\u20135.0 percentage points and over 30 percentage points, respectively, compared with the strongest baseline (Music2Dance), and it reveals an intrinsic coupling between cultural embedding density and motion stability. The code and the curated Helouwu dataset are publicly available.<\/jats:p>","DOI":"10.3390\/bdcc9120307","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:31:46Z","timestamp":1764689506000},"page":"307","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CAFE-Dance: A Culture-Aware Generative Framework for Chinese Folk and Ethnic Dance Synthesis via Self-Supervised Cultural Learning"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5154-7944","authenticated-orcid":false,"given":"Bin","family":"Niu","sequence":"first","affiliation":[{"name":"School of Dance, Northwest Normal University, Lanzhou 730070, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9969-113X","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou 730050, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-388X","authenticated-orcid":false,"given":"Qiuyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Lanzhou University of Technology, Lanzhou 730050, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8769-8518","authenticated-orcid":false,"given":"Yani","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Arts, Shandong University, Jinan 250100, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9921-3118","authenticated-orcid":false,"given":"Ying","family":"Fan","sequence":"additional","affiliation":[{"name":"School of International Communication and Arts, Hainan University, Haikou 570228, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mao, Q., Mastnak, W., and Guan, R. (2025). Chinese ethnic dance therapy: Cultural anthropology and health science perspectives on Tujia ethnic dances. Front. Psychol., 16.","DOI":"10.3389\/fpsyg.2025.1561150"},{"key":"ref_2","first-page":"2","article-title":"Etiquette and dance\u2014An analysis of the cultural phenomenon of the etiquette and custom dance of the ethnic minorities in Southwest China","volume":"25","author":"Li","year":"2025","journal-title":"Mediterr. Archaeol. Archaeom."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1080\/14647893.2020.1782371","article-title":"The Chinese dance: A mirror of cultural representations","volume":"21","author":"Liu","year":"2020","journal-title":"Res. Danc. Educ."},{"key":"ref_4","first-page":"126","article-title":"Dancing in the diaspora: Cultural long-distance nationalism and the staging of Chineseness by San Francisco\u2019s Chinese Folk Dance Association","volume":"2","author":"Wong","year":"2010","journal-title":"J. Transnatl. Am. Stud."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yan, Q., Wang, X., and Rosa, R.D.D. (2023). Ethnography of Chinese Dance Etiquette Culture and Aesthetic Value. Camb. Open Engag.","DOI":"10.33774\/coe-2023-w8p52"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wilcox, E. (2019). Revolutionary Bodies: Chinese Dance and the Socialist Legacy, University of California Press.","DOI":"10.1515\/9780520971905"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"93","DOI":"10.55014\/pij.v7i2.578","article-title":"The Application of Ethnic Folk Dance Elements in Choreographic Techniques from a Contemporary Perspective-Exploring the Fusion of Dai Ethnic Folk Dance and Modernity","volume":"7","author":"Lei","year":"2024","journal-title":"Pac. Int. J."},{"key":"ref_8","first-page":"72","article-title":"On the Origin of Helou Dance and Chunniu Dance in Southern Guangdong Province","volume":"2","author":"Ji","year":"2011","journal-title":"J. Beijing Danc. Acad."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, Y., He, X., Wang, J., Bai, X., and Ma, M. (2024, January 8\u201310). Exploration and research on the digital protection methods of ethnic dance. Proceedings of the International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), Guangzhou, China.","DOI":"10.1117\/12.3033546"},{"key":"ref_10","first-page":"44","article-title":"Daily Life, Time, and People in the Field: The Academic Transition of Folk Dance Research","volume":"6","author":"Zhang","year":"2022","journal-title":"J. Beijing Danc. Acad."},{"key":"ref_11","first-page":"145","article-title":"An Analysis of the Rushan Yangko Dance Becoming an Intangible Cultural Heritage in the Jiaodong Area","volume":"44","author":"Zhang","year":"2022","journal-title":"J. Guangxi Univ. Natl. (Philos. Soc. Sci. Ed.)"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ye, Z., Wu, H., Jia, J., Bu, Y., Chen, W., Meng, F., and Wang, Y. (2020, January 12\u201316). ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3414005"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tseng, J.H., Castellon, R., and Liu, C.K. (2023, January 18\u201322). EDGE: Editable Dance Generation From Music. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"14192","DOI":"10.1109\/TPAMI.2023.3319435","article-title":"Bailando++: 3D Dance GPT With Choreographic Memory","volume":"45","author":"Siyao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., and Theobalt, C. (2023, January 17\u201324). MoFusion: A Framework for Denoising-Diffusion-Based Motion Synthesis. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sun, S., Tang, Q., Liu, Y., Zhang, H., Song, Q., and Xu, D. (2024, January 24\u201326). YNU-Dance: A Multimodal Ethnic Dance Action Dataset. Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of Things, online.","DOI":"10.1145\/3670105.3670151"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gong, K., Lian, D., Chang, H., Guo, C., Zuo, X., Jiang, Z., and Wang, X. (2023, January 2\u20133). TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"ref_18","unstructured":"Tsuchida, S., Fukayama, S., Hamasaki, M., and Goto, M. (2019, January 4\u20138). AIST Dance Video Database: Multi-genre, Multi-dancer, and Multi-camera Database for Dance Information Processing. Proceedings of the 20th International Society for Music Information Retrieval Conference, Delft, The Netherlands."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhuang, H.W., Lei, S., Xiao, L., Li, W., Chen, L., Yang, S., Wu, Z., Kang, S., and Meng, H.M. (2023, January 4\u201310). GTN-Bailando: Genre Consistent long-Term 3D Dance Generation Based on Pre-Trained Genre Token Network. Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10095203"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1007\/s00371-024-03376-5","article-title":"QEAN: Quaternion-enhanced attention network for visual dance generation: QEAN: Quaternion-enhanced attention network for visual dance generation","volume":"41","author":"Zhou","year":"2024","journal-title":"Vis. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Siyao, L., Yu, W., Gu, T., Lin, C., Wang, Q., Qian, C., Loy, C.C., and Liu, Z. (2022, January 18\u201324). Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref_22","unstructured":"Qi, Q., Zhuo, L., Zhang, A., Liao, Y., Fang, F., Liu, S., and Yan, S. (November, January 29). Diffdance: Cascaded human motion diffusion model for dance generation. Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, ON, Canada."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., and Kanazawa, A. (2021, January 10\u201317). AI Choreographer: Music Conditioned 3D Dance Generation with AIST++. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref_24","unstructured":"Bai, J. (2009). Modern Consciousness and Li Ethnic Dance. J. Beijing Danc. Acad., 106\u2013110."},{"key":"ref_25","unstructured":"Lee, H.Y., Yang, X., Liu, M.Y., Wang, T.C., Lu, Y.D., Yang, M.H., and Kautz, J. (2019). Dancing to music. Adv. Neural Inf. Process. Syst., 32."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3485664","article-title":"Music2dance: Dancenet for music-driven dance generation","volume":"18","author":"Zhuang","year":"2022","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/12\/307\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T05:11:57Z","timestamp":1764825117000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/12\/307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":26,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bdcc9120307"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9120307","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,12,2]]}}}