{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:45Z","timestamp":1778083545438,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01226","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13193-13202","source":"Crossref","is-referenced-by-count":1,"title":["Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation"],"prefix":"10.1109","author":[{"given":"Congyi","family":"Fan","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanjia","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongli","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Academy of Artificial Intelligence for Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youtian","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengming","family":"Feng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Space-Ground Integrated Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiwei","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"In Proc. Int. Conf. Mach. Learn. (ICML)","author":"Dao","year":"2024"},{"key":"ref3","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","article-title":"Fairmotion - tools to load, process and visualize motion capture data","author":"Gopinath","year":"2020","journal-title":"Github"},{"key":"ref7","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Heusel","year":"2017"},{"key":"ref9","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448469"},{"key":"ref12","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Huang","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2735951"},{"key":"ref15","article-title":"Dancing to music","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lee","year":"2019"},{"key":"ref16","article-title":"FTMoMamba: Motion generation with frequency and text state space models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Learning to generate diverse dance motions with Transformer","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"ref21","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref23","volume-title":"Mixamo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073247"},{"key":"ref25","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Fmdistance: A fast and effective distance function for motion capture data","author":"Onuma","year":"2008","journal-title":"Eurographics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612307"},{"key":"ref28","article-title":"SMCD: High realism motion style transfer via Mamba-based diffusion","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319435"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.2981989"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-024-00273-2"},{"key":"ref35","article-title":"Attention is all you need. Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27783"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2702613.2732759"},{"key":"ref39","article-title":"Light-t2m: A lightweight and fast model for text-tomotion generation","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"InfiniMotion: Mamba boosts memory in Transformer for arbitrary long motion generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref42","article-title":"Beat-It: Beatsynchronized multi-condition 3D dance generation","volume-title":"Proc. Springer Eur. Conf. Comput. Vis. (ECCV)","author":"Zheng","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3330935"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095203"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3485664"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445624.pdf?arnumber=11445624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:36Z","timestamp":1777611756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01226","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}