{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:58Z","timestamp":1784268718057,"version":"3.55.0"},"reference-count":75,"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\/iccv51701.2025.01240","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13349-13359","source":"Crossref","is-referenced-by-count":2,"title":["StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion"],"prefix":"10.1109","author":[{"given":"Ziyu","family":"Guo","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhak","family":"Ben-Shabat","sequence":"additional","affiliation":[{"name":"Roblox,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Yoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Roblox,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Liu","sequence":"additional","affiliation":[{"name":"Roblox,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor","family":"Zordan","sequence":"additional","affiliation":[{"name":"Roblox,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mubbasir","family":"Kapadia","sequence":"additional","affiliation":[{"name":"Roblox,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392469"},{"key":"ref2","article-title":"Lead: Latent realignment for human motion diffusion","author":"Andreou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00182"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610603"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687563"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref10","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref15","article-title":"Generative human motion stylization in latent space","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref17","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Pisa: A self-augmented data engine and training strategy for 3d understanding with large models","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1010"},{"key":"ref20","article-title":"Can we generate images with cot? let\u2019s verify and reinforce image generation step by step","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01607"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3516429"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref26","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Gmd: Controllable human motion synthesis via guided diffusion models","volume-title":"ICCV","author":"Karunratanakul","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00168"},{"key":"ref29","volume-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024a"},{"key":"ref30","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"ICLR 2025 Spotlight"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/310"},{"key":"ref33","article-title":"Mulsmo: Multimodal stylized motion generation by bidirectional control flow","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Lamp: Language-motion pretraining for motion generation, retrieval, and captioning","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"I","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3522618"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3480145"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref44","article-title":"Smcd: High realism motion style transfer via mamba-based diffusion","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Single motion diffusion","author":"Raab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687579"},{"key":"ref47","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591514"},{"key":"ref52","article-title":"Exploring the potential of encoder-free architectures in 3d lmms","author":"Tang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00648"},{"key":"ref54","article-title":"Human motion diffusion model","author":"Tevet","year":"2023","journal-title":"ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"ref57","article-title":"Thor: Text to human-object interaction diffusion via relation intervention","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Motionllm: Multimodal motion-language learning with large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Omnicontrol: Control any joint at any time for human motion generation","author":"Xie","year":"2024","journal-title":"ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_11"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref62","article-title":"Interdreamer: Zero-shot text to 3d dynamic human-object interaction","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref68","article-title":"Point-clip: Point cloud understanding by clip","author":"Zhang","year":"2022","journal-title":"CVPR 2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref70","article-title":"Llama-adapter: Efficient fine-tuning of large language models with zeroinitialized attention","author":"Zhang","year":"2024","journal-title":"ICLR 2024"},{"key":"ref71","article-title":"Mathverse: Does your multi-modal 11 m truly see the diagrams in visual math problems?","author":"Zhang","year":"2024","journal-title":"ECCV 2024"},{"key":"ref72","article-title":"Mavis: Mathematical visual instruction tuning with an automatic data engine","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref74","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"}],"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\/11444780.pdf?arnumber=11444780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:09Z","timestamp":1777613409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01240","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}