{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:19Z","timestamp":1777865359310,"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\/iccv51701.2025.00996","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10698-10707","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Framework for Motion Reasoning and Generation in Human Interaction"],"prefix":"10.1109","author":[{"given":"Jeongeun","family":"Park","sequence":"first","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungjoon","family":"Choi","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangdoo","family":"Yun","sequence":"additional","affiliation":[{"name":"Naver AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392469"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687559"},{"key":"ref3","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546\/mm1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00756"},{"key":"ref7","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"ref9","article-title":"SEED-X: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"ReMos: Reactive 3d motion synthesis for two-person interactions","author":"Ghosh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref14","article-title":"Generative human motion stylization in latent space","volume-title":"Proc. of the Twelfth International Conference on Learning Representations (ICLR)","author":"Guo","year":"2024"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"Hu","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref21","article-title":"Motion-X: A largescale 3d expressive whole-body human motion dataset","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NEURIPS)","volume":"36","author":"Lin","year":"2024"},{"key":"ref22","article-title":"Visual instruction tuning","volume-title":"Proc. of the Advances in neural information processing systems (NEURIPS)","volume":"36","author":"Liu","year":"2024"},{"key":"ref23","article-title":"M3 GPT: An advanced multimodal, multitask framework for motion comprehension and generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref25","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref28","article-title":"MAUVE: Measuring the gap between neural text and human text using divergence frontiers","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NEURIPS)","author":"Pillutla","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00200"},{"key":"ref30","article-title":"Human motion diffusion as a generative prior","volume-title":"Proc. of the Twelfth International Conference on Learning Representations (ICLR)","author":"Shafir","year":"2024"},{"key":"ref31","article-title":"Llasm: Large language and speech model","author":"Shu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. of the Twelfth International Conference on Learning Representations (ICLR)","author":"Tang","year":"2024"},{"key":"ref33","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Human motion diffusion model","volume-title":"Proc. of the Eleventh International Conference on Learning Representations (ICLR)","author":"Tevet","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref36","article-title":"Motionllm: Multimodal motion-language learning with large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref39","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref43","article-title":"Large motion model for unified multi-modal motion generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"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\/11445634.pdf?arnumber=11445634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:32Z","timestamp":1777529972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00996","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}