{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:11Z","timestamp":1781761871211,"version":"3.54.5"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557005","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["FILD: Flash Interaction Latent Diffusion for Real-Time Text-Conditioned Human-Human Interaction Generation"],"prefix":"10.1109","author":[{"given":"Guanhe","family":"Huang","sequence":"first","affiliation":[{"name":"King’s College London,Department of Engineering,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"King’s College London,Department of Engineering,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oya","family":"Celiktutan","sequence":"additional","affiliation":[{"name":"King’s College London,Department of Engineering,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref7","first-page":"arXiv","article-title":"Motionclr: Motion generation and training-free editing via understanding attention mechanisms","author":"Chen","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27988"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"issue":"4","key":"ref18","first-page":"2005","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","volume-title":"Intermask: 3d human interaction generation via collaborative masked modeling. arXiv preprint arXiv:2410.10010","author":"Javed","year":"2024"},{"key":"ref20","volume-title":"Motionpcm: Real-time motion synthesis with phased consistency model. arXiv preprint arXiv:2501.19083","author":"Jiang","year":"2025"},{"key":"ref21","article-title":"Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs","volume":"36","author":"Jin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref23","volume-title":"aitviewer","author":"Kaufmann","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref25","volume-title":"Imagine flash: Accelerating emu diffusion models with backward distillation. arXiv preprint arXiv:2405.05224","author":"Kohler","year":"2024"},{"key":"ref26","article-title":"Two-in-one: Unified multiperson interactive motion generation by latent diffusion transformer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2412.16670"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref28","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"International Conference on Learning Representations","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref30","first-page":"57755787","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv:2310.04378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01285"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00200"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","volume-title":"Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418","author":"Shafir","year":"2023"},{"key":"ref39","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/960126.806879"},{"key":"ref41","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511801181"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref45","volume-title":"Human motion diffusion model. arXiv preprint arXiv:2209.14916","author":"Tevet","year":"2022"},{"key":"ref46","article-title":"Mola: Motion generation and editing with latent diffusion enhanced by adversarial training","author":"Uchida","year":"2024","journal-title":"arXiv preprint arXiv:2406.01867"},{"key":"ref47","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00672"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref50","article-title":"Learning fast samplers for diffusion models by differentiating through sample quality","volume-title":"International Conference on Learning Representations","author":"Watson"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref54","article-title":"T2m-gpt","author":"Zhang","year":"2023","journal-title":"Generating human motion from textual descriptions with discrete representations. arXiv preprint arXiv:2301.06052"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref56","article-title":"Fast sampling of diffusion models with exponential integrator","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2204.13902"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01384"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_8"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557005.pdf?arnumber=11557005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:43Z","timestamp":1781758363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557005","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}