{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:46:30Z","timestamp":1781279190422,"version":"3.54.1"},"reference-count":65,"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\/iccv51701.2025.01017","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10929-10939","source":"Crossref","is-referenced-by-count":4,"title":["GestureLSM: Latent Shortcut Based Co-Speech Gesture Generation with Spatial-Temporal Modeling"],"prefix":"10.1109","author":[{"given":"Pinxin","family":"Liu","sequence":"first","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luchuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhua","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","author":"Blattmann","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-2958.1990.tb00229.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2012.01183.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616117"},{"key":"ref9","article-title":"BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref10","volume-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref11","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref12","volume-title":"One step diffusion via shortcut models","author":"Frans","year":"2024"},{"key":"ref13","article-title":"Eraseanything: Enabling concept erasure in rectified flow transformers","volume-title":"Proceedings of the Forty-second International Conference on Machine Learning (ICML).","author":"Gao","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"ref17","volume-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"ref18","article-title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref21","volume-title":"Improving the training of rectified flows","author":"Lee","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754546"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref25","article-title":"Flow Matching for Generative Modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref28","article-title":"EMAGE: Towards Unified Holistic CoSpeech Gesture Generation via Masked Audio Gesture Modeling","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Tango: Co-speech gesture video reenactment with hierarchical audio motion embedding and diffusion interpolation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01296"},{"key":"ref31","volume-title":"Intentional gesture: Deliver your intentions with gestures for speech","author":"Liu","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755140"},{"key":"ref33","volume-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref35","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR).","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00615"},{"key":"ref39","article-title":"Robust watermarking using generative priors against image editing: From benchmarking to advances","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Dctdiff: Intriguing properties of image generative modeling in the dct space","author":"Ning","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87361-5_61"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506512"},{"key":"ref47","first-page":"20839","article-title":"Emotional listener portrait: Neural listener head generation with emotion","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Song","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687632"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446837"},{"key":"ref51","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00400"},{"key":"ref53","volume-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref54","volume-title":"Rectified diffusion: Straightness is not your need in rectified flow","author":"Wang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28458"},{"key":"ref58","volume-title":"Mambatalk: Efficient holistic gesture synthesis with selective state space models","author":"Xu","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref62","volume-title":"Kinmo: Kinematic-aware human motion understanding and generation","author":"Zhang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3658134"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_20"},{"key":"ref65","volume-title":"Oftsr: One-step flow for image super-resolution with tunable fidelity-realism trade-offs","author":"Zhu","year":"2024"}],"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\/11445869.pdf?arnumber=11445869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:21Z","timestamp":1777611801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01017","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}