{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:49:18Z","timestamp":1776887358875,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/vcip67698.2025.11396818","type":"proceedings-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:55:27Z","timestamp":1771966527000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Ges-QA: A Multidimensional Quality Assessment Dataset for Audio-to-3D Gesture Generation"],"prefix":"10.1109","author":[{"given":"Zhilin","family":"Gao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijing","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqin","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Processing and Information Communications,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681366"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3623560"},{"key":"ref5","article-title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00190"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32183"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.102987"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754731"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3639620"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755332"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755700"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095347"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447636"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222061"},{"key":"ref22","first-page":"102540","article-title":"A no-reference quality assessment metric for dynamic 3d digital human","volume-title":"Displays","volume":"80","author":"Chen","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"ref25","article-title":"Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506408"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222476"},{"key":"ref28","article-title":"Mambatalk: Efficient holistic gesture synthesis with selective state space models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Xu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref33","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Dosovitskiy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290528"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"}],"event":{"name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","location":"Klagenfurt, Austria","start":{"date-parts":[[2025,12,1]]},"end":{"date-parts":[[2025,12,4]]}},"container-title":["2025 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11396756\/11396790\/11396818.pdf?arnumber=11396818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:41:48Z","timestamp":1772005308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396818","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}