{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T14:06:34Z","timestamp":1772633194135,"version":"3.50.1"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"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":[[2025,9,8]]},"DOI":"10.1109\/ijcb65343.2025.11411217","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:39Z","timestamp":1772571039000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Emotion-Guided Masked Transformer for Long-Sequence Co-Speech Gestures with Partial Supervision"],"prefix":"10.1109","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongze","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"}],"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":"10.1109\/ICCV51070.2023.01910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01991"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04380-2_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0011631000003417"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref16","first-page":"9","article-title":"Stylistic locomotion modeling with conditional variational autoencoder","volume-title":"40th Annual Conference of the European Association for Computer Graphics, Eurographics 2019 - Short Papers, Genoa, Italy, May 6-10, 2019","author":"Du"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models for styled walking synthesis","author":"Findlay","year":"2022","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01397-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"ref25","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017","author":"Heusel"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687648"},{"key":"ref29","article-title":"Gesture generation by imitation: from human behavior to computer character animation","volume-title":"PhD thesis","author":"Kipp","year":"2003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s44159-023-00186-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3276973"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3687272.3690915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01022"},{"key":"ref35","article-title":"MAG: multi-modal aligned autoregressive co-speechgesture generation without vector quantization","author":"Liu","year":"2025","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ro-man57019.2023.10309493"},{"key":"ref37","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023","volume":"202","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00138"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref45","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3480145"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref48","article-title":"Detecting Verbal and Nonverbal Cues in the Communication of Emotions","volume-title":"PhD thesis","author":"Polzin","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407692"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00992"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103613"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70797"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58750-9_28"},{"key":"ref56","first-page":"38:1","article-title":"RSMT: real-time stylized motion transition for","volume-title":"ACM SIGGRAPH 2023 Conference Proceedings, SIGGRAPH 2023, Los Angeles, CA, USA, August 6-10, 2023","author":"Tang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00648"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3527188.3561924"},{"key":"ref59","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref60","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017","author":"den Oord"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448208"},{"key":"ref64","first-page":"5860","article-title":"Diffusestylegesture: Stylized audio-driven co-speech gesture generation with diffusion models","volume-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023","author":"Yang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"ref66","article-title":"Emog: Synthesizing emotive co-speech 3d gesture with diffusion model","author":"Yin","year":"2023","journal-title":"CoRR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3658134"},{"key":"ref70","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01902"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_8"}],"event":{"name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","location":"Osaka, Japan","start":{"date-parts":[[2025,9,8]]},"end":{"date-parts":[[2025,9,11]]}},"container-title":["2025 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410556\/11410616\/11411217.pdf?arnumber=11411217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:18:31Z","timestamp":1772608711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11411217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/ijcb65343.2025.11411217","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]}}}