{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:21Z","timestamp":1777889841561,"version":"3.51.4"},"reference-count":38,"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\/iccv51701.2025.01204","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12956-12965","source":"Crossref","is-referenced-by-count":0,"title":["ARIG: Autoregressive Interactive Head Generation for Real-Time Conversations"],"prefix":"10.1109","author":[{"given":"Ying","family":"Guo","sequence":"first","affiliation":[{"name":"Vision AI Department,Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Liu","sequence":"additional","affiliation":[{"name":"Vision AI Department,Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhen","sequence":"additional","affiliation":[{"name":"Vision AI Department,Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Yan","sequence":"additional","affiliation":[{"name":"Vision AI Department,Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Wei","sequence":"additional","affiliation":[{"name":"Vision AI Department,Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref3","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"International Conference on Machine Learning","author":"Dehghani","year":"2023"},{"key":"ref4","article-title":"Autoregressive video generation without vector quantization","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref7","article-title":"Affective faces for goal-driven dyadic communication","author":"Geng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551577"},{"key":"ref10","article-title":"Interact: Capture and modelling of realistic, expressive and interactive activities between two persons in daily scenarios","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1907"},{"key":"ref13","first-page":"56424","article-title":"Autoregressive image generation without vector quantization","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00234"},{"key":"ref16","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.860"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref21","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02300-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref26","first-page":"484","article-title":"Dim: Dyadic interaction modeling for social behavior generation","volume-title":"European Conference on Computer Vision","author":"Tran","year":"2024"},{"key":"ref27","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91578-9_8"},{"key":"ref29","article-title":"Mrecgen: Multimodal appropriate reaction generator","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00057-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref34","article-title":"Memo: Memory-guided diffusion for expressive talking video generation","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3562651"},{"key":"ref37","article-title":"A unified framework for multimodal, multi-part human motion synthesis","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00997"}],"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\/11446285.pdf?arnumber=11446285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:31Z","timestamp":1777612891000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01204","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}