{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:40:53Z","timestamp":1769636453848,"version":"3.49.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"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":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10581929","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Finite Scalar Quantization as Facial Tokenizer for Dyadic Reaction Generation"],"prefix":"10.1109","author":[{"given":"Quang Tien","family":"Dam","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tri Tung","family":"Nguyen Nguyen","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinh Tuan","family":"Tran","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo-Ho","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2020","journal-title":"International Confer-ence on Learning Representations"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136780"},{"key":"ref5","first-page":"32942","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","volume":"35","author":"Dou","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423911"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612854"},{"key":"ref9","volume-title":"Finite scalar quantization: Vq-vae made simple","author":"Mentzer","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581935"},{"key":"ref15","volume-title":"Multiple appropriate facial reaction generation in dyadic interaction settings: What, why and how?","author":"Song","year":"2023"},{"key":"ref16","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"ref18","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu"},{"key":"ref19","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Istanbul, Turkiye","start":{"date-parts":[[2024,5,27]]},"end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10581929.pdf?arnumber=10581929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:13:42Z","timestamp":1721279622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10581929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10581929","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}