{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T11:10:24Z","timestamp":1737025824857,"version":"3.33.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"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":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10826672","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"19-24","source":"Crossref","is-referenced-by-count":0,"title":["SemanticVQVAE for Co-Speech Gesture Quantization with Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Chungil","family":"Kim","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"San","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin Yea","family":"Jang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byunggill","family":"Joe","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minyeoung","family":"Jung","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saim","family":"Shin","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, Korea Electronic Technology Institute,Gyeonggi-do,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00230"},{"key":"ref2","article-title":"C2g2: Controllable co-speech gesture generation with latent diffusion model","author":"Ji","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479914"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2697.001.0001"},{"key":"ref5","article-title":"Neural discrete representation learning","author":"Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"45\u201353","key":"ref6","article-title":"Vector quantized-variational autoen-coders for gesture generation","volume":"169","author":"Lee","year":"2023","journal-title":"Pattern Recognition Letters"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1515\/9783110874259.351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511807572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl141"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.10.055"},{"key":"ref11","article-title":"Semantic congruency and its effects on gesture-speech integration","author":"Ginosar","year":"2023","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref12","article-title":"Engagement and comprehension in gesture-speech communication","author":"Holle","year":"2023","journal-title":"Frontiers in Psychology"},{"key":"ref13","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981117"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref16","article-title":"Speech2affectivegestures: Synthesizing co-speech gestures with generative adversarial networks","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Taming diffusion models for audio-driven co-speech gesture generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Emog: Synthesizing emotive co-speech 3d gesture with diffusion model","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"article-title":"Efficient codebook learning for vq-vae","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Nguyen","key":"ref19"},{"key":"ref20","article-title":"Recent advances in vq-vae for gesture generation","author":"Taylor","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Audio-driven co-speech gesture video generation","author":"Liu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref24","article-title":"Taming diffusion models for audio-driven co-speech gesture generation","author":"Advocate","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref30","article-title":"A tutorial on evaluating generative models","author":"Theis","year":"2015","journal-title":"arXiv preprint"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10826672.pdf?arnumber=10826672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:42:10Z","timestamp":1736923330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10826672","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}