{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:36:36Z","timestamp":1773200196559,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612587","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"3827-3836","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["That's What I Said: Fully-Controllable Talking Face Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0500-6025","authenticated-orcid":false,"given":"Youngjoon","family":"Jang","sequence":"first","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6487-5418","authenticated-orcid":false,"given":"Kyeongha","family":"Rho","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4941-6837","authenticated-orcid":false,"given":"Jongbin","family":"Woo","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2152-3639","authenticated-orcid":false,"given":"Hyeongkeun","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-0953","authenticated-orcid":false,"given":"Jihwan","family":"Park","sequence":"additional","affiliation":[{"name":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3328-0064","authenticated-orcid":false,"given":"Youshin","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6019-5047","authenticated-orcid":false,"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7741-7275","authenticated-orcid":false,"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503385.2503473"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"e_1_3_2_1_5_1","volume-title":"What comprises a good talking-head video generation?: A survey and benchmark. arXiv preprint arXiv:2005.03201","author":"Chen Lele","year":"2020","unstructured":"Lele Chen, Guofeng Cui, Ziyi Kou, Haitian Zheng, and Chenliang Xu. 2020. What comprises a good talking-head video generation?: A survey and benchmark. arXiv preprint arXiv:2005.03201 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc","author":"Chen Lele","unstructured":"Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, and Chenliang Xu. 2020. Talking-head generation with rhythmic head motion. In Proc. ECCV. Springer, 35--51."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. BMVC.","author":"Chung Joon Son","year":"2017","unstructured":"Joon Son Chung, Amir Jamaludin, and Andrew Zisserman. 2017. You said that?. In Proc. BMVC."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc","author":"Chung Joon Son","unstructured":"Joon Son Chung and Andrew Zisserman. 2017. Out of time: automated lip sync in the wild. In Proc. ACCV. Springer, 251--263."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc","author":"Das Dipanjan","unstructured":"Dipanjan Das, Sandika Biswas, Sanjana Sinha, and Brojeshwar Bhowmick. 2020. Speech-driven facial animation using cascaded gans for learning of motion and texture. In Proc. ECCV. Springer, 408--424."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2944-3"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00584"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_19_1","volume-title":"DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions. arXiv preprint arXiv:2303.07697","author":"Hwang Geumbyeol","year":"2023","unstructured":"Geumbyeol Hwang, Sunwon Hong, Seunghyun Lee, Sungwoo Park, and Gyeongsu Chae. 2023. DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions. arXiv preprint arXiv:2303.07697 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"On the \"steerability\" of generative adversarial networks. arXiv preprint arXiv:1907.07171","author":"Jahanian Ali","year":"2019","unstructured":"Ali Jahanian, Lucy Chai, and Phillip Isola. 2019. On the \"steerability\" of generative adversarial networks. arXiv preprint arXiv:1907.07171 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Learning Representations.","author":"Jahanian Ali","year":"2020","unstructured":"Ali Jahanian, Lucy Chai, and Phillip Isola. 2020. On the \"steerability\" of generative adversarial networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01223"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_25_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. ACM MM. 1428--1436","author":"Rudrabha Mukhopadhyay Prajwal KR","year":"2019","unstructured":"Prajwal KR, Rudrabha Mukhopadhyay, Jerin Philip, Abhishek Jha, Vinay Namboodiri, and CV Jawahar. 2019. Towards automatic face-to-face translation. In Proc. ACM MM. 1428--1436."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"e_1_3_2_1_28_1","volume-title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles. arXiv preprint arXiv:2301.01081","author":"Ma Yifeng","year":"2023","unstructured":"Yifeng Ma, Suzhen Wang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Zhidong Deng, and Xin Yu. 2023. StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles. arXiv preprint arXiv:2301.01081 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"StyleTalker: Oneshot Style-based Audio-driven Talking Head Video Generation. arXiv preprint arXiv:2208.10922","author":"Min Dongchan","year":"2022","unstructured":"Dongchan Min, Minyoung Song, and Sung Ju Hwang. 2022. StyleTalker: Oneshot Style-based Audio-driven Talking Head Video Generation. arXiv preprint arXiv:2208.10922 (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"e_1_3_2_1_31_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_35"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00009"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"e_1_3_2_1_39_1","volume-title":"NeurIPS","volume":"32","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First order motion model for image animation. In NeurIPS, Vol. 32."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. ICLR.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proc. ICLR."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"e_1_3_2_1_43_1","volume-title":"Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786","author":"Song Yang","year":"2018","unstructured":"Yang Song, Jingwen Zhu, Dawei Li, Xiaolong Wang, and Hairong Qi. 2018. Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_1_45_1","volume-title":"Proc","author":"Thies Justus","unstructured":"Justus Thies, Mohamed Elgharib, Ayush Tewari, Christian Theobalt, and Matthias Nie\u00dfner. 2020. Neural voice puppetry: Audio-driven facial reenactment. In Proc. ECCV. Springer, 716--731."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"e_1_3_2_1_48_1","volume-title":"Unsupervised discovery of interpretable directions in the gan latent space. arXiv preprint arXiv:2002.03754","author":"Voynov Andrey","year":"2014","unstructured":"Andrey Voynov and Artem Babenko. 2014. Unsupervised discovery of interpretable directions in the gan latent space. arXiv preprint arXiv:2002.03754 (2014)."},{"key":"e_1_3_2_1_49_1","volume-title":"Proc. ICML. PMLR, 9786--9796","author":"Voynov Andrey","year":"2020","unstructured":"Andrey Voynov and Artem Babenko. 2020. Unsupervised discovery of interpretable directions in the gan latent space. In Proc. ICML. PMLR, 9786--9796."},{"key":"e_1_3_2_1_50_1","volume-title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis. arXiv preprint arXiv:2211.14506","author":"Deng Yu","year":"2022","unstructured":"DuominWang, Yu Deng, Zixin Yin, Heung-Yeung Shum, and BaoyuanWang. 2022. Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis. arXiv preprint arXiv:2211.14506 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"UK","author":"Wang Kaisiyuan","year":"2020","unstructured":"Kaisiyuan Wang, Qianyi Wu, Linsen Song, Zhuoqian Yang, Wayne Wu, Chen Qian, Ran He, Yu Qiao, and Chen Change Loy. 2020. Mead: A large-scale audiovisual dataset for emotional talking-face generation. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXI. Springer, 700--717."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. IJCAI.","author":"Li Lincheng","year":"2021","unstructured":"SuzhenWang, Lincheng Li, Yu Ding, Changjie Fan, and Xin Yu. 2021. Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion. In Proc. IJCAI."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_2_1_55_1","volume-title":"International Conference on Learning Representations.","author":"Wang Yaohui","year":"2022","unstructured":"Yaohui Wang, Di Yang, Francois Bremond, and Antitza Dantcheva. 2022. Latent Image Animator: Learning to Animate Images via Latent Space Navigation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_56_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00297"},{"key":"e_1_3_2_1_59_1","volume-title":"Audiodriven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137","author":"Yi Ran","year":"2020","unstructured":"Ran Yi, Zipeng Ye, Juyong Zhang, Hujun Bao, and Yong-Jin Liu. 2020. Audiodriven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137 (2020)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417774","article-title":"Makelttalk: speaker-aware talking-head animation","volume":"39","author":"Zhou Yang","year":"2020","unstructured":"Yang Zhou, Xintong Han, Eli Shechtman, Jose Echevarria, Evangelos Kalogerakis, and Dingzeyu Li. 2020. Makelttalk: speaker-aware talking-head animation. ACM Transactions On Graphics 39, 6 (2020), 1--15.","journal-title":"ACM Transactions On Graphics"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/327"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612587","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:56Z","timestamp":1755820856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":65,"alternative-id":["10.1145\/3581783.3612587","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612587","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}