{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:53:06Z","timestamp":1781538786760,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Jilin Provincial Scientific and Technological Development Program","award":["20230201082GX"],"award-info":[{"award-number":["20230201082GX"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810650","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1908-1917","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ExpPortrait: Novel Expression Generation for Fine-Grained Controllable Portrait Animation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7417-2687","authenticated-orcid":false,"given":"Hualiang","family":"Wei","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6490-9852","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00834"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00986"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Zheng Chong Wenqing Zhang Shiyue Zhang Jun Zheng Xiao Dong Haoxiang Li Yiling Wu Dongmei Jiang and Xiaodan Liang. 2025. Catv2ton: Taming diffusion transformers for vision-based virtual try-on with temporal concatenation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.11325 (2025). 10.48550\/arXiv.2501.11325","DOI":"10.48550\/arXiv.2501.11325"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02012"},{"key":"e_1_3_3_1_12_2","unstructured":"Ian\u00a0J Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00995"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Hanzhong Guo Hongwei Yi Daquan Zhou Alexander\u00a0William Bergman Michael Lingelbach and Yizhou Yu. 2024. Real-time One-Step Diffusion-based Expressive Portrait Videos Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.13479 (2024). 10.48550\/arXiv.2412.13479","DOI":"10.48550\/arXiv.2412.13479"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Jianzhu Guo Dingyun Zhang Xiaoqiang Liu Zhizhou Zhong Yuan Zhang Pengfei Wan and Di Zhang. 2024. Liveportrait: Efficient portrait animation with stitching and retargeting control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.03168 (2024). 10.48550\/arXiv.2407.03168","DOI":"10.48550\/arXiv.2407.03168"},{"key":"e_1_3_3_1_16_2","first-page":"20","volume-title":"European Conference on Computer Vision","author":"Han Yue","year":"2024","unstructured":"Yue Han, Junwei Zhu, Keke He, Xu Chen, Yanhao Ge, Wei Li, Xiangtai Li, Jiangning Zhang, Chengjie Wang, and Yong Liu. 2024. Face-adapter for pre-trained diffusion models with fine-grained id and attribute control. In European Conference on Computer Vision. Springer, 20\u201336."},{"key":"e_1_3_3_1_17_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00524"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Tobias Kirschstein Shenhan Qian Simon Giebenhain Tim Walter and Matthias Nie\u00dfner. 2023. Nersemble: Multi-view radiance field reconstruction of human heads. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201314.","DOI":"10.1145\/3592455"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3407662.3407756"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Ronghui Li Hongwen Zhang Yachao Zhang Yuxiang Zhang Youliang Zhang Jie Guo Yan Zhang Xiu Li and Yebin Liu. 2024. Lodge++: High-quality and long dance generation with vivid choreography patterns. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.20389 (2024). 10.48550\/arXiv.2410.20389","DOI":"10.48550\/arXiv.2410.20389"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Tianye Li Timo Bolkart Michael\u00a0J Black Hao Li and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans.ACM Trans. Graph. 36 6 (2017) 194\u20131.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01222"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02444"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01252"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00013"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14062"},{"key":"e_1_3_3_1_32_2","first-page":"181","volume-title":"European Conference on Computer Vision","author":"Ostrek Mirela","year":"2024","unstructured":"Mirela Ostrek and Justus Thies. 2024. Stable video portraits. In European Conference on Computer Vision. Springer, 181\u2013198."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_3_1_36_2","unstructured":"Aliaksandr Siarohin St\u00e9phane Lathuili\u00e8re Sergey Tulyakov Elisa Ricci and Nicu Sebe. 2019. First order motion model for image animation. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Vanessa Sklyarova Egor Zakharov Otmar Hilliges Michael\u00a0J Black and Justus Thies. 2023. Haar: Text-conditioned generative model of 3d strand-based human hairstyles. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11666 (2023). 10.48550\/arXiv.2312.11666","DOI":"10.48550\/arXiv.2312.11666"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Phong Tran Egor Zakharov Long-Nhat Ho Liwen Hu Adilbek Karmanov Aviral Agarwal McLean Goldwhite Ariana\u00a0Bermudez Venegas Anh\u00a0Tuan Tran and Hao Li. 2024. Voodoo xp: Expressive one-shot head reenactment for vr telepresence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.16204 (2024). 10.48550\/arXiv.2405.16204","DOI":"10.48550\/arXiv.2405.16204"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Cong Wang Kuan Tian Jun Zhang Yonghang Guan Feng Luo Fei Shen Zhiwei Jiang Qing Gu Xiao Han and Wei Yang. 2024. V-express: Conditional dropout for progressive training of portrait video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02511 (2024). 10.48550\/arXiv.2406.02511","DOI":"10.48550\/arXiv.2406.02511"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Wenqing Wang Haosen Yang Josef Kittler and Xiatian Zhu. 2024. Single image any face: Generalisable 3D face generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.16990 (2024). 10.48550\/arXiv.2409.16990","DOI":"10.48550\/arXiv.2409.16990"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Huawei Wei Zejun Yang and Zhisheng Wang. 2024. Aniportrait: Audio-driven synthesis of photorealistic portrait animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17694 (2024). 10.48550\/arXiv.2403.17694","DOI":"10.48550\/arXiv.2403.17694"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Sicheng Xu Guojun Chen Yu-Xiao Guo Jiaolong Yang Chong Li Zhenyu Zang Yizhong Zhang Xin Tong and Baining Guo. 2024. Vasa-1: Lifelike audio-driven talking faces generated in real time. Advances in Neural Information Processing Systems 37 (2024) 660\u2013684.","DOI":"10.52202\/079017-0021"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Zunnan Xu Yukang Lin Haonan Han Sicheng Yang Ronghui Li Yachao Zhang and Xiu Li. 2024. Mambatalk: Efficient holistic gesture synthesis with selective state space models. Advances in Neural Information Processing Systems 37 (2024) 20055\u201320080.","DOI":"10.52202\/079017-0633"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01483"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","unstructured":"Shurong Yang Huadong Li Juhao Wu Minhao Jing Linze Li Renhe Ji Jiajun Liang and Haoqiang Fan. 2024. Megactor: Harness the power of raw video for vivid portrait animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.20851 (2024). 10.48550\/arXiv.2405.20851","DOI":"10.48550\/arXiv.2405.20851"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00070"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02116"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Longtao Zheng Yifan Zhang Hanzhong Guo Jiachun Pan Zhenxiong Tan Jiahao Lu Chuanxin Tang Bo An and Shuicheng Yan. 2024. Memo: Memory-guided diffusion for expressive talking video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04448 (2024). 10.48550\/arXiv.2412.04448","DOI":"10.48550\/arXiv.2412.04448"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_11"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:54:04Z","timestamp":1781535244000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":53,"alternative-id":["10.1145\/3805622.3810650","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810650","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}