{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T12:19:11Z","timestamp":1783685951573,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":34,"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\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["62022083"],"award-info":[{"award-number":["62022083"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702491"],"award-info":[{"award-number":["61702491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611772","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"6969-6977","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["CoP: Chain-of-Pose for Image Animation in Large Pose Changes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7195-0765","authenticated-orcid":false,"given":"Xiaomeng","family":"Fu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6642-8160","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9106-8630","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-8009","authenticated-orcid":false,"given":"Jiao","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1107-3873","authenticated-orcid":false,"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480559"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"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\/CVPR.2017.143"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 14638--14647","author":"Cui Aiyu","year":"2021","unstructured":"Aiyu Cui, Daniel McKee, and Svetlana Lazebnik. 2021. Dressing in order: Recurrent person image generation for pose transfer, virtual try-on and outfit editing. In Proceedings of the IEEE\/CVF international conference on computer vision. 14638--14647."},{"key":"e_1_3_2_1_7_1","volume-title":"Diffusion Models Beat GANs on Image Synthesis. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Quinn Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 8780--8794. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/49ad23d1ec9fa4bd8d77d02681df5cfa-Abstract.html"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"e_1_3_2_1_10_1","volume-title":"Fourier Spectrum Discrepancies in Deep Network Generated Images. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Dzanic Tarik","year":"2020","unstructured":"Tarik Dzanic, Karan Shah, and Freddie D. Witherden. 2020. Fourier Spectrum Discrepancies in Deep Network Generated Images. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1f8d87e1161af68b81bace188a1ec624-Abstract.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_14_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459884"},{"key":"e_1_3_2_1_16_1","volume-title":"18th Annual Conference of the International Speech Communication Association","author":"Nagrani Arsha","year":"2017","unstructured":"Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. VoxCeleb: A Large-Scale Speaker Identification Dataset. In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017, Francisco Lacerda (Ed.). ISCA, 2616--2620. http:\/\/www.isca-speech.org\/archive\/Interspeech_2017\/abstracts\/0950.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_1_18_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"5310","author":"Rahaman Nasim","year":"2019","unstructured":"Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, and Aaron C. Courville. 2019. On the Spectral Bias of Neural Networks. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 5301--5310. http:\/\/proceedings.mlr.press\/v97\/rahaman19a.html"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_16"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"e_1_3_2_1_22_1","volume-title":"First Order Motion Model for Image Animation. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019b. First Order Motion Model for Image Animation. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9 -Buc, Emily B. Fox, and Roman Garnett (Eds.). 7135--7145. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/31c0b36aef265d9221af80872ceb62f9-Abstract.html"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_2_1_24_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"e_1_3_2_1_26_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Wang Yaohui","year":"2022","unstructured":"Yaohui Wang, Di Yang, Francc ois Br\u00e9 mond, and Antitza Dantcheva. 2022. Latent Image Animator: Learning to Animate Images via Latent Space Navigation. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=7r6kDq0mK_"},{"key":"e_1_3_2_1_27_1","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed H Chi Quoc V Le Denny Zhou et al. [n. d.]. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"e_1_3_2_1_29_1","volume-title":"Overview frequency principle\/spectral bias in deep learning. ArXiv preprint","author":"John Xu Zhi-Qin","year":"2022","unstructured":"Zhi-Qin John Xu, Yaoyu Zhang, and Tao Luo. 2022. Overview frequency principle\/spectral bias in deep learning. ArXiv preprint, Vol. abs\/2201.07395 (2022). https:\/\/arxiv.org\/abs\/2201.07395"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00758"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"e_1_3_2_1_32_1","volume-title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation. ArXiv preprint","author":"Zhang Bowen","year":"2022","unstructured":"Bowen Zhang, Chenyang Qi, Pan Zhang, Bo Zhang, HsiangTao Wu, Dong Chen, Qifeng Chen, Yong Wang, and Fang Wen. 2022. MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation. ArXiv preprint, Vol. abs\/2212.08062 (2022). https:\/\/arxiv.org\/abs\/2212.08062"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00537"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"}],"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\/3581783.3611772","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:15:03Z","timestamp":1755821703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":34,"alternative-id":["10.1145\/3581783.3611772","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611772","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"}}]}}