{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:29:32Z","timestamp":1759332572912,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The Youth Innovation Promotion Association Chinese Academy of Sciences","award":["Y2021122"],"award-info":[{"award-number":["Y2021122"]}]},{"name":"The National Key R&D Program of China under Grand","award":["No. 2020AAA0103800"],"award-info":[{"award-number":["No. 2020AAA0103800"]}]},{"name":"The National Nature Science Foundation of China","award":["62121002, 62022076, U1936210, 62102127"],"award-info":[{"award-number":["62121002, 62022076, U1936210, 62102127"]}]},{"name":"The Fundamental Research Funds for the Central Universities under Grant","award":["WK3480000011"],"award-info":[{"award-number":["WK3480000011"]}]},{"name":"The Hefei Postdoc- toral Research Activities Foundation","award":["BSH202101"],"award-info":[{"award-number":["BSH202101"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547896","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"1128-1137","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer"],"prefix":"10.1145","author":[{"given":"Quanwei","family":"Yang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Xinchen","family":"Liu","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}]},{"given":"Wu","family":"Liu","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Xiaoyan","family":"Gu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Lingyun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"volume-title":"Synthesizing Images of Humans in Unseen Poses. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8340--8348","author":"Balakrishnan Guha","key":"e_1_3_2_2_1_1","unstructured":"Guha Balakrishnan , Amy Zhao , Adrian V. Dalca , Fr\u00e9 do Durand , and John V. Guttag . 2018 . Synthesizing Images of Humans in Unseen Poses. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8340--8348 . Guha Balakrishnan, Amy Zhao, Adrian V. Dalca, Fr\u00e9 do Durand, and John V. Guttag. 2018. Synthesizing Images of Humans in Unseen Poses. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8340--8348."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2463223"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"volume-title":"Everybody Dance Now. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5932--5941","author":"Chan Caroline","key":"e_1_3_2_2_4_1","unstructured":"Caroline Chan , Shiry Ginosar , Tinghui Zhou , and Alexei A. Efros . 2019 . Everybody Dance Now. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5932--5941 . Caroline Chan, Shiry Ginosar, Tinghui Zhou, and Alexei A. Efros. 2019. Everybody Dance Now. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5932--5941."},{"key":"e_1_3_2_2_5_1","volume-title":"Single-Shot Freestyle Dance Reenactment. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 882--891","author":"Gafni Oran","year":"2021","unstructured":"Oran Gafni , Oron Ashual , and Lior Wolf . 2021 . Single-Shot Freestyle Dance Reenactment. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 882--891 . Oran Gafni, Oron Ashual, and Lior Wolf. 2021. Single-Shot Freestyle Dance Reenactment. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 882--891."},{"key":"e_1_3_2_2_6_1","unstructured":"Ian J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron C. Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems (NIPS). 2672--2680.  Ian J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron C. Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems (NIPS). 2672--2680."},{"key":"e_1_3_2_2_7_1","volume-title":"StylePeople: A Generative Model of Fullbody Human Avatars. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5151--5160","author":"Grigorev Artur","year":"2021","unstructured":"Artur Grigorev , Karim Iskakov , Anastasia Ianina , Renat Bashirov , Ilya Zakharkin , Alexander Vakhitov , and Victor Lempitsky . 2021 . StylePeople: A Generative Model of Fullbody Human Avatars. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5151--5160 . Artur Grigorev, Karim Iskakov, Anastasia Ianina, Renat Bashirov, Ilya Zakharkin, Alexander Vakhitov, and Victor Lempitsky. 2021. StylePeople: A Generative Model of Fullbody Human Avatars. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5151--5160."},{"key":"e_1_3_2_2_8_1","volume-title":"DensePose: Dense Human Pose Estimation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7297--7306","author":"Riza Alp G\u00fc","year":"2018","unstructured":"Riza Alp G\u00fc ler, Natalia Neverova , and Iasonas Kokkinos . 2018 . DensePose: Dense Human Pose Estimation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7297--7306 . Riza Alp G\u00fc ler, Natalia Neverova, and Iasonas Kokkinos. 2018. DensePose: Dense Human Pose Estimation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7297--7306."},{"volume-title":"Mask R-CNN. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2980--2988","author":"He Kaiming","key":"e_1_3_2_2_9_1","unstructured":"Kaiming He , Georgia Gkioxari , Piotr Doll\u00e1 r, and Ross B. Girshick . 2017 . Mask R-CNN. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2980--2988 . Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1 r, and Ross B. Girshick. 2017. Mask R-CNN. In IEEE\/CVF International Conference on Computer Vision (ICCV). 2980--2988."},{"key":"e_1_3_2_2_10_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778 . Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778."},{"key":"e_1_3_2_2_11_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems (NIPS). 6626--6637.  Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems (NIPS). 6626--6637."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00233"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"volume-title":"Image-to-Image Translation with Conditional Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5967--5976","author":"Isola Phillip","key":"e_1_3_2_2_14_1","unstructured":"Phillip Isola , Jun-Yan Zhu , Tinghui Zhou , and Alexei A. Efros . 2017 . Image-to-Image Translation with Conditional Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5967--5976 . Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. 2017. Image-to-Image Translation with Conditional Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5967--5976."},{"key":"e_1_3_2_2_15_1","volume-title":"Cross-Identity Motion Transfer for Arbitrary Objects Through Pose-Attentive Video Reassembling. In European Conference on Computer Vision (ECCV). 292--308","author":"Jeon Subin","year":"2020","unstructured":"Subin Jeon , Seonghyeon Nam , Seoung Wug Oh , and Seon Joo Kim . 2020 . Cross-Identity Motion Transfer for Arbitrary Objects Through Pose-Attentive Video Reassembling. In European Conference on Computer Vision (ECCV). 292--308 . Subin Jeon, Seonghyeon Nam, Seoung Wug Oh, and Seon Joo Kim. 2020. Cross-Identity Motion Transfer for Arbitrary Objects Through Pose-Attentive Video Reassembling. In European Conference on Computer Vision (ECCV). 292--308."},{"key":"e_1_3_2_2_16_1","volume-title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution. In European Conference on Computer Vision (ECCV). 694--711","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson , Alexandre Alahi , and Li Fei-Fei . 2016 . Perceptual Losses for Real-Time Style Transfer and Super-Resolution. In European Conference on Computer Vision (ECCV). 694--711 . Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. In European Conference on Computer Vision (ECCV). 694--711."},{"key":"e_1_3_2_2_17_1","volume-title":"End-to-End Recovery of Human Shape and Pose. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7122--7131","author":"Kanazawa Angjoo","year":"2018","unstructured":"Angjoo Kanazawa , Michael J. Black , David W. Jacobs , and Jitendra Malik . 2018 . End-to-End Recovery of Human Shape and Pose. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7122--7131 . Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik. 2018. End-to-End Recovery of Human Shape and Pose. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7122--7131."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR).","author":"Diederik","key":"e_1_3_2_2_19_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR). Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_20_1","volume-title":"Self-Correction for Human Parsing","author":"Li Peike","year":"2020","unstructured":"Peike Li , Yunqiu Xu , Yunchao Wei , and Yi Yang . 2020. Self-Correction for Human Parsing . IEEE Trans. Pattern Anal. Mach. Intell . ( 2020 ), 3260 -- 3271. Peike Li, Yunqiu Xu, Yunchao Wei, and Yi Yang. 2020. Self-Correction for Human Parsing. IEEE Trans. Pattern Anal. Mach. Intell. (2020), 3260 -- 3271."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350854"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537337"},{"key":"e_1_3_2_2_23_1","volume-title":"Recent advances in monocular 2d and 3d human pose estimation: A deep learning perspective. ACM Computing Surveys","author":"Liu Wu","year":"2022","unstructured":"Wu Liu , Qian Bao , Yu Sun , and Tao Mei . 2022a. Recent advances in monocular 2d and 3d human pose estimation: A deep learning perspective. ACM Computing Surveys ( 2022 ). Wu Liu, Qian Bao, Yu Sun, and Tao Mei. 2022a. Recent advances in monocular 2d and 3d human pose estimation: A deep learning perspective. ACM Computing Surveys (2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"Appearance Transfer and Novel View Synthesis. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5903--5912","author":"Liu Wen","year":"2019","unstructured":"Wen Liu , Zhixin Piao , Jie Min , Wenhan Luo , Lin Ma , and Shenghua Gao . 2019 b. Liquid Warping GAN: A Unified Framework for Human Motion Imitation , Appearance Transfer and Novel View Synthesis. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5903--5912 . Wen Liu, Zhixin Piao, Jie Min, Wenhan Luo, Lin Ma, and Shenghua Gao. 2019b. Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis. In IEEE\/CVF International Conference on Computer Vision (ICCV). 5903--5912."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350857"},{"key":"e_1_3_2_2_27_1","volume-title":"Deep Dual Consecutive Network for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 525--534","author":"Liu Zhenguang","year":"2021","unstructured":"Zhenguang Liu , Haoming Chen , Runyang Feng , Shuang Wu , Shouling Ji , Bailin Yang , and Xun Wang . 2021 a. Deep Dual Consecutive Network for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 525--534 . Zhenguang Liu, Haoming Chen, Runyang Feng, Shuang Wu, Shouling Ji, Bailin Yang, and Xun Wang. 2021a. Deep Dual Consecutive Network for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 525--534."},{"key":"e_1_3_2_2_28_1","volume-title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11006--11016","author":"Liu Zhenguang","year":"2022","unstructured":"Zhenguang Liu , Runyang Feng , Haoming Chen , Shuang Wu , Yixing Gao , Yunjun Gao , and Xiang Wang . 2022 b. Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11006--11016 . Zhenguang Liu, Runyang Feng, Haoming Chen, Shuang Wu, Yixing Gao, Yunjun Gao, and Xiang Wang. 2022b. Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11006--11016."},{"key":"e_1_3_2_2_29_1","volume-title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","author":"Liu Zhenguang","year":"2021","unstructured":"Zhenguang Liu , Shuang Wu , Shuyuan Jin , Shouling Ji , Qi Liu , Shijian Lu , and Li Cheng . 2021b. Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction . IEEE Trans. Pattern Anal. Mach. Intell . ( 2021 ), 1--16. Zhenguang Liu, Shuang Wu, Shuyuan Jin, Shouling Ji, Qi Liu, Shijian Lu, and Li Cheng. 2021b. Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction. IEEE Trans. Pattern Anal. Mach. Intell. (2021), 1--16."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_2_32_1","unstructured":"Liqian Ma Xu Jia Qianru Sun Bernt Schiele Tinne Tuytelaars and Luc Van Gool. 2017. Pose Guided Person Image Generation. In Advances in Neural Information Processing Systems (NIPS). 406--416.  Liqian Ma Xu Jia Qianru Sun Bernt Schiele Tinne Tuytelaars and Luc Van Gool. 2017. Pose Guided Person Image Generation. In Advances in Neural Information Processing Systems (NIPS). 406--416."},{"key":"e_1_3_2_2_33_1","volume-title":"Conditional Generative Adversarial Nets. CoRR","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero . 2014. Conditional Generative Adversarial Nets. CoRR , Vol. abs\/ 1411 .1784 ( 2014 ). Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. CoRR , Vol. abs\/1411.1784 (2014)."},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10975--10985","author":"Pavlakos Georgios","key":"e_1_3_2_2_34_1","unstructured":"Georgios Pavlakos , Vasileios Choutas , Nima Ghorbani , Timo Bolkart , Ahmed A. A. Osman , Dimitrios Tzionas , and Michael J. Black . 2019. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image . In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10975--10985 . Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black. 2019. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10975--10985."},{"key":"e_1_3_2_2_35_1","volume-title":"Pose-Normalized Image Generation for Person Re-identification. In European Conference on Computer Vision (ECCV). 661--678","author":"Qian Xuelin","year":"2018","unstructured":"Xuelin Qian , Yanwei Fu , Tao Xiang , Wenxuan Wang , Jie Qiu , Yang Wu , Yu-Gang Jiang , and Xiangyang Xue . 2018 . Pose-Normalized Image Generation for Person Re-identification. In European Conference on Computer Vision (ECCV). 661--678 . Xuelin Qian, Yanwei Fu, Tao Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, and Xiangyang Xue. 2018. Pose-Normalized Image Generation for Person Re-identification. In European Conference on Computer Vision (ECCV). 661--678."},{"key":"e_1_3_2_2_36_1","volume-title":"Real-Time Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779--788","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon , Santosh Kumar Divvala , Ross B. Girshick , and Ali Farhadi . 2016 . You Only Look Once: Unified , Real-Time Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779--788 . Joseph Redmon, Santosh Kumar Divvala, Ross B. Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779--788."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478560"},{"key":"e_1_3_2_2_38_1","volume-title":"Sergey Tulyakov, Elisa Ricci, and Nicu Sebe.","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin , St\u00e9 phane Lathuili\u00e8 re , Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019 . First Order Motion Model for Image Animation. In Advances in Neural Information Processing Systems (NIPS) . 7135--7145. Aliaksandr Siarohin, St\u00e9 phane Lathuili\u00e8 re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First Order Motion Model for Image Animation. In Advances in Neural Information Processing Systems (NIPS). 7135--7145."},{"key":"e_1_3_2_2_39_1","volume-title":"Motion Representations for Articulated Animation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 13653--13662","author":"Siarohin Aliaksandr","year":"2021","unstructured":"Aliaksandr Siarohin , Oliver J. Woodford , Jian Ren , Menglei Chai , and Sergey Tulyakov . 2021 . Motion Representations for Articulated Animation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 13653--13662 . Aliaksandr Siarohin, Oliver J. Woodford, Jian Ren, Menglei Chai, and Sergey Tulyakov. 2021. Motion Representations for Articulated Animation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 13653--13662."},{"key":"e_1_3_2_2_40_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In 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 International Conference on Learning Representations (ICLR). Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_41_1","volume-title":"Black","author":"Sun Yu","year":"2022","unstructured":"Yu Sun , Wu Liu , Qian Bao , Yili Fu , Tao Mei , and Michael J . Black . 2022 . Putting People in their Place : Monocular Regression of 3D People in Depth . In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 13243--13252. Yu Sun, Wu Liu, Qian Bao, Yili Fu, Tao Mei, and Michael J. Black. 2022. Putting People in their Place: Monocular Regression of 3D People in Depth. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 13243--13252."},{"key":"e_1_3_2_2_42_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818--2826","author":"Szegedy Christian","year":"2016","unstructured":"Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe , Jonathon Shlens , and Zbigniew Wojna . 2016 . Rethinking the Inception Architecture for Computer Vision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818--2826 . Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2016. Rethinking the Inception Architecture for Computer Vision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818--2826."},{"key":"e_1_3_2_2_43_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems (NIPS). 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems (NIPS). 5998--6008."},{"key":"e_1_3_2_2_44_1","unstructured":"Ting-Chun Wang Ming-Yu Liu Andrew Tao Guilin Liu Bryan Catanzaro and Jan Kautz. 2019. Few-shot Video-to-Video Synthesis. In Advances in Neural Information Processing Systems (NIPS). 5014--5025.  Ting-Chun Wang Ming-Yu Liu Andrew Tao Guilin Liu Bryan Catanzaro and Jan Kautz. 2019. Few-shot Video-to-Video Synthesis. In Advances in Neural Information Processing Systems (NIPS). 5014--5025."},{"key":"e_1_3_2_2_45_1","volume-title":"High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8798--8807","author":"Wang Ting-Chun","year":"2018","unstructured":"Ting-Chun Wang , Ming-Yu Liu , Jun-Yan Zhu , Andrew Tao , Jan Kautz , and Bryan Catanzaro . 2018 a. High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8798--8807 . Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018a. High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 8798--8807."},{"key":"e_1_3_2_2_46_1","unstructured":"Ting-Chun Wang Ming-Yu Liu Jun-Yan Zhu Nikolai Yakovenko Andrew Tao Jan Kautz and Bryan Catanzaro. 2018b. Video-to-Video Synthesis. In Advances in Neural Information Processing Systems (NIPS). 1152--1164.  Ting-Chun Wang Ming-Yu Liu Jun-Yan Zhu Nikolai Yakovenko Andrew Tao Jan Kautz and Bryan Catanzaro. 2018b. Video-to-Video Synthesis. In Advances in Neural Information Processing Systems (NIPS). 1152--1164."},{"volume-title":"Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis. In International Conference on 3D Vision (3DV). IEEE, 268--277","author":"Wang Tuanfeng Y.","key":"e_1_3_2_2_47_1","unstructured":"Tuanfeng Y. Wang , Duygu Ceylan , Krishna Kumar Singh , and Niloy J. Mitra . 2021 . Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis. In International Conference on 3D Vision (3DV). IEEE, 268--277 . Tuanfeng Y. Wang, Duygu Ceylan, Krishna Kumar Singh, and Niloy J. Mitra. 2021. Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis. In International Conference on 3D Vision (3DV). IEEE, 268--277."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16391"},{"key":"e_1_3_2_2_50_1","volume-title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5305--5314","author":"Yang Zhuoqian","year":"2020","unstructured":"Zhuoqian Yang , Wentao Zhu , Wayne Wu , Chen Qian , Qiang Zhou , Bolei Zhou , and Chen Change Loy . 2020 . TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5305--5314 . Zhuoqian Yang, Wentao Zhu, Wayne Wu, Chen Qian, Qiang Zhou, Bolei Zhou, and Chen Change Loy. 2020. TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5305--5314."},{"key":"e_1_3_2_2_51_1","volume-title":"Occlusion-aware Video Temporal Consistency. In ACM International Conference on Multimedia (MM). 777--785","author":"Yao Chun-Han","year":"2017","unstructured":"Chun-Han Yao , Chia-Yang Chang , and Shao-Yi Chien . 2017 . Occlusion-aware Video Temporal Consistency. In ACM International Conference on Multimedia (MM). 777--785 . Chun-Han Yao, Chia-Yang Chang, and Shao-Yi Chien. 2017. Occlusion-aware Video Temporal Consistency. In ACM International Conference on Multimedia (MM). 777--785."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091863"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"e_1_3_2_2_54_1","volume-title":"Neural Architecture Search for Joint Human Parsing and Pose Estimation. In IEEE\/CVF International Conference on Computer Vision (ICCV). 11365--11374","author":"Zeng Dan","year":"2021","unstructured":"Dan Zeng , Yuhang Huang , Qian Bao , Junjie Zhang , Chi Su , and Wu Liu . 2021 . Neural Architecture Search for Joint Human Parsing and Pose Estimation. In IEEE\/CVF International Conference on Computer Vision (ICCV). 11365--11374 . Dan Zeng, Yuhang Huang, Qian Bao, Junjie Zhang, Chi Su, and Wu Liu. 2021. Neural Architecture Search for Joint Human Parsing and Pose Estimation. In IEEE\/CVF International Conference on Computer Vision (ICCV). 11365--11374."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01959"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Lisboa Portugal","acronym":"MM '22"},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547896","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:30Z","timestamp":1750186830000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":57,"alternative-id":["10.1145\/3503161.3547896","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547896","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}