{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T11:03:25Z","timestamp":1784372605914,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233960","type":"print"},{"value":"9789819233977","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3397-7_16","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T10:15:25Z","timestamp":1784369725000},"page":"181-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Pose-Guided Video Synthesis via Motion Capture and Skeleton Maps"],"prefix":"10.1007","author":[{"given":"Yujia","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"16_CR1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Y Tian","year":"2021","unstructured":"Tian, Y., Ren, J., Chai, M., Olszewski, K., Peng, X., Metaxas, D.N., et al.: A good image generator is what you need for high-resolution video synthesis. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"16_CR2","first-page":"10039","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"T-C Wang","year":"2021","unstructured":"Wang, T.-C., Mallya, A., Liu, M.-Y.: One-shot free-view neural talking-head synthesis for video conferencing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10039\u201310049. IEEE (2021)"},{"key":"16_CR3","first-page":"15039","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"JS Yoon","year":"2021","unstructured":"Yoon, J.S., Liu, L., Golyanik, V., Sarkar, K., Park, H.S., Theobalt, C.: Pose-guided human animation from a single image in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15039\u201315048. IEEE (2021)"},{"key":"16_CR4","volume-title":"International Conference on Learning Representations (ICLR)","author":"Y Guo","year":"2024","unstructured":"Guo, Y., Yang, C., Rao, A., Liang, Z., Wang, Y., Qiao, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"16_CR5","first-page":"9326","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"T Wang","year":"2024","unstructured":"Wang, T., Li, L., Lin, K., Zhai, Y., Lin, C.-C., Yang, Z., et al.: DisCo: disentangled control for realistic human dance generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9326\u20139336. IEEE (2024)"},{"key":"16_CR6","first-page":"10684","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"R Rombach","year":"2022","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695. IEEE (2022)"},{"key":"16_CR7","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning, PMLR","author":"A Radford","year":"2021","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, PMLR, vol. 139, pp. 8748\u20138763. PMLR (2021)"},{"key":"16_CR8","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"L Hu","year":"2024","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8153\u20138163. IEEE (2024)"},{"key":"16_CR9","first-page":"1481","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Z Xu","year":"2024","unstructured":"Xu, Z., Zhang, J., Liew, J.H., Yan, H., Liu, J.-W., Zhang, C., et al.: MagicAnimate: temporally consistent human image animation using diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1481\u20131490. IEEE (2024)"},{"issue":"1","key":"16_CR10","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/TPAMI.2022.3145820","volume":"45","author":"A Barroso-Laguna","year":"2023","unstructured":"Barroso-Laguna, A., Mikolajczyk, K.: Key.net: keypoint detection by handcrafted and learned CNN filters revisited. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 698\u2013711 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"16_CR11","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2021","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172\u2013186 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR12","first-page":"1","volume":"99","author":"T Chen","year":"2026","unstructured":"Chen, T., Wang, C., Zhang, Y., Xia, K., Qian, P.: DMFusion: degradation-customized mixture-of-experts with adaptive discrimination for multi-modal image fusion. IEEE Trans. Circuits Syst. Video Technol. 99, 1\u20131 (2026)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"16_CR13","doi-asserted-by":"publisher","first-page":"17386","DOI":"10.1109\/TITS.2024.3478051","volume":"26","author":"W Cai","year":"2025","unstructured":"Cai, W., Qian, P., Wang, C., Yao, J., Gao, M., Hu, W., et al.: Multi-source patch feature fusion with neighborhood flash attention transformer for pixel-level vehicle and road recognition in hyperspectral image. IEEE Trans. Intell. Transp. Syst. 26(10), 17386\u201317402 (2025)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"16_CR14","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.aej.2025.12.033","volume":"134","author":"Z Zhou","year":"2026","unstructured":"Zhou, Z., Fu, C., Wang, C., Zhu, P., Xia, K., Qian, P.: Decoupled feature extraction and correspondence modeling for deformable medical image registration using large kernel attention. Alex. Eng. J. 134, 556\u2013569 (2026)","journal-title":"Alex. Eng. J."},{"key":"16_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103904","volume":"127","author":"J Yao","year":"2026","unstructured":"Yao, J., Ma, S., Qian, P., Wang, C., Li, S., Yang, J., et al.: Multi-scale strip-shape kernel convolution based memory and difference attention for industrial anomaly detection. Inf. Fusion. 127, 103904 (2026)","journal-title":"Inf. Fusion"},{"key":"16_CR16","first-page":"22623","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"J Karras","year":"2023","unstructured":"Karras, J., Holynski, A., Wang, T.-C., Kemelmacher-Shlizerman, I.: DreamPose: fashion image-to-video synthesis via stable diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22623\u201322633. IEEE (2023)"},{"key":"16_CR17","first-page":"145","volume-title":"Computer Vision \u2013 ECCV 2024","author":"S Zhu","year":"2025","unstructured":"Zhu, S., Chen, J.L., Dai, Z., Su, Q., Xu, Y., Cao, X., et al.: Champ: controllable and consistent human image animation with 3D parametric guidance. In: Computer Vision \u2013 ECCV 2024, pp. 145\u2013162. Springer, Cham (2025)"},{"key":"16_CR18","volume-title":"International Conference on Learning Representations (ICLR)","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: training-free controllable text-to-video generation. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"16_CR19","volume-title":"Advances in Neural Information Processing Systems 35 (NeurIPS)","author":"A Mallya","year":"2022","unstructured":"Mallya, A., Wang, T.-C., Liu, M.-Y.: Implicit warping for animation with image sets. In: Advances in Neural Information Processing Systems 35 (NeurIPS) (2022)"},{"key":"16_CR20","first-page":"7297","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"RA G\u00fcler","year":"2018","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: DensePose: dense human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7297\u20137306. IEEE (2018)"},{"key":"16_CR21","first-page":"3813","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"L Zhang","year":"2023","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3813\u20133824. IEEE (2023)"},{"key":"16_CR22","volume-title":"International Conference on Learning Representations (ICLR)","author":"G Tevet","year":"2023","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"16_CR23","first-page":"1","volume-title":"2022 IEEE International Conference on Advanced Robotics and Its Social Impacts (ARSO)","author":"N Ooke","year":"2022","unstructured":"Ooke, N., Ikegami, Y., Yamamoto, K., Nakamura, Y.: Transfer learning of deep neural network human pose estimator by domain-specific data for video motion capturing. In: 2022 IEEE International Conference on Advanced Robotics and Its Social Impacts (ARSO), pp. 1\u20136. IEEE (2022)"},{"key":"16_CR24","first-page":"762","volume-title":"2024 International Conference on Integrated Circuits and Communication Systems (ICICACS)","author":"Z Lu","year":"2024","unstructured":"Lu, Z.: Intelligent processing algorithms for motion capture data oriented to artificial intelligence. In: 2024 International Conference on Integrated Circuits and Communication Systems (ICICACS), pp. 762\u2013766. IEEE (2024)"},{"key":"16_CR25","volume-title":"2025 IEEE 3rd International Conference on Control, Electronics and Computer Technology (ICCECT)","author":"C Guang","year":"2025","unstructured":"Guang, C.: Research on optimization model of track and field athlete motion capture based on machine vision. In: 2025 IEEE 3rd International Conference on Control, Electronics and Computer Technology (ICCECT). IEEE (2025)"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1109\/HPCC67675.2025.00106","volume-title":"2025 IEEE International Conference on High Performance Computing and Communications (HPCC)","author":"A Athama","year":"2025","unstructured":"Athama, A., Srivastava, A., Huang, S., Wang, K., Li, Y., Zhai, X.: Wireless single-camera markerless motion capture system for healthcare applications. In: 2025 IEEE International Conference on High Performance Computing and Communications (HPCC), pp. 694\u2013700. IEEE (2025)"},{"issue":"2","key":"16_CR27","volume":"3","author":"C Gu","year":"2023","unstructured":"Gu, C., Lin, W., He, X., Zhang, L., Zhang, M.: IMU-based motion capture system for rehabilitation applications: a systematic review. Biomim. Intell. Robot. 3(2), 100097 (2023)","journal-title":"Biomim. Intell. Robot."},{"key":"16_CR28","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1109\/CITSC64390.2025.00161","volume-title":"2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing (CITSC)","author":"N Shao","year":"2025","unstructured":"Shao, N.: Research on automatic generation of animation characters and motion capture technology based on deep learning. In: 2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing (CITSC), pp. 861\u2013866. IEEE (2025)"},{"key":"16_CR29","first-page":"6840","volume-title":"Advances in Neural Information Processing Systems 33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33, pp. 6840\u20136851. Curran Associates, Inc (2020)"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1109\/ICPR.2010.579","volume-title":"2010 20th International Conference on Pattern Recognition (ICPR)","author":"A Hor\u00e9","year":"2010","unstructured":"Hor\u00e9, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition (ICPR), pp. 2366\u20132369. IEEE (2010)"},{"issue":"4","key":"16_CR31","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR32","first-page":"586","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"R Zhang","year":"2018","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595. IEEE (2018)"},{"key":"16_CR33","volume-title":"Advances in Neural Information Processing Systems 30 (NIPS)","author":"M Heusel","year":"2017","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems 30 (NIPS) (2017)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3397-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T10:15:29Z","timestamp":1784369729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3397-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819233960","9789819233977"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3397-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}