{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T22:40:44Z","timestamp":1760740844176,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819534555","type":"print"},{"value":"9789819534562","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3456-2_17","type":"book-chapter","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T09:28:05Z","timestamp":1760693285000},"page":"239-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PoseMaster: Editing Your Pose in\u00a0a\u00a0Video with\u00a0a\u00a0One-Shot Framework"],"prefix":"10.1007","author":[{"given":"Yiwen","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jianguo","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Min","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Boquan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Myung Hwan","family":"Na","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"17_CR1","unstructured":"Chang, D., et al.: MagicPose: realistic human poses and facial expressions retargeting with identity-aware diffusion. In: Forty-first International Conference on Machine Learning (2023)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Fan, D., et al.: One-shot learning for pose-guided person image synthesis in the wild. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10890784"},{"key":"17_CR3","unstructured":"Fang, Z., et al.: ViViD: Video virtual try-on using diffusion models. arXiv preprint arXiv:2405.11794 (2024)"},{"key":"17_CR4","unstructured":"Guo, Y., et al.: AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"17_CR5","unstructured":"He, R., et al.: FreeEdit: Mask-free reference-based image editing with multi-modal instruction. arXiv preprint arXiv:2409.18071 (2024)"},{"key":"17_CR6","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Hong, F.T., et al.: Free-viewpoint human animation with pose-correlated reference selection. arXiv preprint arXiv:2412.17290 (2024)","DOI":"10.1109\/CVPR52734.2025.02445"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Hu, 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, pp. 8153\u20138163 (2024)","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Jafarian, Y., Park, H.S.: Learning high fidelity depths of dressed humans by watching social media dance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12753\u201312762 (June 2021)","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: DreamPose: fashion image-to-video synthesis via stable diffusion. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22623\u201322633. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, M.J., Lee, J., Choo, J.: TCAN: Animating human images with temporally consistent pose guidance using diffusion models (2024). https:\/\/arxiv.org\/abs\/2407.09012","DOI":"10.1007\/978-3-031-73202-7_19"},{"key":"17_CR13","unstructured":"Liu, J., Yu, K., Feng, M., Guo, X., Cui, M.: Disentangling foreground and background motion for enhanced realism in human video generation (2024). https:\/\/arxiv.org\/abs\/2405.16393"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: VideoFusion: Decomposed diffusion models for high-quality video generation. arXiv preprint arXiv:2303.08320 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: pose-guided text-to-video generation using pose-free videos. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 4117\u20134125 (2024)","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Men, Y., Yao, Y., Cui, M., Bo, L.: MIMO: Controllable character video synthesis with spatial decomposed modeling. arXiv preprint arXiv:2409.16160 (2024)","DOI":"10.1109\/CVPR52734.2025.01973"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"17_CR18","doi-asserted-by":"crossref","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Shi, X., et\u00a0al.: Motion-I2V: consistent and controllable image-to-video generation with explicit motion modeling. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657497"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Singer, U., et al.: Video editing via factorized diffusion distillation. In: European Conference on Computer Vision, pp. 450\u2013466. Springer (2024)","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: StyleGAN-V: a continuous video generator with the price, image quality and perks of StyleGAN2. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3626\u20133636 (2022)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"17_CR22","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: AR-Diffusion: Asynchronous video generation with auto-regressive diffusion (2025). https:\/\/arxiv.org\/abs\/2503.07418","DOI":"10.1109\/CVPR52734.2025.00690"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Tian, L., Wang, Q., Zhang, B., Bo, L.: EMO: emote portrait alive generating expressive portrait videos with Audio2Video diffusion model under weak conditions. In: European Conference on Computer Vision, pp. 244\u2013260. Springer (2024)","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Tu, S., et al.: MotionEditor: editing video motion via content-aware diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2024)","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"17_CR26","unstructured":"Tu, S., et al.: MotionFollower: Editing video motion via lightweight score-guided diffusion. arXiv preprint arXiv:2405.20325 (2024)"},{"key":"17_CR27","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"17_CR28","unstructured":"Wang, L., Boddeti, V., Lim, S.: Action reimagined: Text-to-pose video editing for dynamic human actions. arXiv preprint arXiv:2403.07198 (2024)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: UniAnimate: Taming unified video diffusion models for consistent human image animation. arXiv preprint arXiv:2406.01188 (2024)","DOI":"10.1007\/s11432-024-4592-3"},{"issue":"4","key":"17_CR30","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":"17_CR31","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: MagicAnimate: temporally consistent human image animation using diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1481\u20131490 (2024)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"17_CR33","unstructured":"Xue, J., et\u00a0al.: Follow-your-pose v2: Multiple-condition guided character image animation for stable pose control. arXiv preprint arXiv:2406.03035 (2024)"},{"key":"17_CR34","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"17_CR35","doi-asserted-by":"crossref","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, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"17_CR36","unstructured":"Zhang, Q., Yang, C., Shen, Y., Xu, Y., Zhou, B.: Towards smooth video composition. arXiv preprint arXiv:2212.07413 (2022)"},{"key":"17_CR37","doi-asserted-by":"crossref","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 Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"17_CR38","unstructured":"Zhang, S., Yang, H., Lim, S.N.: VideoMerge: Towards training-free long video generation (2025). https:\/\/arxiv.org\/abs\/2503.09926"},{"key":"17_CR39","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: Training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"},{"key":"17_CR40","unstructured":"Zhang, Y., et al.: MimicMotion: High-quality human motion video generation with confidence-aware pose guidance. arXiv preprint arXiv:2406.19680 (2024)"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Zhong, X., Huang, X., Yang, X., Lin, G., Wu, Q.: DeCo: decoupled human-centered diffusion video editing with motion consistency. In: European Conference on Computer Vision, pp. 352\u2013370. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_20"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, S., et al.: Champ: controllable and consistent human image animation with 3D parametric guidance. In: European Conference on Computer Vision, pp. 145\u2013162. Springer (2025)","DOI":"10.1007\/978-3-031-73001-6_9"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3456-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T22:04:15Z","timestamp":1760738655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3456-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"ISBN":["9789819534555","9789819534562"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3456-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"17 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}