{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:58:50Z","timestamp":1772834330946,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543830","type":"print"},{"value":"9789819543847","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"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\/978-981-95-4384-7_29","type":"book-chapter","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T15:42:44Z","timestamp":1762357364000},"page":"411-425","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Semantic Mask-Guided Image Animation with\u00a0Fused Cross-Attention"],"prefix":"10.1007","author":[{"given":"Jixiang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"jianjun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J, Ren, J., et al.: motion representations for articulated animation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Tao, J., Wang, B., Ge, T., et al.: Motion Transformer for Unsupervised Image Animation. (2022)","DOI":"10.1007\/978-3-031-19787-1_40"},{"key":"29_CR3","unstructured":"Mallya, A., Wang, T.C., Liu, M.Y.: Implicit warping for animation with image sets (2022)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Hong, F.T., Zhang, L., Shen, L., et al.: Depth-aware generative adversarial network for talking head video generation. In; 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"29_CR5","volume-title":"Pose Guided Person Image Generation[J]","author":"L Ma","year":"2017","unstructured":"Ma, L., Xu, J., Sun, Q., et al.: Pose Guided Person Image Generation[J]. Cornell University - arXiv, Cornell University - arXiv (2017)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., et al.: Disentangled person image generation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT (2018)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuiliere, S., Tulyakov, S., et al.: Animating Arbitrary Objects via Deep Motion Transfer. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"29_CR8","volume-title":"First Order Motion Model for Image Animation","author":"A Siarohin","year":"2019","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., et al.: First Order Motion Model for Image Animation. Neural Information Processing Systems, Neural Information Processing Systems (2019)"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01261-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"O Wiles","year":"2018","unstructured":"Wiles, O., Koepke, A.S., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Geng, Z., Cao, C., Tulyakov, S.: 3D Guided Fine-Grained Face Manipulation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.01005"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: subject agnostic face swapping and reenactment. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South) (2019)","DOI":"10.1109\/ICCV.2019.00728"},{"key":"29_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_16","volume-title":"Human Motion Transfer from Poses in the Wild[J]","author":"J Ren","year":"2020","unstructured":"Ren, J., Chai, M., Tulyakov, S., et al.: Human Motion Transfer from Poses in the Wild[J]. Cornell University - arXiv, Cornell University - arXiv (2020)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., et al.: Realtime multi-person 2D pose estimation using part affinity fields[C\/OL]. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"29_CR14","unstructured":"Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2D and 3D Face Alignment problem? And a dataset of 230,000 3D facial landmarks"},{"key":"29_CR15","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv: Computer Vision and Pattern Recognition,arXiv: Computer Vision and Pattern Recognition (2017)"},{"key":"29_CR16","unstructured":"Amos, B., Ludwiczuk, B., Satyanarayanan, M.: OpenFace: a general-purpose face recognition library with mobile applications (2016)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., et al.: Everybody dance now. ITNOW, 2007: 34-34","DOI":"10.1093\/combul\/bwl126"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Doukas, M., Zafeiriou, S., Sharmanska, V.: HeadGAN: One-Shot Neural Head Synthesis and Editing[J]. In: International Conference on Computer Vision, International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Ha, S., Kersner, M., Kim, B., et al.: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 10893\u201310900 (2020)","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollhofer, M., Stamminger, M., et al.: Face2Face: real-Time Face Capture and Reenactment of RGB Videos. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV (2016)","DOI":"10.1109\/CVPR.2016.262"},{"key":"29_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., et al.: Residual attention network for image classification. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuiliere, S., et al.: Deformable GANs for Pose-based Human Image Generation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT. (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"key":"29_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01033","volume-title":"High-Resolution Optical Flow from 1D Attention and Correlation[J]","author":"H Xu","year":"2021","unstructured":"Xu, H., Yang, J., Cai, J., et al.: High-Resolution Optical Flow from 1D Attention and Correlation[J]. Cornell University - arXiv, Cornell University - arXiv (2021)"},{"key":"29_CR25","unstructured":"Zhao, J., Zhang, H.: Thin-Plate Spline Motion Model for Image Animation"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., et al.: Disentangled person image generation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT (2018)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Shalev, Y., Wolf, L.: Image Animation with Perturbed Masks. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA (2022). http:\/\/dx.doi.org\/10.1109\/cvpr52688.2022.00363","DOI":"10.1109\/CVPR52688.2022.00363"},{"key":"29_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-030-01249-6_50","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Pumarola","year":"2018","unstructured":"Pumarola, A., Agudo, A., Martinez, A.M., Sanfeliu, A., Moreno-Noguer, F.: GANimation: anatomically-aware facial animation from a single image. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 835\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_50"},{"key":"29_CR29","doi-asserted-by":"publisher","unstructured":"Li, H., Ding, W., Kang, Y., et al.: CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations[C\/OL]. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic. (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.323.","DOI":"10.18653\/v1\/2021.emnlp-main.323."},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Tao, J., Wang, B., Xu, B., et al.: Structure-Aware Motion Transfer with Deformable Anchor Model. (2022)","DOI":"10.1109\/CVPR52688.2022.00362"},{"key":"29_CR31","unstructured":"Ting-Chun W., Arun M., Ming-Yu L.: One-shot free-view neural talking-head synthesis for video conferencing. In CVPR (2021)"},{"key":"29_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"29_CR33","unstructured":"[1]Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition[J]. In: International Conference on Learning Representations,International Conference on Learning Representations (2015)"},{"key":"29_CR34","unstructured":"Hamdi, D., Albert, A.S., Theo, G.: Are you really smiling at me? Sponta-neous versus posed enjoyment smiles. In ECCV (2012)"},{"key":"29_CR35","unstructured":"Qingzhe G., Bin W., Libin L., Baoquan C.: Unsupervised Co-part Segmentation through Assembly. arXiv: Computer Vision and Pattern Recognition (2021)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4384-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:06:46Z","timestamp":1772806006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4384-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"ISBN":["9789819543830","9789819543847"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4384-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]},"assertion":[{"value":"6 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","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":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}