{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T08:13:44Z","timestamp":1762071224430,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031197802"},{"type":"electronic","value":"9783031197819"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19781-9_41","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"713-729","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["SCAM! Transferring Humans Between Images with\u00a0Semantic Cross Attention Modulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1903-5110","authenticated-orcid":false,"given":"Nicolas","family":"Dufour","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6296-4222","authenticated-orcid":false,"given":"David","family":"Picard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7368-6993","authenticated-orcid":false,"given":"Vicky","family":"Kalogeiton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"41_CR1","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"41_CR3","unstructured":"Denton, E., Chintala, S., Szlam, A., Fergus, R.: Deep generative image models using a Laplacian pyramid of adversarial networks. In: NeurIPS (2015)"},{"key":"41_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"41_CR5","unstructured":"Dong, H., Liang, X., Gong, K., Lai, H., Zhu, J., Yin, J.: Soft-gated warping-GAN for pose-guided person image synthesis. In: NeurIPS (2018)"},{"key":"41_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Endo, Y., Kanamori, Y.: Diversifying semantic image synthesis and editing via class-and layer-wise VAEs. Comput. Graph. Forum 39(7), 519\u2013530 (2020)","DOI":"10.1111\/cgf.14164"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Fu, D., et al.: Unsupervised pre-training for person re-identification. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"41_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Gu, S., Bao, J., Yang, H., Chen, D., Wen, F., Yuan, L.: Mask-guided portrait editing with conditional GANs. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00355"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Han, X., Hu, X., Huang, W., Scott, M.R.: Clothflow: A flow-based model for clothed person generation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01057"},{"key":"41_CR13","unstructured":"Hudson, D.A., Zitnick, C.L.: Generative adversarial transformers. In: Proceedings ICML (2021)"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"41_CR15","unstructured":"Jaegle, A., et al.: Perceiver IO: a general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)"},{"key":"41_CR16","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver: general perception with iterative attention. In: Proceedings ICML (2021)"},{"key":"41_CR17","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: two transformers can make one strong GAN, and that can scale up. arXiv preprint arXiv:2102.07074 (2021)"},{"key":"41_CR18","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of styleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"41_CR22","unstructured":"Lee, K., Chang, H., Jiang, L., Zhang, H., Tu, Z., Liu, C.: ViTGAN: training GANs with vision transformers. arXiv preprint arXiv:2107.04589 (2021)"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, J., Liu, Y., Lai, Y.K., Dai, Q.: PoNa: pose-guided non-local attention for human pose transfer. In: IEEE Trans. Image Process. 29, 9584\u20139599 (2020)","DOI":"10.1109\/TIP.2020.3029455"},{"key":"41_CR24","unstructured":"Li, P., Xu, Y., Wei, Y., Yang, Y.: Self-correction for human parsing. In: IEEE TPAMI (2020)"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y.J., Singh, K.K.: Collaging class-specific GANs for semantic image synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01415"},{"key":"41_CR26","unstructured":"Lim, J.H., Ye, J.C.: Geometric GAN. arXiv preprint arXiv:1705.02894 (2017)"},{"key":"41_CR27","unstructured":"Liu, X., Yin, G., Shao, J., Wang, X., Li, h.: Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: NeurIPS (2019)"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Gool, L.V.: Pose guided person image generation. In: NeurIPS (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"41_CR30","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"41_CR32","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)"},{"key":"41_CR33","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. In: ArXiv (2018)"},{"key":"41_CR34","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. In: ArXiv (2019)"},{"key":"41_CR35","unstructured":"R.J. Lehman, H.H.: iDesigner 2019. In: FGVC6 (2019)"},{"key":"41_CR36","unstructured":"Sch\u00f6nfeld, E., Sushko, V., Zhang, D., Gall, J., Schiele, B., Khoreva, A.: You only need adversarial supervision for semantic image synthesis. In: ICLR (2021)"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Tan, Z., et al.: Diverse semantic image synthesis via probability distribution modeling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00787"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Tan, Z., et al.: Efficient semantic image synthesis via class-adaptive normalization. In: IEEE TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3076487"},{"key":"41_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-030-58595-2_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tang","year":"2020","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P.H.S., Sebe, N.: XingGAN for person image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 717\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_43"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Yan, Y., Torr, P.H., Sebe, N.: Local class-specific and global image-level generative adversarial networks for semantic-guided scene generation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"41_CR41","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings ICML (2021)"},{"key":"41_CR42","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. In: CVPR (2020)"},{"key":"41_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"41_CR44","unstructured":"Wang, T.C., Liu, M.Y., Tao, A., Liu, G., Kautz, J., Catanzaro, B.: Few-shot video-to-video synthesis. In: NeurIPS (2019)"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"41_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, L., Chen, Y.C., Zhang, X., Jia, J.: Image synthesis via semantic composition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"41_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: StyleSwin: Transformer-based GAN for high-resolution image generation. arXiv preprint arXiv:2112.10762 (2021)","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"41_CR48","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: Proceedings ICML (2019)"},{"key":"41_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, K., Lai, Y.K., Yang, J.: PISE: person image synthesis and editing with decoupled GAN. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"41_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, X., Li, K.: Human pose transfer by adaptive hierarchical deformation. In: CGF (2020)","DOI":"10.1111\/cgf.14148"},{"key":"41_CR51","unstructured":"Zhao, L., Zhang, Z., Chen, T., Metaxas, D., Zhang, H.: Improved transformer for high-resolution GANs. In: NeurIPS, vol. 34 (2021)"},{"key":"41_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"41_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"41_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Qin, Y., Wonka, P.: SEAN: image synthesis with semantic region-adaptive normalization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"41_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., Bai, X.: Progressive pose attention transfer for person image generation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00245"},{"key":"41_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, Z., You, A., Bai, X.: Semantically multi-modal image synthesis. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00551"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19781-9_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:45:19Z","timestamp":1710261919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19781-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197802","9783031197819"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19781-9_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}