{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:02:23Z","timestamp":1777568543158,"version":"3.51.4"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031500718","type":"print"},{"value":"9783031500725","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-50072-5_36","type":"book-chapter","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T08:02:17Z","timestamp":1703750537000},"page":"455-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FoldGEN: Multimodal Transformer for\u00a0Garment Sketch-to-Photo Generation"],"prefix":"10.1007","author":[{"given":"Jia","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","first-page":"2145","DOI":"10.1007\/s00371-020-01943-0","volume":"36","author":"J Bai","year":"2020","unstructured":"Bai, J., Chen, R., Liu, M.: Feature-attention module for context-aware image-to-image translation. Vis. Comput. 36, 2145\u20132159 (2020). https:\/\/doi.org\/10.1007\/s00371-020-01943-0","journal-title":"Vis. Comput."},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"36_CR3","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"36_CR4","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"36_CR5","unstructured":"Dong, X., et al.: PeCo: perceptual codebook for BERT pre-training of vision transformers. arXiv preprint arXiv:2111.12710 (2021)"},{"key":"36_CR6","doi-asserted-by":"publisher","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12868\u201312878 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01268","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"36_CR7","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1007\/s00371-020-01995-2","volume":"37","author":"L Huang","year":"2021","unstructured":"Huang, L., Wang, Y., Bai, T.: Recognizing art work image from natural type: a deep adaptive depiction fusion method. Vis. Comput. 37, 1221\u20131232 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01995-2","journal-title":"Vis. Comput."},{"key":"36_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11523\u201311532 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, Z., Mech, R., Yumer, E., Ramanan, D.: Photo-sketching: inferring contour drawings from images. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1403\u20131412. IEEE (2019)","DOI":"10.1109\/WACV.2019.00154"},{"key":"36_CR11","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1007\/s00371-023-02956-1","volume":"39","author":"S Li","year":"2023","unstructured":"Li, S., Wu, F., Fan, Y., Song, X., Dong, W.: PLDGAN: portrait line drawing generation with prior knowledge and conditioning target. Vis. Comput. 39, 3507\u20133518 (2023). https:\/\/doi.org\/10.1007\/s00371-023-02956-1","journal-title":"Vis. Comput."},{"key":"36_CR12","unstructured":"Li, Z., Zhou, H., Bai, S., Li, P., Zhou, C., Yang, H.: M6-fashion: high-fidelity multi-modal image generation and editing. arXiv preprint arXiv:2205.11705 (2022)"},{"key":"36_CR13","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"36_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"36_CR15","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper\/files\/paper\/2019\/file\/5f8e2fa1718d1bbcadf1cd9c7a54fb8c-Paper.pdf"},{"issue":"14","key":"36_CR16","first-page":"71","volume":"8","author":"MDM Reddy","year":"2021","unstructured":"Reddy, M.D.M., Basha, M.S.M., Hari, M.M.C., Penchalaiah, M.N.: DALL-E: creating images from text. UGC Care Group I J. 8(14), 71\u201375 (2021)","journal-title":"UGC Care Group I J."},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2287\u20132296 (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"36_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Xu, C.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16515\u201316525 (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"issue":"9\u201310","key":"36_CR20","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1007\/s00371-022-02538-7","volume":"38","author":"T Yoshikawa","year":"2022","unstructured":"Yoshikawa, T., Endo, Y., Kanamori, Y.: Diversifying detail and appearance in sketch-based face image synthesis. Vis. Comput. 38(9\u201310), 3121\u20133133 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02538-7","journal-title":"Vis. Comput."},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: CoCosNet v2: full-resolution correspondence learning for image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11465\u201311475 (2021)","DOI":"10.1109\/CVPR46437.2021.01130"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50072-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T23:26:22Z","timestamp":1730935582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50072-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"ISBN":["9783031500718","9783031500725"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50072-5_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"29 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2023","order":10,"name":"conference_id","label":"Conference ID","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"385","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":"149","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":"39% - 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","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","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)"}}]}}