{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:26:33Z","timestamp":1783362393380,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819720910","type":"print"},{"value":"9789819720927","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-2092-7_13","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:02:18Z","timestamp":1711692138000},"page":"259-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FreeStyler: A Free-Form Stylization Method via\u00a0Multimodal Vector Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1787-1593","authenticated-orcid":false,"given":"WuQin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5130-5754","authenticated-orcid":false,"given":"MinXuan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-6428","authenticated-orcid":false,"given":"HaiBin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8243-9513","authenticated-orcid":false,"given":"ChongYang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"WeiMing","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"An, J., Huang, S., Song, Y., Dou, D., Liu, W., Luo, J.: Artflow: unbiased image style transfer via reversible neural flows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 862\u2013871 (2021)","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"13_CR2","first-page":"26561","volume":"34","author":"H Chen","year":"2021","unstructured":"Chen, H., et al.: Artistic style transfer with internal-external learning and contrastive learning. Adv. Neural. Inf. Process. Syst. 34, 26561\u201326573 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR3","doi-asserted-by":"publisher","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: European Conference on Computer Vision (ECCV), pp. 88\u2013105 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Huang, H., Ma, C., Xu, C.: Arbitrary video style transfer via multi-channel correlation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1210\u20131217 (2021)","DOI":"10.1609\/aaai.v35i2.16208"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Ma, C., Pan, X., Wang, L., Xu, C.: StyTr$$^2$$: image style transfer with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11326\u201311336 (2022)","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"13_CR6","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR7","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: Cogview: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR8","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: Cogview2: Faster and better text-to-image generation via hierarchical transformers. arXiv preprint arXiv:2204.14217 (2022)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"13_CR10","doi-asserted-by":"publisher","unstructured":"Fu, T.J., Wang, X.E., Wang, W.Y.: Language-driven artistic style transfer. In: European Conference on Computer Vision, pp. 717\u2013734. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_41","DOI":"10.1007\/978-3-031-20059-5_41"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Huang, S., An, J., Wei, D., Luo, J., Pfister, H.: Quantart: quantizing image style transfer towards high visual fidelity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5947\u20135956 (2023)","DOI":"10.1109\/CVPR52729.2023.00576"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"13_CR15","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":"13_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Kwon, G., Ye, J.C.: CLIPstyler: Image style transfer with a single text condition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18062\u201318071 (2022)","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"13_CR18","unstructured":"Kwon, G., Ye, J.C.: Diffusion-based image translation using disentangled style and content representation. arXiv preprint arXiv:2209.15264 (2022)"},{"key":"13_CR19","unstructured":"Lee, S.H., Kim, C., Byeon, W., Yoon, S.H., Kim, J., Kim, S.: Lisa: localized image stylization with audio via implicit neural representation. arXiv preprint arXiv:2211.11381 (2022)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Lee, S.H., et al.: Sound-guided semantic image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3377\u20133386 (2022)","DOI":"10.1109\/CVPR52688.2022.00337"},{"key":"13_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1007\/978-3-319-46487-9_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Li","year":"2016","unstructured":"Li, C., Wand, M.: Precomputed real-time texture synthesis with markovian generative adversarial networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 702\u2013716. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_43"},{"key":"13_CR22","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Universal style transfer via feature transforms. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"13_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1007\/978-3-030-01219-9_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Liu, M.-Y., Li, X., Yang, M.-H., Kautz, J.: A closed-form solution to photorealistic image stylization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 468\u2013483. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_28"},{"key":"13_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58548-8_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Lin","year":"2020","unstructured":"Lin, J., Pang, Y., Xia, Y., Chen, Z., Luo, J.: TuiGAN: learning versatile image-to-image translation with two unpaired images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 18\u201335. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_2"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Lin, M., Tang, F., Dong, W., Li, X., Xu, C., Ma, C.: Distribution aligned multimodal and multi-domain image stylization. ACM Trans, Multimedia Comput. Commun. Appli. (TOMM) 17(3), 1\u201317 (2021)","DOI":"10.1145\/3450525"},{"key":"13_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Tsung-Yi","year":"2014","unstructured":"Tsung-Yi, L., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"13_CR27","unstructured":"Liu, A.H., Liu, Y.C., Yeh, Y.Y., Wang, Y.C.F.: A unified feature disentangler for multi-domain image translation and manipulation. Adv. Neural Inform. Process. Sys. 31 (2018)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Adaattn: revisit attention mechanism in arbitrary neural style transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6649\u20136658 (2021)","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Park, D.Y., Lee, K.H.: Arbitrary style transfer with style-attentional networks. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5880\u20135888 (2019)","DOI":"10.1109\/CVPR.2019.00603"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Phillips, F., Mackintosh, B.: Wiki art gallery, inc.: a case for critical thinking. Issues in Accounting Educ. 26(3), 593\u2013608 (2011)","DOI":"10.2308\/iace-50038"},{"key":"13_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR32","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"13_CR33","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"13_CR34","unstructured":"Razavi, A., Van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"13_CR35","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":"13_CR36","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6924\u20136932 (2017)","DOI":"10.1109\/CVPR.2017.437"},{"key":"13_CR38","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"13_CR39","unstructured":"Wang, Z., Liu, W., He, Q., Wu, X., Yi, Z.: Clip-gen: language-free training of a text-to-image generator with clip. arXiv preprint arXiv:2203.00386 (2022)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Wu, H.H., Seetharaman, P., Kumar, K., Bello, J.P.: Wav2clip: learning robust audio representations from clip. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4563\u20134567. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Wu, X., Hu, Z., Sheng, L., Xu, D.: Styleformer: real-time arbitrary style transfer via parametric style composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14618\u201314627 (2021)","DOI":"10.1109\/ICCV48922.2021.01435"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Yoo, J., Uh, Y., Chun, S., Kang, B., Ha, J.W.: Photorealistic style transfer via wavelet transforms. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9036\u20139045 (2019)","DOI":"10.1109\/ICCV.2019.00913"},{"key":"13_CR43","unstructured":"Zhang, C., Yang, J., Wang, L., Dai, Z.: S2wat: image style transfer via hierarchical vision transformer using strips window attention. arXiv preprint arXiv:2210.12381 (2022)"},{"key":"13_CR44","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354\u20137363. PMLR (2019)"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Domain enhanced arbitrary image style transfer via contrastive learning. arXiv preprint arXiv:2205.09542 (2022)","DOI":"10.1145\/3528233.3530736"},{"key":"13_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"C1","DOI":"10.1007\/978-3-030-58545-7_47","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Wu, R., Dong, H.: Correction to: unpaired image-to-image translation using adversarial consistency loss. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. C1\u2013C1. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_47"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2092-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:06:18Z","timestamp":1711692378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2092-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819720910","9789819720927"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2092-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2024","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":"CVM submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","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":"34","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":"16% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}