{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T02:49:01Z","timestamp":1768618141625,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":59,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609161","type":"print"},{"value":"9789819609178","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0917-8_11","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:54:21Z","timestamp":1733558061000},"page":"187-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Content-Adaptive Style Transfer: A Training-Free Approach with\u00a0VQ Autoencoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9082-7427","authenticated-orcid":false,"given":"Jongmin","family":"Gim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1072-1239","authenticated-orcid":false,"given":"Jihun","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2581-3610","authenticated-orcid":false,"given":"Kyoungmin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9776-8101","authenticated-orcid":false,"given":"Sunghoon","family":"Im","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Cao, S., Yin, Y., Huang, L., Liu, Y., Zhao, X., Zhao, D., Huang, K.: Efficient-vqgan: Towards high-resolution image generation with efficient vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7368\u20137377 (2023)","DOI":"10.1109\/ICCV51070.2023.00677"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chandran, P., Zoss, G., Gotardo, P., Gross, M., Bradley, D.: Adaptive convolutions for structure-aware style transfer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7972\u20137981 (2021)","DOI":"10.1109\/CVPR46437.2021.00788"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Chang, H.Y., Wang, Z., Chuang, Y.Y.: Domain-specific mappings for generative adversarial style transfer (2020)","DOI":"10.1007\/978-3-030-58598-3_34"},{"key":"11_CR5","unstructured":"Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.H., Murphy, K., Freeman, W.T., Rubinstein, M., et\u00a0al.: Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"11_CR6","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":"11_CR7","first-page":"26561","volume":"34","author":"H Chen","year":"2021","unstructured":"Chen, H., Wang, Z., Zhang, H., Zuo, Z., Li, A., Xing, W., Lu, D., 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":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.J., Cheng, S.I., Chiu, W.C., Tseng, H.Y., Lee, H.Y.: Vector quantized image-to-image translation. In: European Conference on Computer Vision. pp. 440\u2013456. Springer (2022)","DOI":"10.1007\/978-3-031-19787-1_25"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Chung, J., Hyun, S., Heo, J.P.: Style injection in diffusion: A training-free approach for adapting large-scale diffusion models for style transfer (2024)","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Couairon, G., Grechka, A., Verbeek, J., Schwenk, H., Cord, M.: Flexit: Towards flexible semantic image translation (2022)","DOI":"10.1109\/CVPR52688.2022.01773"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Crowson, K., Biderman, S., Kornis, D., Stander, D., Hallahan, E., Castricato, L., Raff, E.: Vqgan-clip: Open domain image generation and editing with natural language guidance (2022)","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR13","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Sun, W., Huang, F., Xu, C.: Arbitrary style transfer via multi-adaptation network (2020)","DOI":"10.1145\/3394171.3414015"},{"key":"11_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"11_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale (2021)"},{"key":"11_CR17","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. arXiv preprint arXiv:1610.07629 (2016)"},{"key":"11_CR18","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":"11_CR19","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 (CVPR) (June 2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"11_CR20","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks (2014)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, C., Liao, J., Yuan, L.: Arbitrary style transfer with deep feature reshuffle. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8222\u20138231 (2018)","DOI":"10.1109\/CVPR.2018.00858"},{"key":"11_CR22","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Hong, K., Jeon, S., Lee, J., Ahn, N., Kim, K., Lee, P., Kim, D., Uh, Y., Byun, H.: Aespa-net: Aesthetic pattern-aware style transfer networks (2023)","DOI":"10.1109\/ICCV51070.2023.02080"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Huang, S., An, J., Wei, D., Luo, J., Pfister, H.: Quantart: Quantizing image style transfer towards high visual fidelity (2023)","DOI":"10.1109\/CVPR52729.2023.00576"},{"key":"11_CR25","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 (ICCV) (Oct 2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Jeong, J., Kwon, M., Uh, Y.: Training-free content injection using h-space in diffusion models (2024)","DOI":"10.1109\/WACV57701.2024.00507"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"11_CR28","unstructured":"Kondratyuk, D., Yu, L., Gu, X., Lezama, J., Huang, J., Hornung, R., Adam, H., Akbari, H., Alon, Y., Birodkar, V., Cheng, Y., Chiu, M.C., Dillon, J., Essa, I., Gupta, A., Hahn, M., Hauth, A., Hendon, D., Martinez, A., Minnen, D., Ross, D., Schindler, G., Sirotenko, M., Sohn, K., Somandepalli, K., Wang, H., Yan, J., Yang, M.H., Yang, X., Seybold, B., Jiang, L.: Videopoet: A large language model for zero-shot video generation (2023)"},{"key":"11_CR29","unstructured":"Kwon, G., Ye, J.C.: Diffusion-based image translation using disentangled style and content representation (2023)"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Diversified texture synthesis with feed-forward networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3920\u20133928 (2017)","DOI":"10.1109\/CVPR.2017.36"},{"key":"11_CR31","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Universal style transfer via feature transforms (2017)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M.Y., Li, X., Yang, M.H., Kautz, J.: A closed-form solution to photorealistic image stylization (2018)","DOI":"10.1007\/978-3-030-01219-9_28"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, P.: Microsoft coco: Common objects in context (2015)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S., Lin, T., He, D., Li, F., Wang, M., Li, X., Sun, Z., Li, Q., Ding, E.: Adaattn: Revisit attention mechanism in arbitrary neural style transfer (2021)","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"11_CR35","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Park, D.Y., Lee, K.H.: Arbitrary style transfer with style-attentional networks (2019)","DOI":"10.1109\/CVPR.2019.00603"},{"key":"11_CR37","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer (2023)"},{"key":"11_CR38","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., Sutskever, I.: Zero-shot text-to-image generation (2021)"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR40","unstructured":"Sohn, K., Ruiz, N., Lee, K., Chin, D.C., Blok, I., Chang, H., Barber, J., Jiang, L., Entis, G., Li, Y., Hao, Y., Essa, I., Rubinstein, M., Krishnan, D.: Styledrop: Text-to-image generation in any style (2023)"},{"key":"11_CR41","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Tan, W.R., Chan, C.S., Aguirre, H., Tanaka, K.: Improved artgan for conditional synthesis of natural image and artwork (2018)","DOI":"10.1109\/TIP.2018.2866698"},{"key":"11_CR43","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: Scalable image generation via next-scale prediction (2024)"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation (2022)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"11_CR45","unstructured":"Ulyanov, D., Lebedev, V., Vedaldi, A., Lempitsky, V.: Texture networks: Feed-forward synthesis of textures and stylized images. arXiv preprint arXiv:1603.03417 (2016)"},{"key":"11_CR46","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)"},{"key":"11_CR47","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Advances in neural information processing systems 30 (2017)"},{"key":"11_CR48","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need (2023)"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Wright, M., Ommer, B.: Artfid: Quantitative evaluation of neural style transfer (2022)","DOI":"10.1007\/978-3-031-16788-1_34"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Xu, W., Long, C., Wang, R., Wang, G.: Drb-gan: A dynamic resblock generative adversarial network for artistic style transfer (2021)","DOI":"10.1109\/ICCV48922.2021.00632"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Xu, Z., Sangineto, E., Sebe, N.: Stylerdalle: Language-guided style transfer using a vector-quantized tokenizer of a large-scale generative model (2023)","DOI":"10.1109\/ICCV51070.2023.00699"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Yang, S., Hwang, H., Ye, J.C.: Zero-shot contrastive loss for text-guided diffusion image style transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 22873\u201322882 (2023)","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Yao, Y., Ren, J., Xie, X., Liu, W., Liu, Y.J., Wang, J.: Attention-aware multi-stroke style transfer (2019)","DOI":"10.1109\/CVPR.2019.00156"},{"key":"11_CR54","unstructured":"Yu, L., Cheng, Y., Wang, Z., Kumar, V., Macherey, W., Huang, Y., Ross, D.A., Essa, I., Bisk, Y., Yang, M.H., Murphy, K., Hauptmann, A.G., Jiang, L.: Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms (2023)"},{"key":"11_CR55","unstructured":"Yu, L., Lezama, J., Gundavarapu, N.B., Versari, L., Sohn, K., Minnen, D., Cheng, Y., Gupta, A., Gu, X., Hauptmann, A.G., Gong, B., Yang, M.H., Essa, I., Ross, D.A., Jiang, L.: Language model beats diffusion \u2013 tokenizer is key to visual generation (2023)"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, M., Li, R., Jia, K., Zhang, L.: Exact feature distribution matching for arbitrary style transfer and domain generalization (2022)","DOI":"10.1109\/CVPR52688.2022.00787"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, N., Tang, F., Huang, H., Ma, C., Dong, W., Xu, C.: Inversion-based style transfer with diffusion models (2023)","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tang, F., Dong, W., Huang, H., Ma, C., Lee, T.Y., Xu, C.: Domain enhanced arbitrary image style transfer via contrastive learning. In: ACM SIGGRAPH 2022 Conference Proceedings. pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3528233.3530736"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wei, F., Lu, Y.: Beyond text: Frozen large language models in visual signal comprehension (2024)","DOI":"10.1109\/CVPR52733.2024.02554"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0917-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:25:58Z","timestamp":1733559958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0917-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609161","9789819609178"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0917-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}