{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T02:07:21Z","timestamp":1774058841971,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197963","type":"print"},{"value":"9783031197970","type":"electronic"}],"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\/978-3-031-19797-0_21","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:28:41Z","timestamp":1667420921000},"page":"360-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["L-CoDer: Language-Based Colorization with\u00a0Color-Object Decoupling Transformer"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Chang","sequence":"first","affiliation":[]},{"given":"Shuchen","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Si","family":"Li","sequence":"additional","affiliation":[]},{"given":"Boxin","family":"Shi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"21_CR1","unstructured":"Antic, J.: A deep learning based project for colorizing and restoring old images (and video!). https:\/\/github.com\/jantic\/DeOldify"},{"key":"21_CR2","unstructured":"Ardizzone, L., L\u00fcth, C., Kruse, J., Rother, C., K\u00f6the, U.: Guided image generation with conditional invertible neural networks. arXiv preprint arXiv:1907.02392 (2019)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Shen, Y., Gao, J., Liu, J., Liu, X.: Language-based image editing with recurrent attentive models. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00909"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.55"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Lu, J., Yeh, M.C., Jin Chong, M., Forsyth, D.: Learning diverse image colorization. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.307"},{"key":"21_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"21_CR8","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. In: NIPS (2021)"},{"key":"21_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"4","key":"21_CR10","first-page":"1","volume":"37","author":"M He","year":"2018","unstructured":"He, M., Chen, D., Liao, J., Sander, P.V., Yuan, L.: Deep exemplar-based colorization. ACM TOG 37(4), 1\u201316 (2018)","journal-title":"ACM TOG"},{"issue":"13","key":"21_CR11","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image\/video quality assessment. Electron. Lett. 44(13), 800\u2013801 (2008)","journal-title":"Electron. Lett."},{"issue":"4","key":"21_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925974","volume":"35","author":"S Iizuka","year":"2016","unstructured":"Iizuka, S., Simo-Serra, E., Ishikawa, H.: Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM ToG 35(4), 1\u201311 (2016)","journal-title":"ACM ToG"},{"key":"21_CR13","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: ICML (2021)"},{"key":"21_CR14","unstructured":"Kumar, M., Weissenborn, D., Kalchbrenner, N.: Colorization transformer. In: ICLR (2021)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R.: Swinir: image restoration using swin transformer. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Liu, R., ET AL.: FuseFormer: fusing fine-grained information in transformers for video inpainting. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Lu, P., Yu, J., Peng, X., Zhao, Z., Wang, X.: Gray2colornet: transfer more colors from reference image. In: ACM MM (2020)","DOI":"10.1145\/3394171.3413594"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Manjunatha, V., Iyyer, M., Boyd-Graber, J., Davis, L.: Learning to color from language. In: NAACL (2018)","DOI":"10.18653\/v1\/N18-2120"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Sangkloy, P., Lu, J., Fang, C., Yu, F., Hays, J.: Scribbler: controlling deep image synthesis with sketch and color. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.723"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Su, J.W., Chu, H.K., Huang, J.B.: Instance-aware image colorization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"21_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Vitoria, P., Raad, L., Ballester, C.: ChromaGAN: adversarial picture colorization with semantic class distribution. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093389"},{"issue":"4","key":"21_CR24","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Weng, S., Wu, H., Chang, Z.C., Tang, J., Li, S., Shi, B.: L-code: language-based colorization using color-object decoupled conditions. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20170"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wang, X., Li, Y., Zhang, H., Zhao, X., Shan, Y.: Towards vivid and diverse image colorization with generative color prior. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"21_CR27","unstructured":"Xie, Y.: Language-guided image colorization. Master\u2019s thesis, ETH Zurich, Departement of Computer Science (2018)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wang, T., Fang, F., Sheng, Y., Zhang, G.: Stylization-based architecture for fast deep exemplar colorization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00938"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., Lee, H., Yang, Y.: Cross-modal contrastive learning for text-to-image generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Real-time user-guided image colorization with learned deep priors. ACM TOG (2017)","DOI":"10.1145\/3072959.3073703"},{"key":"21_CR33","unstructured":"Zhao, J., Liu, L., Snoek, C.G., Han, J., Shao, L.: Pixel-level semantics guided image colorization. In: BMVC (2018)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: TRAR: routing the attention spans in transformer for visual question answering. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"21_CR36","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: ICLR (2020)"}],"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\/978-3-031-19797-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:43:01Z","timestamp":1667421781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19797-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197963","9783031197970"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19797-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 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)"}}]}}