{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:38:28Z","timestamp":1761845908606,"version":"3.35.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T00:00:00Z","timestamp":1733702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T00:00:00Z","timestamp":1733702400000},"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":["SIViP"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11760-024-03650-y","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T14:38:34Z","timestamp":1733755114000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MMC: Multi-modal colorization of images using textual description"],"prefix":"10.1007","volume":"19","author":[{"given":"Subhankar","family":"Ghosh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saumik","family":"Bhattacharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasun","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Blumenstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"3650_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J.R.R., Ferrari, V.: Coco-stuff: Thing and stuff classes in context. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"3650_CR2","unstructured":"Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-ucsd birds 200. In: Technical Report CNS-TR-2010-001, California Institute of Technology (2010)"},{"key":"3650_CR3","doi-asserted-by":"crossref","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, 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3650_CR4","unstructured":"Kumar, M., Weissenborn, D., Kalchbrenner, N.: Colorization transformer. arXiv:2102.04432 (2021)"},{"key":"3650_CR5","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: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 14357\u201314366 (2021)","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"3650_CR6","doi-asserted-by":"crossref","unstructured":"Su, J.-W., Chu, H.-k., Huang, J.-B.: Instance-aware image colorization. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7965\u20137974 (2020)","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"3650_CR7","doi-asserted-by":"publisher","first-page":"1810","DOI":"10.1109\/TIP.2017.2665975","volume":"26","author":"AS Parihar","year":"2017","unstructured":"Parihar, A.S., Verma, O.P., Khanna, C.: Fuzzy-contextual contrast enhancement. IEEE Trans. Image Process. 26, 1810\u20131819 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"3650_CR8","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/TFUZZ.2016.2551289","volume":"25","author":"OP Verma","year":"2017","unstructured":"Verma, O.P., Parihar, A.S.: An optimal fuzzy system for edge detection in color images using bacterial foraging algorithm. IEEE Trans. Fuzzy Syst. 25, 114\u2013127 (2017)","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"3650_CR9","doi-asserted-by":"publisher","first-page":"2952","DOI":"10.1002\/int.22726","volume":"37","author":"DNBH Wu","year":"2022","unstructured":"Wu, D.N.B.H., Gan, J., Zhou, J., Wang, J., Gao, W.: Fine-grained semantic ethnic costume high-resolution image colorization with conditional gan. Int. J. Intell. Syst. 37, 2952\u20132968 (2022)","journal-title":"Int. J. Intell. Syst."},{"key":"3650_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105006","volume":"114","author":"S Huang","year":"2022","unstructured":"Huang, S., Jin, X., Jiang, Q., Liu, L.: Deep learning for image colorization: current and future prospects. Eng. Appl. Artif. Intell. 114, 105006 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"3650_CR11","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1002\/int.22667","volume":"37","author":"Y Xiao","year":"2022","unstructured":"Xiao, Y., Jiang, A., Liu, C., Wang, M.: Semantic-aware automatic image colorization via unpaired cycle-consistent self-supervised network. Int. J. Intell. Syst. 37, 1222\u20131238 (2022)","journal-title":"Int. J. Intell. Syst."},{"key":"3650_CR12","doi-asserted-by":"publisher","first-page":"15808","DOI":"10.1109\/TITS.2022.3145476","volume":"23","author":"F Luo","year":"2022","unstructured":"Luo, F., Li, Y., Zeng, G., Peng, P., Wang, G., Li, Y.: Thermal infrared image colorization for nighttime driving scenes with top-down guided attention. IEEE Trans. Intell. Transp. Syst. 23, 15808\u201315823 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3650_CR13","doi-asserted-by":"crossref","unstructured":"Treneska, S., Zdravevski, E., Pires, I., Lameski, P., Gievska, S.: Gan-based image colorization for self-supervised visual feature learning. Sensors (Basel, Switzerland) 22 (2022)","DOI":"10.3390\/s22041599"},{"key":"3650_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing (TIP) (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"3650_CR15","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","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. IEEE Trans. Image Process. 13, 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"3650_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y.-C., Tung, Y.-S., Chen, J.-C., Wang, S.-W., Wu, J.-L.: An adaptive edge detection based colorization algorithm and its applications. In: MULTIMEDIA \u201905 (2005)","DOI":"10.1145\/1101149.1101223"},{"key":"3650_CR17","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1016\/j.patrec.2007.02.018","volume":"28","author":"D Nie","year":"2007","unstructured":"Nie, D., Ma, Q., Ma, L., Xiao, S.: Optimization based grayscale image colorization. Pattern Recognit. Lett. 28, 1445\u20131451 (2007)","journal-title":"Pattern Recognit. Lett."},{"key":"3650_CR18","doi-asserted-by":"crossref","unstructured":"Wang, P., Patel, V.M.: Generating high quality visible images from SAR images using CNNS. In: 2018 IEEE Radar Conference (RadarConf18), 0570\u20130575 (2018)","DOI":"10.1109\/RADAR.2018.8378622"},{"key":"3650_CR19","doi-asserted-by":"crossref","unstructured":"Tola, E., Lepetit, V., Fua, P.V.: A fast local descriptor for dense matching. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587673"},{"key":"3650_CR20","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Gool, L.V., Gross, M.H., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"3650_CR21","unstructured":"Lu, Y., Yang, X., Li, X., Wang, X.E., Wang, W.Y.: Llmscore: Unveiling the power of large language models in text-to-image synthesis evaluation. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol. 36, pp. 23075\u201323093. Curran Associates, Inc., (2023)"},{"key":"3650_CR22","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":"3650_CR23","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.-Z.: You\u2019ll never walk alone: A sketch and text duet for fine-grained image retrieval. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16509\u201316519 (2024)","DOI":"10.1109\/CVPR52733.2024.01562"},{"key":"3650_CR24","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: 2015 IEEE International Conference on Computer Vision (ICCV), 415\u2013423 (2015)","DOI":"10.1109\/ICCV.2015.55"},{"key":"3650_CR25","doi-asserted-by":"crossref","unstructured":"Carlucci, F.M., Russo, P., Caputo, B.: $$(de)^2co$$: Deep depth colorization. IEEE Robotics and Automation Letters (2018)","DOI":"10.1109\/LRA.2018.2812225"},{"key":"3650_CR26","doi-asserted-by":"crossref","unstructured":"Bahng, H., Yoo, S., Cho, W., Park, D.K., Wu, Z., Ma, X., Choo, J.: Coloring with words: Guiding image colorization through text-based palette generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"3650_CR27","first-page":"1","volume":"36","author":"R Zhang","year":"2017","unstructured":"Zhang, R., Zhu, J.-Y., Isola, P., Geng, X., Lin, A.S., Yu, T., Efros, A.A.: Real-time user-guided image colorization with learned deep priors. ACM Transactions on Graphics (TOG) 36, 1\u201311 (2017)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"3650_CR28","doi-asserted-by":"crossref","unstructured":"Weng, S., Wu, H., Chang, Z., 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":"3650_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask r-cnn. In: 2017 IEEE International Conference on Computer Vision (ICCV), 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3650_CR30","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2019)"},{"key":"3650_CR31","unstructured":"Ren, M., Kiros, R., Zemel, R.S.: Exploring models and data for image question answering. In: NIPS (2015)"},{"key":"3650_CR32","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! ACM Transactions on Graphics (TOG) 35, 1\u201311 (2016)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"3650_CR33","unstructured":"Antic., J.: A deep learning based project for colorizing and restoring old images (and video!). https:\/\/github.com\/jantic\/deoldify,. (2019)"},{"key":"3650_CR34","doi-asserted-by":"crossref","unstructured":"Lei, C., Chen, Q.: Fully automatic video colorization with self-regularization and diversity. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3748\u20133756 (2019)","DOI":"10.1109\/CVPR.2019.00387"},{"key":"3650_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: The International Conference on Learning Representations (ICLR) (2015)"},{"key":"3650_CR36","doi-asserted-by":"crossref","unstructured":"Manjunatha, V., Iyyer, M., Boyd-Graber, J.L., Davis, L.S.: Learning to color from language. In: NAACL (2018)","DOI":"10.18653\/v1\/N18-2120"},{"key":"3650_CR37","doi-asserted-by":"crossref","unstructured":"Chang, Z., Weng, S., Li, Y., Li, S., Shi, B.: L-coder: Language-based colorization with color-object decoupling transformer. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19797-0_21"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03650-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03650-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03650-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T14:56:11Z","timestamp":1738335371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03650-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,9]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3650"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03650-y","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2024,12,9]]},"assertion":[{"value":"24 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Yes","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Materials will be made available at a reasonable request.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}}],"article-number":"107"}}