{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:18:01Z","timestamp":1766067481977,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030954666"},{"type":"electronic","value":"9783030954673"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-95467-3_8","type":"book-chapter","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T10:07:13Z","timestamp":1643710033000},"page":"105-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ViT - Inception - GAN for\u00a0Image Colourisation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5519-3071","authenticated-orcid":false,"given":"Tejas","family":"Bana","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-7754","authenticated-orcid":false,"given":"Jatan","family":"Loya","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-4565","authenticated-orcid":false,"given":"Siddhant","family":"Kulkarni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"issue":"7553","key":"8_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"8_CR2","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"8_CR3","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., Tenenbaum, J.B.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. arXiv preprint arXiv:1610.07584 (2016)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Vitoria, P., Raad, L., Ballester, C.: ChromaGAN: adversarial picture colorization with semantic class distribution. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2445\u20132454 (2020)","DOI":"10.1109\/WACV45572.2020.9093389"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Manjunatha, V., Iyyer, M., Boyd-Graber, J., Davis, L.: Learning to color from language. arXiv preprint arXiv:1804.06026 (2018)","DOI":"10.18653\/v1\/N18-2120"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Bahng, H., et al.: Coloring with words: guiding image colorization through text-based palette generation. In: Proceedings of the European conference on computer vision (ECCV), pp. 431\u2013447 (2018)","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, J., Han, J., Shao, L., Snoek, C.G.: Pixelated semantic colorization. Int. J. Comput. Vis. 1\u201317 (2019)","DOI":"10.1007\/s11263-019-01271-4"},{"key":"8_CR9","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), pp. 0570\u20130575. IEEE, April 2018","DOI":"10.1109\/RADAR.2018.8378622"},{"issue":"4","key":"8_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 Trans. Graph. (TOG) 37(4), 1\u201316 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR11","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up Preprint (2021)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"8_CR13","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. CoRR, abs\/1511.06434 (2016)"},{"key":"8_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR15","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, pp. 248\u2013255. IEEE, June 2009","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR16","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: Advances in Neural Information Processing Systems. Curran Associates Inc (2016)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, April 2018","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"8_CR18","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","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin, Tsung-Yi., et al.: Microsoft coco: common objects in context. In: Fleet, David, Pajdla, Tomas, Schiele, Bernt, Tuytelaars, Tinne (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"8_CR19","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"issue":"3","key":"8_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"8_CR21","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liao, J., Yao, Y., Yuan, L., Hua, G., Kang, S.B.: Visual attribute transfer through deep image analogy. arXiv preprint arXiv:1705.01088 (2017)","DOI":"10.1145\/3072959.3073683"},{"key":"8_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"8_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"Olaf Ronneberger","year":"2015","unstructured":"Ronneberger, Olaf, Fischer, Philipp, Brox, Thomas: U-Net: convolutional networks for biomedical image segmentation. In: Navab, Nassir, Hornegger, Joachim, Wells, William M.., Frangi, Alejandro F.. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675\u2013678, November 2014","DOI":"10.1145\/2647868.2654889"},{"issue":"4","key":"8_CR26","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 Trans. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR27","unstructured":"Baldassarre, F., Mor\u00edn, D.G., Rod\u00e9s-Guirao, L.: Deep Koalarization: image colorization using CNNs and Inception-Resnet-v2. arXiv preprint arXiv:1712.03400 (2017)"},{"key":"8_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR, June 2015"},{"key":"8_CR29","unstructured":"Anwar, S., et al.: Image colorization: a survey and dataset. arXiv preprint arXiv:2008.10774 (2020)"},{"key":"8_CR30","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6629\u20136640. Curran Associates Inc (2017)"},{"key":"8_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision","author":"Richard Zhang","year":"2016","unstructured":"Zhang, Richard, Isola, Phillip, Efros, Alexei A..: Colorful image colorization. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"8_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-319-46493-0_35","volume-title":"Computer Vision","author":"Gustav Larsson","year":"2016","unstructured":"Larsson, Gustav, Maire, Michael, Shakhnarovich, Gregory: Learning representations for automatic colorization. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9908, pp. 577\u2013593. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_35"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Real-time user-guided image colorization with learned deep priors. ACM Trans. Graph. 36(4) (2017)","DOI":"10.1145\/3072959.3073703"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95467-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T08:28:35Z","timestamp":1680769715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95467-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030954666","9783030954673"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95467-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"2 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2021.icas.cc\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"215","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":"86","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":"40% - 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":"5-6","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":"1-2","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)"}}]}}