{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:57:48Z","timestamp":1785488268229,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774528","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Image Colorization with Instance-Aware Transformer network"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9646-1593","authenticated-orcid":false,"given":"Mrinmoy","family":"Sen","sequence":"first","affiliation":[{"name":"Samsung R&D Institute India - Bangalore, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3577-1399","authenticated-orcid":false,"given":"Akshay","family":"Bankar","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute India - Bangalore, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4736-1380","authenticated-orcid":false,"given":"Ravikiran Kundapur","family":"Subraya","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute India - Bangalore, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2388-2513","authenticated-orcid":false,"given":"Roopa","family":"Sheshadri","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute India - Bangalore, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0564-633X","authenticated-orcid":false,"given":"Kyuwon","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n.d.]. DeOldify. ([n. d.]). https:\/\/github.com\/jantic\/DeOldify https:\/\/github.com\/jantic\/DeOldify."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Radhakrishna Achanta Appu Shaji Kevin Smith Aurelien Lucchi Pascal Fua and Sabine S\u00fcsstrunk. 2012. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 34 11 (2012) 2274\u20132282. 10.1109\/TPAMI.2012.120","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00785"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_21"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3375"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"e_1_3_3_2_9_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"Cun Xiaodong","year":"2019","unstructured":"Xiaodong Cun, Chi-Man Pun, and Cheng Shi. 2019. Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:208175610"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Yuki Endo Satoshi Iizuka Yoshihiro Kanamori and Jun Mitani. 2016. DeepProp: Extracting deep features from a single image for edit propagation. Computer Graphics Forum 35 2 (1 May 2016) 189\u2013201. 10.1111\/cgf.12822","DOI":"10.1111\/cgf.12822"},{"key":"e_1_3_3_2_11_2","volume-title":"European Conference on Computer Vision (ECCV)","author":"Geonung Kim","year":"2022","unstructured":"Kim Geonung, Kang Kyoungkook, Kim Seongtae, Lee Hwayoon, Kim Sehoon, Kim Jonghyun, Baek Seung-Hwan, and Cho Sunghyun. 2022. BigColor: Colorization using a Generative Color Prior for Natural Images. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63 11 (oct 2020) 139\u2013144. 10.1145\/3422622","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"David Hasler and Sabine S\u00fcsstrunk. 2003. Measuring colourfulness in natural images. https:\/\/api.semanticscholar.org\/CorpusID:9176374","DOI":"10.1117\/12.477378"},{"key":"e_1_3_3_2_14_2","unstructured":"Kaiming He and Jian Sun. 2015. Fast Guided Filter. ArXiv abs\/1505.00996 (2015). https:\/\/api.semanticscholar.org\/CorpusID:27930513"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Mingming He Dongdong Chen Jing Liao Pedro\u00a0V. Sander and Lu Yuan. 2018. Deep exemplar-based colorization. ACM Trans. Graph. 37 4 Article 47 (jul 2018) 16\u00a0pages. 10.1145\/3197517.3201365","DOI":"10.1145\/3197517.3201365"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Zhitong Huang Nanxuan Zhao and Jing Liao. 2022. UniColor: A Unified Framework for Multi-Modal Colorization with Transformer. ACM Transactions on Graphics (TOG) 41 6 Article 205 (nov 2022) 16\u00a0pages. 10.1145\/3550454.3555471","DOI":"10.1145\/3550454.3555471"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00037"},{"key":"e_1_3_3_2_22_2","volume-title":"International Conference on Learning Representations","author":"Kumar Manoj","year":"2021","unstructured":"Manoj Kumar, Dirk Weissenborn, and Nal Kalchbrenner. 2021. Colorization Transformer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=5NA1PinlGFu"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov Tom Duerig and Vittorio Ferrari. 2020. The Open Images Dataset V4: Unified image classification object detection and visual relationship detection at scale. IJCV (2020).","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Anat Levin Dani Lischinski and Yair Weiss. 2004. Colorization using optimization. ACM Trans. Graph. 23 3 (aug 2004) 689\u2013694. 10.1145\/1015706.1015780","DOI":"10.1145\/1015706.1015780"},{"key":"e_1_3_3_2_25_2","volume-title":"International Conference on Machine Learning","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C.\u00a0H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:256390509"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/2383847.2383887"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2120"},{"key":"e_1_3_3_2_28_2","unstructured":"Chong Mou Xintao Wang Liangbin Xie Jing Zhang Zhongang Qi Ying Shan and Xiaohu Qie. 2023. T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models. ArXiv abs\/2302.08453 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256900833"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"e_1_3_3_2_30_2","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093389"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Hanzhang Wang Deming Zhai Xianming Liu Junjun Jiang and Wen Gao. 2023. Unsupervised Deep Exemplar Colorization via Pyramid Dual Non-local Attention. IEEE Transactions on Image Processing (TIP) (2023).","DOI":"10.1109\/TIP.2023.3293777"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang Wenyu Liu and Bin Xiao. 2021. Deep High-Resolution Representation Learning for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 43 10 (2021) 3349\u20133364. 10.1109\/TPAMI.2020.2983686","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_16"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_1"},{"key":"e_1_3_3_2_40_2","volume-title":"AAAI","author":"Weng Shuchen","year":"2022","unstructured":"Shuchen Weng, Hao Wu, Zheng Chang, Jiajun Tang, Si Li, and Boxin Shi. 2022. L-CoDe: Language-based Colorization Using Color-object Decoupled Conditions. In AAAI."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Menghan Xia Wenbo Hu Tien-Tsin Wong and Jue Wang. 2022. Disentangled Image Colorization via Global Anchors. ACM Transactions on Graphics (TOG) 41 6 (2022) 204:1\u2013204:13.","DOI":"10.1145\/3550454.3555432"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683686"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01154"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00183"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618180"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00824"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Jiaojiao Zhao Jungong Han Ling Shao and Cees G.\u00a0M. Snoek. 2020. Pixelated Semantic Colorization. Int. J. Comput. Vision 128 4 (apr 2020) 818\u2013834. 10.1007\/s11263-019-01271-4","DOI":"10.1007\/s11263-019-01271-4"}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:02:09Z","timestamp":1785484929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":48,"alternative-id":["10.1145\/3774521.3774528","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774528","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}