{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:24:42Z","timestamp":1777494282044,"version":"3.51.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031189067","type":"print"},{"value":"9783031189074","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\/978-3-031-18907-4_38","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"488-498","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["CTFusion: Convolutions Integrate with\u00a0Transformers for\u00a0Multi-modal Image Fusion"],"prefix":"10.1007","author":[{"given":"Zhengwen","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiyu","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"38_CR1","unstructured":"Wang, Y.K., Huang, W.B., Sun, F.C., Xu, T.Y., Rong, Y., Huang, J.: Deep multimodal fusion by channel exchanging. In: Advances in Neural Information Processing Systems, 33 (2020)"},{"issue":"5","key":"38_CR2","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., Wu, X.J.: DenseFuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614\u20132623 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"38_CR3","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/s12596-013-0148-7","volume":"43","author":"V Naidu","year":"2014","unstructured":"Naidu, V.: Hybrid DDCT-PCA based multi sensor image fusion. J. Opt. 43(1), 48\u201361 (2014)","journal-title":"J. Opt."},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Ram Prabhakar, K., Sai Srikar, V., Babu, R.: DeepFuse: a deep unsupervised approach for exposure fusion with extreme exposure image pairs. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4714\u20134722 (2017)","DOI":"10.1109\/ICCV.2017.505"},{"key":"38_CR5","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu, H., Ma, J., Jiang, J., Guo, X., Ling, H.: U2fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44, 502\u2013518 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, H., Xiao, Y., Guo, X., Ma, J.: Rethinking the image fusion: a fast unified image fusion network based on proportional maintenance of gradient and intensity. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12797\u201312804 (2020)","DOI":"10.1609\/aaai.v34i07.6975"},{"key":"38_CR7","doi-asserted-by":"publisher","first-page":"4733","DOI":"10.1109\/TIP.2020.2975984","volume":"29","author":"H Li","year":"2020","unstructured":"Li, H., Wu, X.J., Kittler, J.: MDLatLRR: a novel decomposition method for infrared and visible image fusion. IEEE Trans. Image Process. 29, 4733\u20134746 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"38_CR8","doi-asserted-by":"publisher","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","volume":"29","author":"J Ma","year":"2020","unstructured":"Ma, J., Xu, H., Jiang, J., Mei, X., Zhang, X.P.: DDcGAN: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans. Image Process. 29, 4980\u20134995 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"38_CR9","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.inffus.2020.08.022","volume":"66","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Le, Z., Shao, Z., Xu, H., Ma, J.: MFF-GAN: an unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion. Inf. Fusion 66, 40\u201353 (2021)","journal-title":"Inf. Fusion"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G., Albanie, S.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 99 (2017)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Wang, X.L., Ross, G., Abhinav, G., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"38_CR12","unstructured":"Ashish, V., et al.: Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"38_CR13","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"38_CR14","unstructured":"Xie, E., et al.: SegFormer: simple and efficient design for semantic segmentation with transformers, in arXiv preprint arXiv:2105.15203 (2021)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7077\u20137087 (2021)","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"38_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Wu, H.P., et al.: CVT: Introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"38_CR18","unstructured":"Xiao, T., Dollar, P., Singh, M., Mintun, E., Darrell, T., Girshick, R.: Early convolutions help transformers see better. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)"},{"key":"38_CR19","unstructured":"Islam, Md.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? In: International Conference on Learning Representations (2020)"},{"key":"38_CR20","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 \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"23","key":"38_CR21","doi-asserted-by":"publisher","first-page":"6480","DOI":"10.1364\/AO.55.006480","volume":"55","author":"Z Zhou","year":"2016","unstructured":"Zhou, Z., Dong, M., Xie, X., Gao, Z.: Fusion of infrared and visible images for night-vision context enhancement. Appl. Opt. 55(23), 6480\u20136490 (2016)","journal-title":"Appl. Opt."},{"key":"38_CR22","unstructured":"Mohammad, H., Masoud Amirkabiri, R.: Fast-FMI: non-reference image fusion metric. In: 2014 IEEE 8th International Conference on Application of Information and Communication Technologies (AICT), pp. 1\u20133 (2014)"},{"issue":"12","key":"38_CR23","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1016\/j.aeue.2015.09.004","volume":"69","author":"V Aslantas","year":"2015","unstructured":"Aslantas, V., Bendes, E.: A new image quality metric for image fusion: the sum of the correlations of differences. AEU-Int. J. Electron. Commun. 69(12), 1890\u20131896 (2015)","journal-title":"AEU-Int. J. Electron. Commun."},{"issue":"4","key":"38_CR24","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(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"38_CR25","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1007\/s11760-012-0361-x","volume":"7","author":"BK Shreyamsha Kumar","year":"2012","unstructured":"Shreyamsha Kumar, B.K.: Multifocus and multispectral image fusion based on pixel significance using discrete cosine harmonic wavelet transform. SIViP 7(6), 1125\u20131143 (2012). https:\/\/doi.org\/10.1007\/s11760-012-0361-x","journal-title":"SIViP"},{"key":"38_CR26","unstructured":"Han, S.S., Li, H.T., Gu, H.Y., et al.: The study on image fusion for high spatial resolution remote sensing images. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XXXVII Part B 7, 1159\u20131164 (2008)"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Kumar, B.S.: Multifocus and multispectral image fusion based on pixel significance using discrete cosine harmonic wavelet transform. Signal Image Video Process. 7(6), 1125\u20131143 (2013)","DOI":"10.1007\/s11760-012-0361-x"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, Y., Sun, P., Yan, H., Zhao, X., Zhang, L.: IFCNN: a general image fusion framework based on convolutional neural network. Inf. Fusion 54, 99\u2013118 (2020)","DOI":"10.1016\/j.inffus.2019.07.011"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Li, W., Xie, Y., Zhou, H., Han, Y., Zhan, K.: Structure-aware image fusion. Optik 172, 1\u201311 (2018)","DOI":"10.1016\/j.ijleo.2018.06.123"},{"issue":"11","key":"38_CR30","doi-asserted-by":"publisher","first-page":"3345","DOI":"10.1109\/TIP.2015.2442920","volume":"24","author":"K Ma","year":"2015","unstructured":"Ma, K., Zeng, K., Wang, Z.: Perceptual quality assessment for multi-exposure image fusion. IEEE Trans. Image Process. 24(11), 3345\u20133356 (2015)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:11:30Z","timestamp":1666825890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_38","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":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}