{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:32:56Z","timestamp":1783398776018,"version":"3.54.6"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72649-1_24","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"420-437","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["InfMAE: A Foundation Model in\u00a0the Infrared Modality"],"prefix":"10.1007","author":[{"given":"Fangcen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenqiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"24_CR1","unstructured":"Awais, M., et al.: Foundational models defining a new era in vision: a survey and outlook (2023)"},{"key":"24_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. In: International Conference on Learning Representations (2021)"},{"key":"24_CR3","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"24_CR5","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":"24_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"5","key":"24_CR7","doi-asserted-by":"publisher","first-page":"3979","DOI":"10.1109\/TAES.2022.3159308","volume":"58","author":"F Chen","year":"2022","unstructured":"Chen, F., et al.: Local patch network with global attention for infrared small target detection. IEEE Trans. Aerosp. Electron. Syst. 58(5), 3979\u20133991 (2022)","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"24_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"24_CR9","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TMM.2021.3050069","volume":"24","author":"X Chen","year":"2021","unstructured":"Chen, X., Gao, C., Li, C., Yang, Y., Meng, D.: Infrared action detection in the dark via cross-stream attention mechanism. IEEE Trans. Multimedia 24, 288\u2013300 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"24_CR10","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 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., et al.: PECO: perceptual codebook for Bert pre-training of vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 552\u2013560 (2023)","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"24_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"24_CR13","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2016.05.094","volume":"212","author":"C Gao","year":"2016","unstructured":"Gao, C., et al.: Infar dataset: infrared action recognition at different times. Neurocomputing 212, 36\u201347 (2016)","journal-title":"Neurocomputing"},{"issue":"12","key":"24_CR14","doi-asserted-by":"publisher","first-page":"4996","DOI":"10.1109\/TIP.2013.2281420","volume":"22","author":"C Gao","year":"2013","unstructured":"Gao, C., Meng, D., Yang, Y., Wang, Y., Zhou, X., Hauptmann, A.G.: Infrared patch-image model for small target detection in a single image. IEEE Trans. Image Process. 22(12), 4996\u20135009 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR15","first-page":"35632","volume":"35","author":"P Gao","year":"2022","unstructured":"Gao, P., Ma, T., Li, H., Lin, Z., Dai, J., Qiao, Y.: MCMAE: masked convolution meets masked autoencoders. Adv. Neural. Inf. Process. Syst. 35, 35632\u201335644 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Imagebind one embedding space to bind them all. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp. 15180\u201315190. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"18","key":"24_CR20","doi-asserted-by":"publisher","first-page":"D155","DOI":"10.1364\/AO.57.00D155","volume":"57","author":"Z He","year":"2018","unstructured":"He, Z., Cao, Y., Dong, Y., Yang, J., Cao, Y., Tisse, C.L.: Single-image-based nonuniformity correction of uncooled long-wave infrared detectors: a deep-learning approach. Appl. Opt. 57(18), D155\u2013D164 (2018)","journal-title":"Appl. Opt."},{"key":"24_CR21","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-031-20056-4_18","volume-title":"ECCV 2022","author":"I Kakogeorgiou","year":"2022","unstructured":"Kakogeorgiou, I., et al.: What to hide from your students: attention-guided masked image modeling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 300\u2013318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_18"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. CoRR abs\/2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"24_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big Transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"24_CR24","unstructured":"Lab, A.S.: Thermal infrared dataset. https:\/\/projects.asl.ethz.ch\/datasets\/doku.php?id=ir:iricra2014"},{"key":"24_CR25","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1109\/TIP.2022.3199107","volume":"32","author":"B Li","year":"2022","unstructured":"Li, B., et al.: Dense nested attention network for infrared small target detection. IEEE Trans. Image Process. 32, 1745\u20131758 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR26","first-page":"14290","volume":"35","author":"G Li","year":"2022","unstructured":"Li, G., Zheng, H., Liu, D., Wang, C., Su, B., Zheng, C.: SEMMAE: semantic-guided masking for learning masked autoencoders. Adv. Neural. Inf. Process. Syst. 35, 14290\u201314302 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR27","unstructured":"Li, X., Wang, W., Yang, L., Yang, J.: Uniform masking: enabling MAE pre-training for pyramid-based vision transformers with locality. arXiv preprint arXiv:2205.10063 (2022)"},{"key":"24_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2023.104678","volume":"131","author":"Y Li","year":"2023","unstructured":"Li, Y., Liu, H., Tian, Z., Geng, W.: Near-infrared vascular image segmentation using improved level set method. Infrared Phys. Technol. 131, 104678 (2023)","journal-title":"Infrared Phys. Technol."},{"key":"24_CR29","unstructured":"Li, Y., Xie, S., Chen, X., Dollar, P., He, K., Girshick, R.: Benchmarking detection transfer learning with vision transformers. arXiv preprint arXiv:2111.11429 (2021)"},{"key":"24_CR30","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., et al.: MST: masked self-supervised transformer for visual representation. Adv. Neural. Inf. Process. Syst. 34, 13165\u201313176 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"12","key":"24_CR31","doi-asserted-by":"publisher","first-page":"15619","DOI":"10.1109\/TPAMI.2023.3309979","volume":"45","author":"ZY Li","year":"2023","unstructured":"Li, Z.Y., Gao, S., Cheng, M.M.: Sere: exploring feature self-relation for self-supervised transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15619\u201315631 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Lin, F., Ge, S., Bao, K., Yan, C., Zeng, D.: Learning shape-biased representations for infrared small target detection. IEEE Trans. Multimedia 1\u201312 (2023)","DOI":"10.1109\/TMM.2023.3325743"},{"key":"24_CR33","doi-asserted-by":"publisher","first-page":"5921","DOI":"10.1109\/TIP.2023.3326396","volume":"32","author":"F Liu","year":"2023","unstructured":"Liu, F., Gao, C., Chen, F., Meng, D., Zuo, W., Gao, X.: Infrared small and dim target detection with transformer under complex backgrounds. IEEE Trans. Image Process. 32, 5921\u20135932 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"24_CR36","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.S.: Image segmentation using text and image prompts. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022, pp. 7076\u20137086. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"issue":"1","key":"24_CR38","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1109\/TPAMI.2023.3322604","volume":"46","author":"N Madan","year":"2024","unstructured":"Madan, N., et al.: Self-supervised masked convolutional transformer block for anomaly detection. IEEE Trans. Pattern Anal. Mach. Intell. 46(1), 525\u2013542 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR39","unstructured":"OpenAI: Gpt-4 technical report. PREPRINT (2023)"},{"key":"24_CR40","unstructured":"OTCBVS: Otcbvs benchmark dataset collection. https:\/\/vcipl-okstate.org\/pbvs\/bench\/index.html"},{"issue":"3","key":"24_CR41","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","volume":"24","author":"H Pan","year":"2022","unstructured":"Pan, H., Hong, Y., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans. Intell. Transp. Syst. 24(3), 3448\u20133460 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"24_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Reed, C.J., et al.: Scale-MAE: a scale-aware masked autoencoder for multiscale geospatial representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4088\u20134099 (2023)","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"24_CR44","unstructured":"Reporter, T.M.: Infrared camera finds 6-year-old lost in deep woods. https:\/\/www.youtube.com\/watch?v=-FajSFRlkIo"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Scheibenreif, L., Mommert, M., Borth, D.: Masked vision transformers for hyperspectral image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2165\u20132175 (2023)","DOI":"10.1109\/CVPRW59228.2023.00210"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"St-Charles, P.L., Bilodeau, G.A., Bergevin, R.: Mutual foreground segmentation with multispectral stereo pairs. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 375\u2013384 (2017)","DOI":"10.1109\/ICCVW.2017.55"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"24_CR48","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83\u201384","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Zhang, H., Jiang, X., Ma, J.: PIAFusion: a progressive infrared and visible image fusion network based on illumination aware. Inf. Fus. 83\u201384, 79\u201392 (2022)","journal-title":"Inf. Fus."},{"key":"24_CR49","doi-asserted-by":"publisher","unstructured":"Tian, Z., Liu, H., Li, Q.: VU-Net: a symmetric network-based method for near-infrared blood vessel image segmentation. In: Long, S., Dhillon, B.S. (eds.) MMESE 2023. LNCS, vol. 1069, pp. 275\u2013280. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-981-99-4882-6_39","DOI":"10.1007\/978-981-99-4882-6_39"},{"key":"24_CR50","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR51","unstructured":"ultralytics: ultralytics (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"24_CR52","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Videomae v2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: Convnext v2: co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"24_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"24_CR56","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.infrared.2018.11.007","volume":"96","author":"Z Xu","year":"2019","unstructured":"Xu, Z., Zhuang, J., Liu, Q., Zhou, J., Peng, S.: Benchmarking a large-scale fir dataset for on-road pedestrian detection. Infrared Phys. Technol. 96, 199\u2013208 (2019)","journal-title":"Infrared Phys. Technol."},{"key":"24_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58555-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Yin","year":"2020","unstructured":"Yin, M., et al.: Disentangled non-local neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 191\u2013207. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_12"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, M., Zhang, R., Yang, Y., Bai, H., Zhang, J., Guo, J.: ISNet: shape matters for infrared small target detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 877\u2013886 (2022)","DOI":"10.1109\/CVPR52688.2022.00095"},{"key":"24_CR59","first-page":"27061","volume":"35","author":"R Zhang","year":"2022","unstructured":"Zhang, R., et al.: Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training. Adv. Neural. Inf. Process. Syst. 35, 27061\u201327074 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"24_CR60","doi-asserted-by":"publisher","first-page":"10535","DOI":"10.1109\/TPAMI.2023.3261282","volume":"45","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Demiris, Y.: Visible and infrared image fusion using deep learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10535\u201310554 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72649-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:12:59Z","timestamp":1727593979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}