{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:14:52Z","timestamp":1773825292258,"version":"3.50.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732256","type":"print"},{"value":"9783031732263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73226-3_3","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"37-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Watching it in\u00a0Dark: A Target-Aware Representation Learning Framework for\u00a0High-Level Vision Tasks in\u00a0Low Illumination"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7316-4354","authenticated-orcid":false,"given":"Yunan","family":"Li","sequence":"first","affiliation":[]},{"given":"Yihao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shoude","family":"Li","sequence":"additional","affiliation":[]},{"given":"Long","family":"Tian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-4657","authenticated-orcid":false,"given":"Dou","family":"Quan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2781-4683","authenticated-orcid":false,"given":"Chaoneng","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-388X","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"3_CR1","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Arruda, V.F., et al.: Cross-domain car detection using unsupervised image-to-image translation: From day to night. In: IJCNN, pp.\u00a01\u20138 (2019)","DOI":"10.1109\/IJCNN.2019.8852008"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Bian, H., Lin, J., Wang, H., Timofte, R., Zhang, Y.: Retinexformer: one-stage retinex-based transformer for low-light image enhancement. In: ICCV, pp. 12504\u201312513 (2023)","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"3_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607 (2020)"},{"key":"3_CR6","unstructured":"Chen, W., Wenjing, W., Wenhan, Y., Jiaying, L.: Deep retinex decomposition for low-light enhancement. In: BMVC, pp. 1\u201312 (2018)"},{"key":"3_CR7","unstructured":"Cui, Z., et al.: You only need 90k parameters to adapt light: a light weight transformer for image enhancement and exposure correction. In: BMVC, pp. 21\u201324 (2022)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Cui, Z., Qi, G.J., Gu, L., You, S., Zhang, Z., Harada, T.: Multitask AET with orthogonal tangent regularity for dark object detection. In: ICCV, pp. 2553\u20132562 (2021)","DOI":"10.1109\/ICCV48922.2021.00255"},{"key":"3_CR9","unstructured":"Feichtenhofer, C., Li, Y., He, K., et\u00a0al.: Masked autoencoders as spatiotemporal learners. In: NeurIPS, pp. 35946\u201335958 (2022)"},{"key":"3_CR10","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent-a new approach to self-supervised learning. In: NeurIPS, pp. 21271\u201321284 (2020)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Zero-reference deep curve estimation for low-light image enhancement. In: CVPR, pp. 1780\u20131789 (2020)","DOI":"10.1109\/CVPR42600.2020.00185"},{"issue":"2","key":"3_CR12","first-page":"982","volume":"26","author":"X Guo","year":"2016","unstructured":"Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE TIP 26(2), 982\u2013993 (2016)","journal-title":"IEEE TIP"},{"key":"3_CR13","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: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In: CVPR, pp.\u00a01\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383267"},{"issue":"5","key":"3_CR17","first-page":"1322","volume":"67","author":"S Huang","year":"2018","unstructured":"Huang, S., Tran, T.D.: Sparse signal recovery via generalized entropy functions minimization. IEEE TSP 67(5), 1322\u20131337 (2018)","journal-title":"IEEE TSP"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Contrastive masked autoencoders are stronger vision learners. IEEE TPAMI 46(4), 2506\u20132517 (2023)","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, H., Zheng, Y.: Learning to see moving objects in the dark. In: ICCV, pp. 7324\u20137333 (2019)","DOI":"10.1109\/ICCV.2019.00742"},{"key":"3_CR20","first-page":"2340","volume":"30","author":"Y Jiang","year":"2021","unstructured":"Jiang, Y., et al.: EnlightenGAN: deep light enhancement without paired supervision. IEEE TIP 30, 2340\u20132349 (2021)","journal-title":"IEEE TIP"},{"issue":"6","key":"3_CR21","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/scientificamerican1277-108","volume":"237","author":"EH Land","year":"1977","unstructured":"Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108\u2013129 (1977)","journal-title":"Sci. Am."},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Lengyel, A., Garg, S., Milford, M., van Gemert, J.C.: Zero-shot day-night domain adaptation with a physics prior. In: ICCV, pp. 4399\u20134409 (2021)","DOI":"10.1109\/ICCV48922.2021.00436"},{"issue":"8","key":"3_CR23","first-page":"4225","volume":"44","author":"C Li","year":"2021","unstructured":"Li, C., Guo, C., Loy, C.C.: Learning to enhance low-light image via zero-reference deep curve estimation. IEEE TPAMI 44(8), 4225\u20134238 (2021)","journal-title":"IEEE TPAMI"},{"issue":"6","key":"3_CR24","first-page":"2828","volume":"27","author":"M Li","year":"2018","unstructured":"Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing low-light image enhancement via robust retinex model. IEEE TIP 27(6), 2828\u20132841 (2018)","journal-title":"IEEE TIP"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. PR 80, 109\u2013117 (2018)","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, H., Feng, G., Miao, Q.: Learning robust representations with information bottleneck and memory network for RGB-D-based gesture recognition. In: ICCV, pp. 20968\u201320978 (2023)","DOI":"10.1109\/ICCV51070.2023.01917"},{"key":"3_CR27","first-page":"4704","volume":"25","author":"Y Li","year":"2023","unstructured":"Li, Y.: Image hazing and dehazing: from the viewpoint of two-way image translation with a weakly supervised framework. IEEE TMM 25, 4704\u20134717 (2023)","journal-title":"IEEE TMM"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: LAP-Net: level-aware progressive network for image dehazing. In: ICCV, pp. 3276\u20133285 (2019)","DOI":"10.1109\/ICCV.2019.00337"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, T., Ma, Z., Quan, D., Miao, Q.: Seeking a hierarchical prototype for multimodal gesture recognition. IEEE TNNLS (2023)","DOI":"10.1109\/TNNLS.2023.3295811"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Liang, Z., Li, C., Zhou, S., Feng, R., Loy, C.C.: Iterative prompt learning for unsupervised backlit image enhancement. In: ICCV, pp. 8094\u20138103 (2023)","DOI":"10.1109\/ICCV51070.2023.00743"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Liu, D., Wen, B., Liu, X., Wang, Z., Huang, T.: When image denoising meets high-level vision tasks: a deep learning approach. In: IJCAI, pp. 842\u2013848 (2018)","DOI":"10.24963\/ijcai.2018\/117"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Liu, R., Ma, L., Zhang, J., Fan, X., Luo, Z.: Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: CVPR, pp. 10561\u201310570 (2021)","DOI":"10.1109\/CVPR46437.2021.01042"},{"key":"3_CR33","first-page":"30","volume":"178","author":"YP Loh","year":"2019","unstructured":"Loh, Y.P., Chan, C.S.: Getting to know low-light images with the exclusively dark dataset. CVIU 178, 30\u201342 (2019)","journal-title":"CVIU"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Luo, R., Wang, W., Yang, W., Liu, J.: Similarity min-max: zero-shot day-night domain adaptation. In: ICCV, pp. 8104\u20138114 (2023)","DOI":"10.1109\/ICCV51070.2023.00744"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Ma, L., Ma, T., Liu, R., Fan, X., Luo, Z.: Toward fast, flexible, and robust low-light image enhancement. In: CVPR, pp. 5637\u20135646 (2022)","DOI":"10.1109\/CVPR52688.2022.00555"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.Y.: Contrastive learning for unpaired image-to-image translation. In: ECCV, pp. 319\u2013345 (2020)","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Porav, H., Maddern, W., Newman, P.: Adversarial training for adverse conditions: robust metric localisation using appearance transfer. In: ICRA, pp. 1011\u20131018 (2018)","DOI":"10.1109\/ICRA.2018.8462894"},{"key":"3_CR38","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Gool, L.V.: Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. In: ICCV, pp. 7374\u20137383 (2019)","DOI":"10.1109\/ICCV.2019.00747"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Sasagawa, Y., Nagahara, H.: YOLO in the dark-domain adaptation method for merging multiple models. In: ECCV, pp. 345\u2013359 (2020)","DOI":"10.1007\/978-3-030-58589-1_21"},{"key":"3_CR41","first-page":"1229","volume":"26","author":"Y Shi","year":"2023","unstructured":"Shi, Y., et al.: A semi-supervised underexposed image enhancement network with supervised context attention and multi-exposure fusion. IEEE TMM 26, 1229\u20131243 (2023)","journal-title":"IEEE TMM"},{"key":"3_CR42","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS, pp. 10078\u201310093 (2022)"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Trahanias, P.E., Venetsanopoulos, A.N.: Color image enhancement through 3-D histogram equalization. In: ICPR, pp. 545\u2013548 (1992)","DOI":"10.1109\/ICPR.1992.202045"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"3_CR45","first-page":"3507","volume":"32","author":"Z Tu","year":"2023","unstructured":"Tu, Z., Liu, Y., Zhang, Y., Mu, Q., Yuan, J.: DTCM: joint optimization of dark enhancement and action recognition in videos. IEEE TIP 32, 3507\u20133520 (2023)","journal-title":"IEEE TIP"},{"issue":"12","key":"3_CR46","doi-asserted-by":"publisher","first-page":"4272","DOI":"10.1109\/TPAMI.2020.2996538","volume":"43","author":"RG VidalMata","year":"2020","unstructured":"VidalMata, R.G., et al.: Bridging the gap between computational photography and visual recognition. IEEE TPAMI 43(12), 4272\u20134290 (2020)","journal-title":"IEEE TPAMI"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV, pp. 3119\u20133127 (2015)","DOI":"10.1109\/ICCV.2015.357"},{"issue":"9","key":"3_CR48","first-page":"3538","volume":"22","author":"S Wang","year":"2013","unstructured":"Wang, S., Zheng, J., Hu, H.M., Li, B.: Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE TIP 22(9), 3538\u20133548 (2013)","journal-title":"IEEE TIP"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., Xu, Z., Huang, H., Liu, J.: Self-aligned concave curve: Illumination enhancement for unsupervised adaptation. In: ACM MM, pp. 2617\u20132626 (2022)","DOI":"10.1145\/3503161.3547991"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., Yang, W., Liu, J.: HLA-Face: joint high-low adaptation for low light face detection. In: CVPR, pp. 16195\u201316204 (2021)","DOI":"10.1109\/CVPR46437.2021.01593"},{"key":"3_CR51","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: CVPR, pp. 1568\u20131576 (2017)","DOI":"10.1109\/CVPR.2017.687"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Wu, W., Weng, J., Zhang, P., Wang, X., Yang, W., Jiang, J.: URetinex-Net: Retinex-based deep unfolding network for low-light image enhancement. In: CVPR, pp. 5901\u20135910 (2022)","DOI":"10.1109\/CVPR52688.2022.00581"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Wu, X., Wu, Z., Guo, H., Ju, L., Wang, S.: DANNet: a one-stage domain adaptation network for unsupervised nighttime semantic segmentation. In: CVPR, pp. 15769\u201315778 (2021)","DOI":"10.1109\/CVPR46437.2021.01551"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yang, J., Cao, H., Mao, K., Yin, J., See, S.: ARID: a new dataset for recognizing action in the dark. In: IJCAI Workshop, pp. 70\u201384 (2021)","DOI":"10.1007\/978-981-16-0575-8_6"},{"issue":"11","key":"3_CR55","doi-asserted-by":"publisher","first-page":"4059","DOI":"10.1109\/TPAMI.2020.2995190","volume":"43","author":"W Yang","year":"2020","unstructured":"Yang, W., Tan, R.T., Wang, S., Fang, Y., Liu, J.: Single image deraining: from model-based to data-driven and beyond. IEEE TPAMI 43(11), 4059\u20134077 (2020)","journal-title":"IEEE TPAMI"},{"key":"3_CR56","first-page":"5737","volume":"29","author":"W Yang","year":"2020","unstructured":"Yang, W., et al.: Advancing image understanding in poor visibility environments: a collective benchmark study. IEEE TIP 29, 5737\u20135752 (2020)","journal-title":"IEEE TIP"},{"key":"3_CR57","unstructured":"Yao, Y., Desai, N., Palaniswami, M.: Masked contrastive representation learning. arXiv preprint arXiv:2211.06012 (2022)"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, F., Li, Y., You, S., Fu, Y.: Learning temporal consistency for low light video enhancement from single images. In: CVPR, pp. 4967\u20134976 (2021)","DOI":"10.1109\/CVPR46437.2021.00493"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Zheng, S., Gupta, G.: Semantic-guided zero-shot learning for low-light image\/video enhancement. In: WACV, pp. 581\u2013590 (2022)","DOI":"10.1109\/WACVW54805.2022.00064"},{"key":"3_CR60","unstructured":"Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: Domain generalization with MixStyle. In: ICLR, pp. 1\u201315 (2021)"},{"key":"3_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, S., Li, C., Change\u00a0Loy, C.: LEDNet: joint low-light enhancement and deblurring in the dark. In: ECCV, pp. 573\u2013589 (2022)","DOI":"10.1007\/978-3-031-20068-7_33"},{"issue":"3","key":"3_CR62","first-page":"3421","volume":"45","author":"J Zhu","year":"2022","unstructured":"Zhu, J., et al.: Masked contrastive representation learning for reinforcement learning. IEEE TPAMI 45(3), 3421\u20133433 (2022)","journal-title":"IEEE TPAMI"}],"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\/978-3-031-73226-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:11:58Z","timestamp":1730387518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73226-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732256","9783031732263"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73226-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 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"}}]}}