{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:04:01Z","timestamp":1790111041368,"version":"4.0.1"},"reference-count":54,"publisher":"Optica Publishing Group","issue":"28","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1364\/OA_License_v2#VOR"},{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/opg.optica.org\/policies\/opg-tdm-policy.json"}],"content-domain":{"domain":["opg.optica.org"],"crossmark-restriction":false},"short-container-title":["Appl. Opt."],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:p>Low-light object detection is a challenging task in computer vision and visual computing, with wide applications in autonomous systems, underwater monitoring, and nighttime surveillance. Images captured under insufficient illumination usually suffer from low contrast, noise amplification, and degraded texture details, which reduce detection reliability. This work proposes CMSA-Net, a context-guided multi-scale adaptive network for low-light object detection. CMSA-Net integrates an adaptive context-split backbone, input-adaptive enhanced attention, and multi-scale adaptive fusion to improve feature representation under illumination degradation. On ExDark and RUOD, CMSA-Net achieves 71.89% and 88.10% mAP@0.5, respectively, while maintaining a lightweight model size and real-time inference speed. A self-built controlled darkroom imaging platform is further used to analyze detector behavior under different illuminance, exposure time, and ISO settings, showing that CMSA-Net provides stable gains under low and mid-to-low effective exposure conditions. These results demonstrate the effectiveness of CMSA-Net for robust object detection in low-light imaging scenarios.<\/jats:p>","DOI":"10.1364\/ao.607058","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T16:00:11Z","timestamp":1788537611000},"page":"9687","update-policy":"https:\/\/doi.org\/10.1364\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Context-guided adaptive feature learning for robust low-light object detection"],"prefix":"10.1364","volume":"65","author":[{"given":"Lusheng","family":"Yan","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00xyeez13","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Ye","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00xyeez13","id-type":"ROR","asserted-by":"publisher"}]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"285","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"ao-65-28-9687-R1","doi-asserted-by":"publisher","first-page":"15685","DOI":"10.1109\/TNNLS.2025.3566647","type":"journal-article","volume":"36","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ao-65-28-9687-R2","doi-asserted-by":"publisher","first-page":"105106","DOI":"10.1016\/j.imavis.2024.105106","type":"journal-article","volume":"148","author":"Ghari","year":"2024","journal-title":"Image Vis. Comput."},{"key":"ao-65-28-9687-R3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.cviu.2018.10.010","type":"journal-article","volume":"178","author":"Loh","year":"2019","journal-title":"Comput. Vis. Image Underst."},{"key":"ao-65-28-9687-R4","first-page":"12504","article-title":"Retinexformer: one-stage retinex-based transformer for low-light image enhancement","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Cai","year":"2023"},{"key":"ao-65-28-9687-R5","first-page":"5678","article-title":"HVI: a new color space for low-light image enhancement","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yan","year":"2025"},{"key":"ao-65-28-9687-R6","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1007\/s00371-024-03452-w","type":"journal-article","volume":"41","author":"Fang","year":"2025","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R7","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s00371-024-03353-y","type":"journal-article","volume":"41","author":"Wu","year":"2025","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R8","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.3390\/electronics12143089","type":"journal-article","volume":"12","author":"Wang","year":"2023","journal-title":"Electronics"},{"key":"ao-65-28-9687-R9","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1038\/s41598-024-54428-8","type":"journal-article","volume":"14","author":"Peng","year":"2024","journal-title":"Sci. Rep."},{"key":"ao-65-28-9687-R10","doi-asserted-by":"publisher","first-page":"27922","DOI":"10.1038\/s41598-024-79211-7","type":"journal-article","volume":"14","author":"Ding","year":"2024","journal-title":"Sci. Rep."},{"key":"ao-65-28-9687-R11","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.3390\/s26041138","type":"journal-article","volume":"26","author":"Tian","year":"2026","journal-title":"Sensors"},{"key":"ao-65-28-9687-R12","doi-asserted-by":"publisher","first-page":"5001617","DOI":"10.1109\/TIM.2026.3655940","type":"journal-article","volume":"75","author":"Wu","year":"2026","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ao-65-28-9687-R13","doi-asserted-by":"publisher","first-page":"111979","DOI":"10.1016\/j.engappai.2025.111979","type":"journal-article","volume":"160","author":"Chen","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ao-65-28-9687-R14","doi-asserted-by":"publisher","first-page":"110719","DOI":"10.1016\/j.knosys.2023.110719","type":"journal-article","volume":"275","author":"Yao","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ao-65-28-9687-R15","doi-asserted-by":"publisher","first-page":"5170","DOI":"10.3390\/app15095170","type":"journal-article","volume":"15","author":"Liu","year":"2025","journal-title":"Appl. Sci."},{"key":"ao-65-28-9687-R16","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s13735-025-00374-8","type":"journal-article","volume":"14","author":"Zhang","year":"2025","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ao-65-28-9687-R17","doi-asserted-by":"publisher","first-page":"7288","DOI":"10.3390\/app15137288","type":"journal-article","volume":"15","author":"Xiong","year":"2025","journal-title":"Appl. Sci."},{"key":"ao-65-28-9687-R18","first-page":"283","article-title":"AMFF-YOLO: low-light object detection method based on adaptive multi-scale feature fusion","volume-title":"5th International Conference on Artificial Intelligence, Robotics, and Communication","author":"Zhu","year":"2025"},{"key":"ao-65-28-9687-R19","first-page":"2117","article-title":"Feature pyramid networks for object detection","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Lin","year":"2017"},{"key":"ao-65-28-9687-R20","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tan","year":"2020"},{"key":"ao-65-28-9687-R21","doi-asserted-by":"publisher","author":"Jiang","year":"2022","DOI":"10.48550\/arXiv.2202.04256","type":"preprint"},{"key":"ao-65-28-9687-R22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s00530-024-01617-0","type":"journal-article","volume":"31","author":"Zheng","year":"2025","journal-title":"Multimed. Syst."},{"key":"ao-65-28-9687-R23","doi-asserted-by":"publisher","first-page":"111266","DOI":"10.1016\/j.patcog.2024.111266","type":"journal-article","volume":"161","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."},{"key":"ao-65-28-9687-R24","doi-asserted-by":"publisher","first-page":"7233","DOI":"10.1007\/s00371-025-03802-2","type":"journal-article","volume":"41","author":"Dai","year":"2025","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R25","doi-asserted-by":"publisher","first-page":"6198","DOI":"10.1109\/TMM.2025.3565935","type":"journal-article","volume":"27","author":"Wen","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"ao-65-28-9687-R26","doi-asserted-by":"publisher","first-page":"e70030","DOI":"10.1002\/cav.70030","type":"journal-article","volume":"36","author":"Lin","year":"2025","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"ao-65-28-9687-R27","first-page":"276","article-title":"Multispectral fusion for object detection with cyclic fuse-and-refine blocks","volume-title":"IEEE International Conference on Image Processing","author":"Zhang","year":"2020"},{"key":"ao-65-28-9687-R28","first-page":"72","article-title":"Guided attentive feature fusion for multispectral pedestrian detection","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Zhang","year":"2021"},{"key":"ao-65-28-9687-R29","first-page":"2920","article-title":"BAANet: learning bi-directional adaptive attention gates for multispectral pedestrian detection","volume-title":"International Conference on Robotics and Automation","author":"Yang","year":"2022"},{"key":"ao-65-28-9687-R30","doi-asserted-by":"publisher","first-page":"2934","DOI":"10.3390\/s23062934","type":"journal-article","volume":"23","author":"Bao","year":"2023","journal-title":"Sensors"},{"key":"ao-65-28-9687-R31","doi-asserted-by":"publisher","author":"Chen","year":"2024","DOI":"10.48550\/arXiv.2412.04931","type":"preprint"},{"key":"ao-65-28-9687-R32","first-page":"22","article-title":"DGC-GatedFusion: an improved YOLOv11 model for low-light RGB-D pedestrian detection","volume-title":"10th International Conference on Signal and Image Processing","author":"Guo","year":"2025"},{"key":"ao-65-28-9687-R33","doi-asserted-by":"publisher","first-page":"6088","DOI":"10.1109\/TPAMI.2025.3544621","type":"journal-article","volume":"47","author":"Ying","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ao-65-28-9687-R34","doi-asserted-by":"publisher","first-page":"13799","DOI":"10.1109\/TAES.2025.3580391","type":"journal-article","volume":"61","author":"Su","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ao-65-28-9687-R35","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/s11263-022-01728-z","type":"journal-article","volume":"131","author":"He","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ao-65-28-9687-R36","first-page":"8103","article-title":"Multi-view adversarial discriminator: mine the non-causal factors for object detection in unseen domains","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xu","year":"2023"},{"key":"ao-65-28-9687-R37","doi-asserted-by":"publisher","first-page":"11947","DOI":"10.1007\/s00371-025-04136-9","type":"journal-article","volume":"41","author":"Wang","year":"2025","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R38","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.neucom.2022.10.039","type":"journal-article","volume":"517","author":"Fu","year":"2023","journal-title":"Neurocomputing"},{"key":"ao-65-28-9687-R39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1364\/JOSA.61.000001","type":"journal-article","volume":"61","author":"Land","year":"1971","journal-title":"J. Opt. Soc. Am."},{"key":"ao-65-28-9687-R40","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s00371-026-04368-3","type":"journal-article","volume":"42","author":"Nan","year":"2026","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R41","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s00371-026-04471-5","type":"journal-article","volume":"42","author":"Xue","year":"2026","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R42","doi-asserted-by":"publisher","first-page":"20240376","DOI":"10.3788\/IRLA20240376","type":"journal-article","volume":"54","author":"Li","year":"2025","journal-title":"Infrared Laser Eng."},{"key":"ao-65-28-9687-R43","doi-asserted-by":"publisher","first-page":"90","DOI":"10.3390\/app15010090","type":"journal-article","volume":"15","author":"Han","year":"2025","journal-title":"Appl. Sci."},{"key":"ao-65-28-9687-R44","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.11591\/eei.v14i3.8903","type":"journal-article","volume":"14","author":"Rendi","year":"2025","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ao-65-28-9687-R45","doi-asserted-by":"publisher","first-page":"113793","DOI":"10.1016\/j.patcog.2026.113793","type":"journal-article","volume":"179","author":"Qin","year":"2026","journal-title":"Pattern Recognit."},{"key":"ao-65-28-9687-R46","article-title":"Gold-YOLO: efficient object detector via gather-and-distribute mechanism","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang","year":"2023"},{"key":"ao-65-28-9687-R47","doi-asserted-by":"publisher","author":"Shi","year":"2025","DOI":"10.48550\/arXiv.2412.10116","type":"preprint"},{"key":"ao-65-28-9687-R48","doi-asserted-by":"publisher","first-page":"105057","DOI":"10.1016\/j.imavis.2024.105057","type":"journal-article","volume":"147","author":"Kang","year":"2024","journal-title":"Image Vis. Comput."},{"key":"ao-65-28-9687-R49","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s40747-025-02126-x","type":"journal-article","volume":"12","author":"Luo","year":"2026","journal-title":"Complex Intell. Syst."},{"key":"ao-65-28-9687-R50","doi-asserted-by":"publisher","first-page":"112965","DOI":"10.1016\/j.patcog.2025.112965","type":"journal-article","volume":"174","author":"Shang","year":"2026","journal-title":"Pattern Recognit."},{"key":"ao-65-28-9687-R51","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","type":"journal-article","volume":"21","author":"Li","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"ao-65-28-9687-R52","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/s00371-026-04483-1","type":"journal-article","volume":"42","author":"Ma","year":"2026","journal-title":"Vis. Comput."},{"key":"ao-65-28-9687-R53","doi-asserted-by":"publisher","author":"Yan","year":"2026","DOI":"10.6084\/m9.figshare.33315516","type":"dataset"},{"key":"ao-65-28-9687-R54","unstructured":"luxiao11 , \u201c CMSA-Net-CLL-ITS ,\u201d GitHub , 2026 , https:\/\/github.com\/luxiao11\/CMSA-Net-CLL-ITS ."}],"container-title":["Applied Optics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/opg.optica.org\/viewmedia.cfm?URI=ao-65-28-9687&seq=0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:05:28Z","timestamp":1790107528000},"score":1,"resource":{"primary":{"URL":"https:\/\/opg.optica.org\/abstract.cfm?URI=ao-65-28-9687"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":54,"journal-issue":{"issue":"28","published-online":{"date-parts":[[2026]]},"published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1364\/ao.607058","relation":{},"ISSN":["1559-128X","2155-3165"],"issn-type":[{"value":"1559-128X","type":"print"},{"value":"2155-3165","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"assertion":[{"value":"Optica Publishing Group","name":"publisher","label":"This article is maintained by"},{"value":"https:\/\/doi.org\/10.1364\/AO.607058","name":"articlelink","label":"Crossref DOI link to publisher maintained version"},{"value":"research-article","name":"content_type","label":"Article type"},{"value":"Screened by Similarity Check","name":"cross_check","label":"Similarity check"},{"value":"Yes","order":0,"name":"peer_reviewed","label":"Peer reviewed","group":{"name":"peer_review","label":"Peer review"}},{"value":"Single blind","order":1,"name":"review_process","label":"Review process","group":{"name":"peer_review","label":"Peer review"}},{"value":"2 June 2026","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"4 September 2026","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"22 September 2026","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}},{"value":"\u00a9 2026 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.","name":"copyright","label":"Copyright"}]}}