{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:48:33Z","timestamp":1783007313973,"version":"3.54.5"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071369"],"award-info":[{"award-number":["12071369"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132275","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:44:12Z","timestamp":1774885452000},"page":"132275","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["PE-Det: Prior-Guided visible preconditioning and routed expert fusion for robust infrared-visible object detection"],"prefix":"10.1016","volume":"321","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3280-5272","authenticated-orcid":false,"given":"Yuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0113-7912","authenticated-orcid":false,"given":"Xiaoyan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyi","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132275_bib0001","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2025.3607632","article-title":"Motion and appearance decoupling representation for event cameras","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132275_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111098","article-title":"Acfnet: an adaptive cross-fusion network for infrared and visible image fusion","volume":"159","author":"Chen","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132275_bib0003","series-title":"International conference on pattern recognition","first-page":"236","article-title":"Deyolo: dual-feature-enhancement yolo for cross-modality object detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0004","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F., Zhou, B., & Zhao, H. (2022). Autoalign: Pixel-instance feature aggregation for multi-modal 3d object detection. arXiv: 2201.06493.","DOI":"10.24963\/ijcai.2022\/116"},{"key":"10.1016\/j.eswa.2026.132275_bib0005","article-title":"Multispectral remote sensing object detection via selective cross-modal interaction and aggregation","author":"Cui","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132275_bib0006","series-title":"Computer vision and pattern recognition","first-page":"1","article-title":"Yolov3: an incremental improvement","volume":"vol. 1804","author":"Farhadi","year":"2018"},{"key":"10.1016\/j.eswa.2026.132275_bib0007","unstructured":"Gevorgyan, Z. (2022). Siou loss: More powerful learning for bounding box regression. arXiv: 2205.12740."},{"key":"10.1016\/j.eswa.2026.132275_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.eswa.2026.132275_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111425","article-title":"Fsenet: feature suppression and enhancement network for tiny object detection","volume":"162","author":"Hu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132275_bib0010","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.eswa.2026.132275_bib0011","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.inffus.2023.02.026","article-title":"Multiscale structural feature transform for multi-modal image matching","volume":"95","author":"Hu","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132275_bib0012","first-page":"1","article-title":"Fddba-net: frequency domain decoupling bidirectional interactive attention network for infrared small target detection","volume":"62","author":"Huang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132275_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3496","article-title":"Llvip: a visible-infrared paired dataset for low-light vision","author":"Jia","year":"2021"},{"key":"10.1016\/j.eswa.2026.132275_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105057","article-title":"Asf-yolo: a novel yolo model with attentional scale sequence fusion for cell instance segmentation","volume":"147","author":"Kang","year":"2024","journal-title":"Image and Vision Computing"},{"key":"10.1016\/j.eswa.2026.132275_bib0015","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.inffus.2022.09.019","article-title":"Current advances and future perspectives of image fusion: a comprehensive review","volume":"90","author":"Karim","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132275_bib0016","series-title":"European conference on computer vision","first-page":"232","article-title":"Diffusion model for robust multi-sensor fusion in 3d object detection and bev segmentation","author":"Le","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0017","unstructured":"Glenn Jocher, Ultralytics yolov5, 2020, https:\/\/github.com\/ultralytics\/yolov5."},{"key":"10.1016\/j.eswa.2026.132275_bib0018","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W. et al. (2022). Yolov6: A single-stage object detection framework for industrial applications. arXiv: 2209.02976."},{"key":"10.1016\/j.eswa.2026.132275_bib0019","unstructured":"Glenn Jocher, Ayush Chaurasia, and Jing Qiu, Ultralytics yolov8, 2023, https:\/\/github.com\/ultralytics\/ultralytics."},{"issue":"3","key":"10.1016\/j.eswa.2026.132275_bib0020","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","volume":"21","author":"Li","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"key":"10.1016\/j.eswa.2026.132275_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127229","article-title":"FefDM-transformer: dual-channel multi-stage transformer-based encoding and fusion mode for infrared\u2013visible images","volume":"277","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132275_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2023.113359","article-title":"Efd-yolov4: a steel surface defect detection network with encoder-decoder residual block and feature alignment module","volume":"220","author":"Li","year":"2023","journal-title":"Measurement"},{"key":"10.1016\/j.eswa.2026.132275_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122038","article-title":"Visible-infrared image matching based on parameter-free attention mechanism and target-aware graph attention mechanism","volume":"238","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132275_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5802","article-title":"Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132275_bib0025","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"8115","article-title":"Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132275_bib0026","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"2226","article-title":"Dcevo: discriminative cross-dimensional evolutionary learning for infrared and visible image fusion","author":"Liu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132275_bib0027","series-title":"European conference on computer vision","first-page":"38","article-title":"Grounding dino: marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0028","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1792","article-title":"Image-adaptive YOLO for object detection in adverse weather conditions","volume":"vol. 36","author":"Liu","year":"2022"},{"issue":"1","key":"10.1016\/j.eswa.2026.132275_bib0029","article-title":"Metal surface defect detection using SLF-YOLO enhanced YOLOv8 model","volume":"15","author":"Liu","year":"2025","journal-title":"Scientific Reports"},{"key":"10.1016\/j.eswa.2026.132275_bib0030","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tang, H., Amini, A., Yang, X., Mao, H., Rus, D., & Han, S. (2022c). Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. arXiv: 2205.13542.","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"10.1016\/j.eswa.2026.132275_bib0031","first-page":"1","article-title":"Stdfusionnet: an infrared and visible image fusion network based on salient target detection","volume":"70","author":"Ma","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.132275_bib0032","unstructured":"Ma, S., & Xu, Y. (2023). Mpdiou: a loss for efficient and accurate bounding box regression. arXiv: 2307.07662."},{"key":"10.1016\/j.eswa.2026.132275_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5694","article-title":"Rewrite the stars","author":"Ma","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0034","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2172","article-title":"Visual modality prompt for adapting vision-language object detectors","author":"Medeiros","year":"2025"},{"key":"10.1016\/j.eswa.2026.132275_bib0035","unstructured":"Qingyun, F., Dapeng, H., & Zhaokui, W. (2021). Cross-modality fusion transformer for multispectral object detection. arXiv: 2111.00273."},{"key":"10.1016\/j.eswa.2026.132275_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108786","article-title":"Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery","volume":"130","author":"Qingyun","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132275_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"658","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.eswa.2026.132275_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109913","article-title":"Icafusion: iterative cross-attention guided feature fusion for multispectral object detection","volume":"145","author":"Shen","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132275_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17773","article-title":"Transnext: robust foveal visual perception for vision transformers","author":"Shi","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2025.117416","article-title":"Data fusion-driven hyperspectral imaging for non-destructive detection of single maize seed vigor","volume":"253","author":"Shi","year":"2025","journal-title":"Measurement"},{"key":"10.1016\/j.eswa.2026.132275_bib0041","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"4003","article-title":"Detfusion: a detection-driven infrared and visible image fusion network","author":"Sun","year":"2022"},{"key":"10.1016\/j.eswa.2026.132275_bib0042","series-title":"The thirty-ninth annual conference on neural information processing systems","article-title":"Controlfusion: a controllable image fusion network with language-vision degradation prompts","author":"Tang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132275_bib0043","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","article-title":"Image fusion in the loop of high-level vision tasks: a semantic-aware real-time infrared and visible image fusion network","volume":"82","author":"Tang","year":"2022","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132275_bib0044","unstructured":"Wang, A., Chen, H., & Liu, L., et al. (2024a). Yolov10: Real-time end-to-end object detection. arXiv: 2405.14458."},{"issue":"23","key":"10.1016\/j.eswa.2026.132275_bib0045","doi-asserted-by":"crossref","first-page":"29200","DOI":"10.1109\/JSEN.2023.3324451","article-title":"Dfecf-det: all-weather detector based on differential feature enhancement and cross-modal fusion with visible and infrared sensors","volume":"23","author":"Wang","year":"2023","journal-title":"IEEE Sensors Journal"},{"issue":"10","key":"10.1016\/j.eswa.2026.132275_bib0046","doi-asserted-by":"crossref","first-page":"15040","DOI":"10.1109\/TITS.2024.3394573","article-title":"Mdd-shipnet: math-data integrated defogging for fog-occlusion ship detection","volume":"25","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"1","key":"10.1016\/j.eswa.2026.132275_bib0047","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1007\/s10462-025-11426-0","article-title":"Advances and challenges in infrared-visible image fusion: a comprehensive review of techniques and applications","volume":"59","author":"Wang","year":"2026","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.132275_bib0048","series-title":"2024\u202fIEEE intelligent vehicles symposium (IV)","first-page":"2776","article-title":"Unibev: multi-modal 3d object detection with uniform bev encoders for robustness against missing sensor modalities","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132275_bib0049","article-title":"Diffusion prior guided deep model driven network for infrared and visible image fusion","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132275_bib0050","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2025.3535316","article-title":"All-in-one weather-degraded image restoration via adaptive degradation-aware self-prompting model","author":"Wen","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132275_bib0051","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"3","article-title":"Cbam: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.eswa.2026.132275_bib0052","series-title":"proceedings of the thirty-fourth AAAI conference on artificial intelligence","article-title":"FusionDN: a unified densely connected network for image fusion","author":"Xu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132275_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128716","article-title":"Dual-IRDet: cross-attention-based dual-band infrared images fusion for aircraft anti-interference detection","author":"Yang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132275_bib0054","first-page":"9125","article-title":"Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132275_bib0055","unstructured":"Zhang, H., Xu, C., & Zhang, S. (2023a). Inner-iou: more effective intersection over union loss with auxiliary bounding box. arXiv: 2311.02877."},{"issue":"1","key":"10.1016\/j.eswa.2026.132275_bib0056","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/TIP.2018.2867733","article-title":"Adversarial spatio-temporal learning for video deblurring","volume":"28","author":"Zhang","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132275_bib0057","series-title":"International conference on artificial neural networks","first-page":"14","article-title":"Adaptive dehazing yolo for object detection","author":"Zhang","year":"2023"},{"issue":"8","key":"10.1016\/j.eswa.2026.132275_bib0058","doi-asserted-by":"crossref","first-page":"10535","DOI":"10.1109\/TPAMI.2023.3261282","article-title":"Visible and infrared image fusion using deep learning","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132275_bib0059","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"issue":"14","key":"10.1016\/j.eswa.2026.132275_bib0060","doi-asserted-by":"crossref","first-page":"2645","DOI":"10.3390\/rs16142645","article-title":"Small object detection in medium\u2013low-resolution remote sensing images based on degradation reconstruction","volume":"16","author":"Zhao","year":"2024","journal-title":"Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132275_bib0061","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12993","article-title":"Distance-iou loss: faster and better learning for bounding box regression","volume":"vol. 34","author":"Zheng","year":"2020"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011887?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011887?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:01:17Z","timestamp":1780934477000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426011887"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":61,"alternative-id":["S0957417426011887"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132275","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PE-Det: Prior-Guided visible preconditioning and routed expert fusion for robust infrared-visible object detection","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132275","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132275"}}