{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:05:17Z","timestamp":1790111117958,"version":"4.0.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004750","name":"Chinese Aeronautical Establishment Aeronautical Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109404","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T06:30:08Z","timestamp":1784356208000},"page":"109404","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Cross-modality fusion with local and global semantic feature correlation for weakly distinguishable object detection in aerial visible and infrared images"],"prefix":"10.1016","volume":"205","author":[{"given":"Maozhen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5709-6862","authenticated-orcid":false,"given":"Xiaoguang","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ximing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.neunet.2026.109404_bib0001","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3390\/rs16010025","article-title":"An efficient rep-style Gaussian\u2013Wasserstein network: Improved UAV infrared small object detection for urban road surveillance and safety","volume":"16","author":"Aibibu","year":"2023","journal-title":"Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0002","series-title":"Proc. IEEE conf. comput. vis. pattern recog. (CVPR)","first-page":"26826","article-title":"Weakly misalignment-free adaptive feature alignment for UAVs-based multimodal object detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109404_bib0003","doi-asserted-by":"crossref","first-page":"10145","DOI":"10.1109\/TMM.2024.3405714","article-title":"HitFusion: Infrared and visible image fusion for high-level vision tasks using transformer","volume":"26","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109404_bib0004","first-page":"1","article-title":"SSTNet: Sliced spatio-temporal network with cross-slice ConvLSTM for moving infrared dim-small target detection","volume":"62","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109404_bib0005","doi-asserted-by":"crossref","first-page":"6437","DOI":"10.1109\/TNNLS.2024.3392238","article-title":"MICPL: Motion-inspired cross-pattern learning for small-object detection in satellite videos","volume":"36","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109404_bib0006","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":"2025"},{"key":"10.1016\/j.neunet.2026.109404_bib0007","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1272","article-title":"CamoDiffusion: Camouflaged object detection via conditional diffusion models","volume":"vol. 38","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109404_bib0008","unstructured":"Dong, W., Zhu, H., Lin, S., & (2024). Fusion-mamba for cross-modality object detection. arXiv preprint arXiv: 2404.09146."},{"key":"10.1016\/j.neunet.2026.109404_bib0009","first-page":"1","article-title":"Triple-domain feature learning with frequency-aware memory enhancement for moving infrared small target detection","volume":"62","author":"Duan","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0010","first-page":"1","article-title":"Semi-supervised multiview prototype learning with motion reconstruction for moving infrared small target detection","volume":"63","author":"Duan","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0011","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2777","article-title":"Camouflaged object detection","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109404_bib0012","series-title":"IEEE conference on computer vision and pattern recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"issue":"1","key":"10.1016\/j.neunet.2026.109404_bib0013","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s44196-024-00632-3","article-title":"Small object detection in UAV images based on Yolov8n","volume":"17","author":"Xu","year":"2024","journal-title":"International Journal of Computational Intelligence Systems"},{"key":"10.1016\/j.neunet.2026.109404_bib0014","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv: 2312.00752."},{"issue":"23","key":"10.1016\/j.neunet.2026.109404_bib0015","doi-asserted-by":"crossref","first-page":"4451","DOI":"10.3390\/rs16234451","article-title":"MMYFNet: Multi-modality YOLO fusion network for object detection in remote sensing images","volume":"16","author":"Guo","year":"2024","journal-title":"Remote Sensing"},{"issue":"6","key":"10.1016\/j.neunet.2026.109404_bib0016","doi-asserted-by":"crossref","first-page":"402","DOI":"10.3390\/drones7060402","article-title":"Research on object detection and recognition method for UAV aerial images based on improved YOLOv5","volume":"7","author":"Zhang","year":"2023","journal-title":"Drones"},{"issue":"6","key":"10.1016\/j.neunet.2026.109404_bib0017","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.3390\/electronics12061312","article-title":"SuperDet: An efficient single-shot network for vehicle detection in remote sensing images","volume":"12","author":"Ju","year":"2023","journal-title":"Electronics"},{"issue":"1","key":"10.1016\/j.neunet.2026.109404_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00530-024-01595-3","article-title":"PCAF: UAV scenarios detector via pyramid converge-and-assign fusion network","volume":"31","author":"Li","year":"2025","journal-title":"Multimedia Systems"},{"key":"10.1016\/j.neunet.2026.109404_bib0019","first-page":"1","article-title":"Aerial image object detection based on RGB-infrared multibranch progressive fusion","volume":"63","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0020","series-title":"European conference on computer vision (ECCV)","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109404_bib0021","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11591","article-title":"Simultaneously localize, segment and rank the camouflaged objects","author":"Lv","year":"2021"},{"key":"10.1016\/j.neunet.2026.109404_bib0022","series-title":"IEEE\/CVF winter conference on applications of computer vision (WACV)","first-page":"9023","article-title":"Mixed patch visible-infrared modality agnostic object detection","author":"Medeiros","year":"2025"},{"issue":"6","key":"10.1016\/j.neunet.2026.109404_bib0023","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.3390\/rs17061095","article-title":"FQDNet: A fusion-enhanced quad-head network for RGB-infrared object detection","volume":"17","author":"Meng","year":"2025","journal-title":"Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0024","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.neunet.2026.109404_bib0025","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.jvcir.2015.11.002","article-title":"Vehicle detection in aerial imagery: A small target detection benchmark","volume":"34","author":"Razakarivony","year":"2016","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.neunet.2026.109404_bib0026","series-title":"IEEE conference on computer vision and pattern recognition","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"issue":"5","key":"10.1016\/j.neunet.2026.109404_bib0027","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/s10489-025-06264-0","article-title":"Semantic-spatial guided context propagation network for camouflaged object detection","volume":"55","author":"Ren","year":"2025","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.neunet.2026.109404_bib0028","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6250","article-title":"GuideFormer: Transformers for image guided depth completion","author":"Rho","year":"2022"},{"key":"10.1016\/j.neunet.2026.109404_bib0029","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.neunet.2026.109404_bib0030","first-page":"1","article-title":"Low-rank multimodal remote sensing object detection with frequency filtering experts","volume":"62","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0031","article-title":"Mask-guided mamba fusion for drone-based visible-infrared vehicle detection","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0032","article-title":"Cross-modal adaptation for object detection in infrared remote sensing imagery","volume":"22","author":"Wang","year":"2025","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"3","key":"10.1016\/j.neunet.2026.109404_bib0033","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.1109\/TETCI.2025.3542146","article-title":"MSDT: Multiscale diffusion transformer for multimodality image fusion","volume":"9","author":"Xia","year":"2025","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"10.1016\/j.neunet.2026.109404_bib0034","article-title":"Airborne small target detection method based on multi-modal and adaptive feature fusion","volume":"62","author":"Xu","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0035","first-page":"1","article-title":"C2Former: Calibrated and complementary transformer for RGB-infrared object detection","volume":"62","author":"Yuan","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0036","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"6926","article-title":"Zero-shot aerial object detection with visual description regularization","volume":"vol. 38","author":"Zang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109404_bib0037","doi-asserted-by":"crossref","first-page":"5155","DOI":"10.1109\/TMM.2022.3188401","article-title":"Deep texton-coherence network for camouflaged object detection","volume":"25","author":"Zhai","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109404_bib0038","article-title":"CODdiff: Prior leading diffusion model for camouflage object detection","volume":"26","author":"Zhang","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109404_bib0039","doi-asserted-by":"crossref","first-page":"52296","DOI":"10.52202\/079017-1658","article-title":"E2E-MFD: Towards end-to-end synchronous multi-modal fusion detection","volume":"37","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109404_bib0040","article-title":"SuperYOLO: Super resolution assisted object detection in multimodal remote sensing imagery","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0041","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"410","article-title":"Scale optimization using evolutionary reinforcement learning for object detection on drone imagery","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109404_bib0042","series-title":"ACM international conference on multimedia","first-page":"5323","article-title":"PreyNet: Preying on camouflaged objects","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109404_bib0043","article-title":"DTNet: A specialized dual-tuning network for infrared vehicle detection in aerial images","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"5407616","key":"10.1016\/j.neunet.2026.109404_bib0044","first-page":"1","article-title":"C2DFF-Net For object detection in multimodal remote sensing images","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0045","first-page":"1","article-title":"FFCA-YOLO for small object detection in remote sensing images","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109404_bib0046","series-title":"European conference on computer vision","first-page":"181","article-title":"FocusDiffuser: Perceiving local disparities for camouflaged object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109404_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125826","article-title":"Differential multimodal fusion algorithm for remote sensing object detection through multi-branch feature extraction","volume":"265","author":"Zhao","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109404_bib0048","article-title":"Efficient multispectral object detection with attentive feature aggregation leveraging zero-shot implicit illumination guidance","volume":"118","author":"Zhongxia","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109404_bib0049","unstructured":"Zhou, M., & (2024). DMM: Disparity-guided multispectral mamba for oriented object detection in remote sensing. arXiv preprint arXiv: 2407.08132."},{"key":"10.1016\/j.neunet.2026.109404_bib0050","series-title":"AAAI conference on artificial intelligence","first-page":"3599","article-title":"Inferring camouflaged objects by texture-aware interactive guidance network","volume":"vol. 35","author":"Zhu","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008622?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008622?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:14:23Z","timestamp":1790108063000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":50,"alternative-id":["S0893608026008622"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109404","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-modality fusion with local and global semantic feature correlation for weakly distinguishable object detection in aerial visible and infrared images","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109404","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":"109404"}}