{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:06:33Z","timestamp":1785603993761,"version":"3.56.0"},"reference-count":52,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:00:00Z","timestamp":1751673600000},"content-version":"vor","delay-in-days":185,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32471866"],"award-info":[{"award-number":["32471866"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018530","name":"Major Science and Technology Projects in Anhui Province","doi-asserted-by":"publisher","award":["202203a07020017"],"award-info":[{"award-number":["202203a07020017"]}],"id":[{"id":"10.13039\/501100018530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Vanilla Transformers focus on semantic relevance between mid\u2010 to high\u2010level features and are not good at extracting smoke features, as they overlook subtle changes in low\u2010level features like color, transparency, and texture, which are essential for smoke recognition. To address this, we propose the cross contrast patch embedding (CCPE) module based on the Swin Transformer. This module leverages multiscale spatial contrast information in both vertical and horizontal directions to enhance the network\u2019s discrimination of underlying details. By combining cross contrast with the transformer, we exploit the advantages of the transformer in the global receptive field and context modeling while compensating for its inability to capture very low\u2010level details, resulting in a more powerful backbone network tailored for smoke recognition tasks. In addition, we introduce the separable negative sampling mechanism (SNSM) to address supervision signal confusion during training and release the SKLFS\u2010WildFire test dataset, the largest real\u2010world wildfire test set to date, for systematic evaluation. Extensive testing and evaluation on the benchmark dataset FIgLib and the SKLFS\u2010WildFire test dataset show significant performance improvements of the proposed method over baseline detection models.<\/jats:p>","DOI":"10.1155\/int\/1610145","type":"journal-article","created":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T03:20:07Z","timestamp":1751685607000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Wildfire Smoke Detection System: Model Architecture, Training Mechanism, and Dataset"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5190-7792","authenticated-orcid":false,"given":"Chong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4163-6024","authenticated-orcid":false,"given":"Chen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9901-0716","authenticated-orcid":false,"given":"Adeel","family":"Akram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7987-4883","authenticated-orcid":false,"given":"Zhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7236-3981","authenticated-orcid":false,"given":"Zhilin","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8784-8674","authenticated-orcid":false,"given":"Qixing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,7,5]]},"reference":[{"key":"e_1_2_13_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.01.013"},{"key":"e_1_2_13_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.10.019"},{"key":"e_1_2_13_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/f13081332"},{"key":"e_1_2_13_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2018.2830099"},{"key":"e_1_2_13_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2929009"},{"key":"e_1_2_13_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/f14020361"},{"key":"e_1_2_13_7_2","doi-asserted-by":"crossref","unstructured":"KhudayberdievO. ZhangJ. ElkhalilA. andBaldeL. Fire Detection Approach Based on Vision Transformer International Conference on Adaptive and Intelligent Systems April 2022 41\u201353 https:\/\/doi.org\/10.1007\/978-3-031-06794-5_4.","DOI":"10.1007\/978-3-031-06794-5_4"},{"key":"e_1_2_13_8_2","doi-asserted-by":"crossref","unstructured":"LiuZ. LinY. CaoY.et al. Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows IEEE International Conference on Computer Vision April 2021 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_13_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02728-3"},{"key":"e_1_2_13_10_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep Residual Learning for Image Recognition IEEE Conference on Computer Vision and Pattern Recognition May 2016 770\u2013778 https:\/\/doi.org\/10.1109\/cvpr.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_13_11_2","article-title":"Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications","author":"Howard A. G.","year":"2017","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_2_13_12_2","doi-asserted-by":"crossref","unstructured":"LiuZ. MaoH. WuC. FeichtenhoferC. DarrellT. andXieS. A Convnet for the 2020s IEEE Conference on Computer Vision and Pattern Recognition July 2022 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_2_13_13_2","doi-asserted-by":"crossref","unstructured":"ShrivastavaA. GuptaA. andGirshickR. Training Region-Based Object Detectors with Online Hard Example Mining IEEE Conference on Computer Vision and Pattern Recognition July 2016 761\u2013769.","DOI":"10.1109\/CVPR.2016.89"},{"key":"e_1_2_13_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2015.2392531"},{"key":"e_1_2_13_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs14041007"},{"key":"e_1_2_13_16_2","doi-asserted-by":"crossref","unstructured":"HuC. TangP. JinW. HeZ. andLiW. Real-time Fire Detection Based on Deep Convolutional Long-Recurrent Networks and Optical Flow Method Chinese Control Conference April 2018 9061\u20139066 https:\/\/doi.org\/10.23919\/chicc.2018.8483118 2-s2.0-85056122164.","DOI":"10.23919\/ChiCC.2018.8483118"},{"key":"e_1_2_13_17_2","doi-asserted-by":"crossref","unstructured":"WangC. XuC. AkramA. WangZ. ShanZ. andZhangQ. Wildfire Smoke Detection System: Model Architecture Training Mechanism and Dataset 2025.","DOI":"10.1155\/int\/1610145"},{"key":"e_1_2_13_18_2","doi-asserted-by":"crossref","unstructured":"ChinoD. Y. AvalhaisL. P. RodriguesJ. F. andTrainaA. J. Bowfire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis SIBGRAPI Conference on Graphics Patterns and Images May 2015 95\u2013102 https:\/\/doi.org\/10.1109\/sibgrapi.2015.19 2-s2.0-84959330819.","DOI":"10.1109\/SIBGRAPI.2015.19"},{"key":"e_1_2_13_19_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5358359"},{"key":"e_1_2_13_20_2","unstructured":"OlayemiA. Fireflame Dataset 2019."},{"key":"e_1_2_13_21_2","article-title":"Firenet: a Specialized Lightweight Fire & Smoke Detection Model for Real-Time Iot Applications","author":"Jadon A.","year":"2019","journal-title":"arXiv preprint arXiv:1905.11922"},{"key":"e_1_2_13_22_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1134496"},{"key":"e_1_2_13_23_2","doi-asserted-by":"crossref","unstructured":"WeiM. C. LinB. R. LinY. Y. ChiouG. J. andKuoW. K. Experimental Study on Effects of Light Source and Different Smoke Characteristics on Signal Intensity of Photoelectric Smoke Detectors 2021 IEEE 3rd Eurasia Conference on IOT Communication and Engineering (ECICE) June 2021 IEEE 518\u2013522.","DOI":"10.1109\/ECICE52819.2021.9645643"},{"key":"e_1_2_13_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.firesaf.2007.01.006"},{"key":"e_1_2_13_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10694-009-0110-z"},{"key":"e_1_2_13_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.firesaf.2011.03.003"},{"key":"e_1_2_13_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2016.2527340"},{"key":"e_1_2_13_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2017.2747399"},{"key":"e_1_2_13_29_2","doi-asserted-by":"publisher","DOI":"10.4316\/aece.2018.04015"},{"key":"e_1_2_13_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.083"},{"key":"e_1_2_13_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2017.12.034"},{"key":"e_1_2_13_32_2","doi-asserted-by":"crossref","unstructured":"JiaoZ. ZhangY. XinJ.et al. A Deep Learning Based Forest Fire Detection Approach Using Uav and Yolov3 International Conference on Industrial Artificial Intelligence June 2019 1\u20135 https:\/\/doi.org\/10.1109\/iciai.2019.8850815 2-s2.0-85073495472.","DOI":"10.1109\/ICIAI.2019.8850815"},{"key":"e_1_2_13_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csite.2020.100625"},{"key":"e_1_2_13_34_2","doi-asserted-by":"crossref","unstructured":"SandlerM. HowardA. ZhuM. ZhmoginovA. andChenL. C. Mobilenetv2: Inverted Residuals and Linear Bottlenecks IEEE Conference on Computer Vision and Pattern Recognition May 2018 4510\u20134520 https:\/\/doi.org\/10.1109\/cvpr.2018.00474 2-s2.0-85062799511.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_13_35_2","unstructured":"RedmonJ.andFarhadiA. Yolov3: An Incremental Improvement 2018."},{"key":"e_1_2_13_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_13_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_13_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2812835"},{"key":"e_1_2_13_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2897594"},{"key":"e_1_2_13_40_2","unstructured":"JocherG. ChaurasiaA. StokenA.et al. Yolov5 by Ultralytics 2020."},{"key":"e_1_2_13_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs15112790"},{"key":"e_1_2_13_42_2","unstructured":"TouvronH. CordM. DouzeM. MassaF. SablayrollesA. andJ\u00e9gouH. Training Data-Efficient Image Transformers & Distillation through Attention International Conference on Machine Learning October 2021 10347\u201310357."},{"key":"e_1_2_13_43_2","unstructured":"TanM.andLeQ. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks International Conference on Machine Learning November 2019 PMLR 6105\u20136114."},{"key":"e_1_2_13_44_2","unstructured":"GeZ. LiuS. WangF. LiZ. andSunJ. Yolox: Exceeding Yolo Series in 2021 2021."},{"key":"e_1_2_13_45_2","unstructured":"JocherG. ChaurasiaA. andQiuJ. Yolo by Ultralytics 2023."},{"key":"e_1_2_13_46_2","doi-asserted-by":"crossref","unstructured":"LiuS. QiL. QinH. ShiJ. andJiaJ. Path Aggregation Network for Instance Segmentation IEEE Conference on Computer Vision and Pattern Recognition March 2018 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"e_1_2_13_47_2","unstructured":"LinT. Y. Doll\u00e1rP. GirshickR. HeK. HariharanB. andBelongieS. Feature Pyramid Networks for Object Detection IEEE Conference on Computer Vision and Pattern Recognition November 2017 2117\u20132125."},{"key":"e_1_2_13_48_2","article-title":"MMDetection: Open Mmlab Detection Toolbox and Benchmark","author":"Chen K.","year":"2019","journal-title":"arXiv preprint arXiv:1906.07155"},{"key":"e_1_2_13_49_2","volume-title":"Pytorch. Programming with TensorFlow: Solution for Edge Computing Applications","author":"Imambi S.","year":"2021"},{"key":"e_1_2_13_50_2","unstructured":"BochkovskiyA. WangC. andLiaoH. M. Yolov4: Optimal Speed and Accuracy of Object Detection 2020."},{"key":"e_1_2_13_51_2","unstructured":"LinT. GoyalP. GirshickR. HeK. andDoll\u00e1rP. Focal Loss for Dense Object Detection IEEE International Conference on Computer Vision August 2017 2980\u20132988."},{"key":"e_1_2_13_52_2","doi-asserted-by":"crossref","unstructured":"SunP. ZhangR. JiangY.et al. Sparse R-Cnn: End-To-End Object Detection with Learnable Proposals IEEE Conference on Computer Vision and Pattern Recognition April 2021 14454\u201314463.","DOI":"10.1109\/CVPR46437.2021.01422"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1610145","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/1610145","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1610145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:56:52Z","timestamp":1772992612000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/1610145"}},"subtitle":[],"editor":[{"given":"Mohamadreza (Mohammad)","family":"Khosravi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/1610145"],"URL":"https:\/\/doi.org\/10.1155\/int\/1610145","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"1610145"}}