{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:56:27Z","timestamp":1782262587900,"version":"3.54.5"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Natural Science Research Project of Anhui Educational Committee","award":["No.2024AH040065"],"award-info":[{"award-number":["No.2024AH040065"]}]},{"name":"Natural Science Research Project of Anhui Educational Committee","award":["No.2024AH040065"],"award-info":[{"award-number":["No.2024AH040065"]}]},{"name":"Natural Science Research Project of Anhui Educational Committee","award":["No.2024AH040065"],"award-info":[{"award-number":["No.2024AH040065"]}]},{"name":"Natural Science Research Project of Anhui Educational Committee","award":["No.2024AH040065"],"award-info":[{"award-number":["No.2024AH040065"]}]},{"name":"Natural Science Research Project of Anhui Educational Committee","award":["No.2024AH040065"],"award-info":[{"award-number":["No.2024AH040065"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07444-y","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T08:14:51Z","timestamp":1748938491000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Dense small object detection via multi-scale fusion and context information enhancement"],"prefix":"10.1007","volume":"81","author":[{"given":"Huaping","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,3]]},"reference":[{"issue":"3","key":"7444_CR1","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1007\/s12596-023-01445-x","volume":"53","author":"B Liu","year":"2024","unstructured":"Liu B (2024) An automated weed detection approach using deep learning and uav imagery in smart agriculture system. J Opt 53(3):2183\u20132191","journal-title":"J Opt"},{"key":"7444_CR2","doi-asserted-by":"crossref","unstructured":"Song X, Chen B, Li P, et\u00a0al (2023) Optimal proposal learning for deployable end-to-end pedestrian detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3250\u20133260","DOI":"10.1109\/CVPR52729.2023.00317"},{"key":"7444_CR3","first-page":"1","volume":"70","author":"Y Cai","year":"2021","unstructured":"Cai Y, Luan T, Gao H et al (2021) Yolov4-5d: an effective and efficient object detector for autonomous driving. IEEE Trans Instrument Measure 70:1\u201313","journal-title":"IEEE Trans Instrument Measure"},{"key":"7444_CR4","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, et\u00a0al (2016) Ssd: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"7444_CR5","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et\u00a0al (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"7444_CR6","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"7444_CR7","unstructured":"Redmon J (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"7444_CR8","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, et\u00a0al (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"7444_CR9","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"7444_CR10","unstructured":"Ren S (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497"},{"key":"7444_CR11","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"7444_CR12","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, et\u00a0al (2021) Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"7444_CR13","doi-asserted-by":"crossref","unstructured":"Yang C, Huang Z, Wang N (2022) Querydet: Cascaded sparse query for accelerating high-resolution small object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 13668\u201313677","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"7444_CR14","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.neucom.2022.03.033","volume":"489","author":"R Zhang","year":"2022","unstructured":"Zhang R, Shao Z, Huang X et al (2022) Adaptive dense pyramid network for object detection in uav imagery. Neurocomputing 489:377\u2013389","journal-title":"Neurocomputing"},{"key":"7444_CR15","doi-asserted-by":"crossref","unstructured":"Jiang L, Yuan B, Du J, et\u00a0al (2024) Mffsodnet: Multi-scale feature fusion small object detection network for uav aerial images. IEEE Transactions on Instrumentation and Measurement","DOI":"10.1109\/TIM.2024.3381272"},{"key":"7444_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7444_CR17","doi-asserted-by":"crossref","unstructured":"Yang X, Yang J, Yan J, et\u00a0al (2019) Scrdet: Towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8232\u20138241","DOI":"10.1109\/ICCV.2019.00832"},{"key":"7444_CR18","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.patrec.2023.10.028","volume":"176","author":"X Wang","year":"2023","unstructured":"Wang X, Yan Y, Sun H et al (2023) Dense-and-similar object detection in aerial images. Patt Recogn Lett 176:153\u2013159","journal-title":"Patt Recogn Lett"},{"key":"7444_CR19","doi-asserted-by":"crossref","unstructured":"Zhang J, Ding A, Li G, et\u00a0al (2023) A pyramid attention network with edge information injection for remote sensing object detection. IEEE Geoscience and Remote Sensing Letters","DOI":"10.1109\/LGRS.2023.3294395"},{"key":"7444_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104390","volume":"146","author":"M Wu","year":"2024","unstructured":"Wu M, Yun L, Wang Y et al (2024) Detection algorithm for dense small objects in high altitude image. Digital Signal Process 146:104390","journal-title":"Digital Signal Process"},{"key":"7444_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123397","volume":"248","author":"M Dang","year":"2024","unstructured":"Dang M, Liu G, Xu Q et al (2024) Multi-object behavior recognition based on object detection for dense crowds. Exp Syst Appl 248:123397","journal-title":"Exp Syst Appl"},{"key":"7444_CR22","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7444_CR23","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, et\u00a0al (2018) Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"7444_CR24","doi-asserted-by":"publisher","first-page":"103447","DOI":"10.1109\/ACCESS.2022.3205602","volume":"10","author":"EM Bakr","year":"2022","unstructured":"Bakr EM, El-Sallab A, Rashwan M (2022) Emca: efficient multiscale channel attention module. IEEE Access 10:103447\u2013103461","journal-title":"IEEE Access"},{"key":"7444_CR25","doi-asserted-by":"crossref","unstructured":"Jiang K, Liu J, Zhang W, et\u00a0al (2023) Manet: An efficient multi-dimensional attention-aggregated network for remote sensing image change detection. IEEE Transactions on Geoscience and Remote Sensing","DOI":"10.1109\/TGRS.2023.3328334"},{"key":"7444_CR26","doi-asserted-by":"crossref","unstructured":"Yang J, Wang L (2019) Feature fusion and enhancement for single shot multibox detector. In: 2019 Chinese automation congress (CAC), IEEE, pp 2766\u20132770","DOI":"10.1109\/CAC48633.2019.8996582"},{"key":"7444_CR27","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin TY, Le QV (2019) Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"7444_CR28","doi-asserted-by":"crossref","unstructured":"Liu Z, Gao G, Sun L, et\u00a0al (2020) Ipg-net: Image pyramid guidance network for small object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 1026\u20131027","DOI":"10.1109\/CVPRW50498.2020.00521"},{"key":"7444_CR29","doi-asserted-by":"crossref","unstructured":"(2023) Cca-fpn: Channel and content adaptive object detection. Journal of Visual Communication and Image Representation 95:103903","DOI":"10.1016\/j.jvcir.2023.103903"},{"key":"7444_CR30","first-page":"9616","volume-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics","author":"J Chang","year":"2024","unstructured":"Chang J, Dai H, Zheng Y (2024) Cag-fpn: Channel self-attention guided feature pyramid network for object detection. ICASSP 2024\u20132024 IEEE International Conference on Acoustics. IEEE, Speech and Signal Processing (ICASSP), pp 9616\u20139620"},{"key":"7444_CR31","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, et\u00a0al (2020) Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11534\u201311542","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"7444_CR32","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, et\u00a0al (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"7444_CR33","doi-asserted-by":"crossref","unstructured":"Zhu X, Cheng D, Zhang Z, et\u00a0al (2019) An empirical study of spatial attention mechanisms in deep networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6688\u20136697","DOI":"10.1109\/ICCV.2019.00679"},{"key":"7444_CR34","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L, et\u00a0al (2019) Ccnet: Criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"issue":"6","key":"7444_CR35","doi-asserted-by":"publisher","first-page":"6881","DOI":"10.1109\/TPAMI.2020.3047209","volume":"45","author":"Y Cao","year":"2020","unstructured":"Cao Y, Xu J, Lin S et al (2020) Global context networks. IEEE Trans Patt Anal Mach Intell 45(6):6881\u20136895","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"7444_CR36","doi-asserted-by":"crossref","unstructured":"Li Y, Hou Q, Zheng Z, et\u00a0al (2023) Large selective kernel network for remote sensing object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 16794\u201316805","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"7444_CR37","first-page":"9969","volume":"35","author":"Y Tang","year":"2022","unstructured":"Tang Y, Han K, Guo J et al (2022) Ghostnetv2: enhance cheap operation with long-range attention. Adv Neural Inf Process Syst 35:9969\u20139982","journal-title":"Adv Neural Inf Process Syst"},{"key":"7444_CR38","doi-asserted-by":"crossref","unstructured":"Cai X, Lai Q, Wang Y, Wang W, Sun Z, Yao Y (2024) Poly kernel inception network for remote sensing detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 27706\u201327716","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"7444_CR39","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, et\u00a0al (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"7444_CR40","doi-asserted-by":"crossref","unstructured":"Du D, Zhu P, Wen L, et\u00a0al (2019) Visdrone-det2019: The vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, pp 0\u20130","DOI":"10.1109\/ICCVW.2019.00030"},{"key":"7444_CR41","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88:303\u2013338","journal-title":"Int J Comput Vision"},{"key":"7444_CR42","doi-asserted-by":"crossref","unstructured":"Xia GS, Bai X, Ding J, et\u00a0al (2018) Dota: A large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3974\u20133983","DOI":"10.1109\/CVPR.2018.00418"},{"key":"7444_CR43","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, et\u00a0al (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"7444_CR44","doi-asserted-by":"crossref","unstructured":"Li Z, Peng C, Yu G, et\u00a0al (2018) Detnet: A backbone network for object detection. arXiv preprint arXiv:1804.06215","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"7444_CR45","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, et\u00a0al (2019) Fcos: Fully convolutional one-stage object detection. arxiv 2019. arXiv preprint arXiv:1904.01355","DOI":"10.1109\/ICCV.2019.00972"},{"key":"7444_CR46","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et\u00a0al (2020) End-to-end object detection with transformers. In: European conference on computer vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7444_CR47","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"7444_CR48","unstructured":"Li Z, Peng C, Yu G, et\u00a0al (2017) Light-head r-cnn: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264"},{"key":"7444_CR49","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (2023) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"7444_CR50","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 840\u2013849","DOI":"10.1109\/CVPR.2019.00093"},{"key":"7444_CR51","doi-asserted-by":"crossref","unstructured":"Chen Q, Wang Y, Yang T, et\u00a0al (2021) You only look one-level feature. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13039\u201313048","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"7444_CR52","doi-asserted-by":"crossref","unstructured":"Zhao Y, Guo X, Lu Y (2022) Semantic-aligned fusion transformer for one-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7601\u20137611","DOI":"10.1109\/CVPR52688.2022.00745"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07444-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07444-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07444-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T08:15:12Z","timestamp":1748938512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07444-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":52,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7444"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07444-y","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,3]]},"assertion":[{"value":"12 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Written informed consent for the publication of this paper was obtained from Anhui University of Science and Technology and all authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"955"}}