{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:20:04Z","timestamp":1783408804887,"version":"3.54.6"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP24K14998"],"award-info":[{"award-number":["JP24K14998"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s13735-025-00373-9","type":"journal-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T04:53:49Z","timestamp":1750568029000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Enhanced YOLOv10 for small object detection with context-aware and adaptive modules"],"prefix":"10.1007","volume":"14","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghui","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"373_CR1","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"373_CR2","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and efficient object detection. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"373_CR3","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: proceedings of the IEEE international conference on computer vision, 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"373_CR4","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: proceedings of the IEEE international conference on computer vision, 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"373_CR5","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28"},{"key":"373_CR6","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: proceedings of the IEEE international conference on computer vision, 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"issue":"3","key":"373_CR7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou Z, Chen K, Shi Z, Guo Y, Ye J (2023) Object detection in 20 years: a survey. Proc IEEE 111(3):257\u2013276","journal-title":"Proc IEEE"},{"issue":"3","key":"373_CR8","first-page":"171","volume":"9","author":"AM Hafiz","year":"2020","unstructured":"Hafiz AM, Bhat GM (2020) A survey on instance segmentation: state of the art. Int J Multimed 9(3):171\u2013189","journal-title":"Int J Multimed"},{"key":"373_CR9","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"},{"key":"373_CR10","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, Liu Y, Chen J (2024) Detrs beat yolos on real-time object detection. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"373_CR11","doi-asserted-by":"crossref","unstructured":"Cheng T, Song L, Ge Y, Liu W, Wang X, Shan Y (2024) Yolo-world: Real-time open-vocabulary object detection. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 16901\u201316911","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"373_CR12","unstructured":"Xu S, Wang X, Lv W, Chang Q, Cui C, Deng K, Wang G, Dang Q, Wei S, Du Y, Lai B (2022) PP-YOLOE: an evolved version of YOLO"},{"key":"373_CR13","doi-asserted-by":"crossref","unstructured":"Wang Z, Li C, Xu H, Zhu X, Li H (2024) Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","DOI":"10.1609\/aaai.v39i8.32885"},{"key":"373_CR14","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J, Ding G (2024) Yolov10: real-time end-to-end object detection. arXiv preprint arXiv:2405.14458"},{"key":"373_CR15","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"373_CR16","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"373_CR17","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q (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, 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"373_CR18","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 preprint arXiv:2209.02976"},{"key":"373_CR19","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (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, 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"373_CR20","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2024) Yolov9: learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"373_CR21","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision, 213\u2013229. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"373_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Advances in Neural Information Processing Systems 30"},{"key":"373_CR23","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Wei Y, Huang L, Liu W, Huang TS (CVPR) Ccnet: criss-cross attention for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019). Conference: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/ICCV.2019.00069"},{"key":"373_CR24","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/CVPR.2018.00745"},{"key":"373_CR25","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon ISK (2018) Cbam: convolutional block attention module. ECCV","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"373_CR26","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (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, 21\u201337. Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"373_CR27","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: proceedings of the IEEE\/CVF international conference on computer vision, 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"373_CR28","doi-asserted-by":"crossref","unstructured":"Xie X, Cheng G, Wang J, Yao X, Han J (2021) Oriented r-cnn for object detection. In: proceedings of the IEEE\/CVF international conference on computer vision, 3520\u20133529","DOI":"10.1109\/ICCV48922.2021.00350"},{"issue":"03","key":"373_CR29","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1109\/TPAMI.2024.3515454","volume":"47","author":"Z Li","year":"2025","unstructured":"Li Z, Wang W, Li H, Xie E, Sima C, Lu T, Yu Q, Dai J (2025) Bevformer: learning bird\u2019s-eye-view representation from lidar-camera via spatiotemporal transformers. IEEE Transactions on Pattern Analysis & Machine Intelligence 47(03):2020\u20132036","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"373_CR30","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. arxiv 2024. arXiv preprint arXiv:2403.06258","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"373_CR31","unstructured":"Zhang X, Liu C, Yang D, Song T, Ye Y, Li K, Song Y (2023) Rfaconv: Innovating spatial attention and standard convolutional operation. arXiv preprint arXiv:2304.03198"},{"key":"373_CR32","unstructured":"Zhang X, Song Y, Song T, Yang D, Ye Y, Zhou J, Zhang L (2023) Akconv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters. arxiv preprint arXiv:2311.11587"},{"key":"373_CR33","doi-asserted-by":"crossref","unstructured":"Xu W, Wan Y (2024) Ela: efficient local attention for deep convolutional neural networks. arXiv preprint arXiv:2403.01123","DOI":"10.1007\/s11554-025-01719-6"},{"issue":"2","key":"373_CR34","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s13735-023-00305-5","volume":"12","author":"Z Wen","year":"2023","unstructured":"Wen Z, Su J, Zhang Y, Li M, Gan G, Zhang S, Fan D (2023) A lightweight small object detection algorithm based on improved yolov5 for driving scenarios. International Journal of Multimedia Information Retrieval 12(2):38","journal-title":"International Journal of Multimedia Information Retrieval"},{"key":"373_CR35","doi-asserted-by":"crossref","unstructured":"Huang S, Lu Z, Cun X, Yu Y, Zhou X, Shen X (2024) Deim: detr with improved matching for fast convergence. arXiv preprint arXiv:2412.04234","DOI":"10.1109\/CVPR52734.2025.01412"},{"key":"373_CR36","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2017) Single-shot refinement neural network for object detection. CoRR","DOI":"10.1109\/CVPR.2018.00442"},{"key":"373_CR37","doi-asserted-by":"crossref","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2018) Detnet: a backbone network for object detection. CoRR","DOI":"10.1007\/978-3-030-01240-3_21"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00373-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-025-00373-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00373-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T10:50:37Z","timestamp":1758883837000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-025-00373-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["373"],"URL":"https:\/\/doi.org\/10.1007\/s13735-025-00373-9","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"6 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that the authors have no competing interests as defined by Springer, or other interests that might be perceived to influence the results and\/or discussion reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"22"}}