{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:42:59Z","timestamp":1781592179659,"version":"3.54.5"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Tianshan Talent Training Program","award":["2023TSYCLJ0023"],"award-info":[{"award-number":["2023TSYCLJ0023"]}]},{"name":"Tianshan Talent Training Program","award":["2023TSYCLJ0023"],"award-info":[{"award-number":["2023TSYCLJ0023"]}]},{"name":"Tianshan Talent Training Program","award":["2023TSYCLJ0023"],"award-info":[{"award-number":["2023TSYCLJ0023"]}]},{"name":"Tianshan Talent Training Program","award":["2023TSYCLJ0023"],"award-info":[{"award-number":["2023TSYCLJ0023"]}]},{"name":"Xinjiang Uygur Autonomous Region","award":["2023D01C176"],"award-info":[{"award-number":["2023D01C176"]}]},{"name":"Xinjiang Uygur Autonomous Region","award":["2023D01C176"],"award-info":[{"award-number":["2023D01C176"]}]},{"name":"Xinjiang Uygur Autonomous Region","award":["2023D01C176"],"award-info":[{"award-number":["2023D01C176"]}]},{"name":"Xinjiang Uygur Autonomous Region Universities Fundamental Research Funds Scientific Research Project","award":["XJEDU2022P018"],"award-info":[{"award-number":["XJEDU2022P018"]}]},{"name":"Xinjiang Uygur Autonomous Region Universities Fundamental Research Funds Scientific Research Project","award":["XJEDU2022P018"],"award-info":[{"award-number":["XJEDU2022P018"]}]},{"name":"Major science and technology programs in the autonomous region","award":["2023A03001"],"award-info":[{"award-number":["2023A03001"]}]},{"name":"Major science and technology programs in the autonomous region","award":["2023A03001"],"award-info":[{"award-number":["2023A03001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00530-024-01447-0","type":"journal-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T10:02:36Z","timestamp":1723543356000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["PS-YOLO: a small object detector based on efficient convolution and multi-scale feature fusion"],"prefix":"10.1007","volume":"30","author":[{"given":"Shifeng","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengwei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,13]]},"reference":[{"key":"1447_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021)","journal-title":"Expert Syst. Appl."},{"key":"1447_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119960","volume":"224","author":"L Wen","year":"2023","unstructured":"Wen, L., Cheng, Y., Fang, Y., Li, X.: A comprehensive survey of oriented object detection in remote sensing images. Expert Syst. Appl. 224, 119960 (2023)","journal-title":"Expert Syst. Appl."},{"key":"1447_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1447_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: IEEE ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1447_CR5","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"2","key":"1447_CR6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1109\/LGRS.2018.2872355","volume":"16","author":"C Wang","year":"2018","unstructured":"Wang, C., Bai, X., Wang, S., Zhou, J., Ren, P.: Multiscale visual attention networks for object detection in vhr remote sensing images. IEEE Geosci. Remote Sens. Lett. 16(2), 310\u2013314 (2018)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"9","key":"1447_CR7","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/rs12091432","volume":"12","author":"J Rabbi","year":"2020","unstructured":"Rabbi, J., Ray, N., Schubert, M., Chowdhury, S., Chao, D.: Small-object detection in remote sensing images with end-to-end edge-enhanced gan and object detector network. Remote Sens. 12(9), 1432 (2020)","journal-title":"Remote Sens."},{"key":"1447_CR8","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: ECCV (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1447_CR9","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1447_CR10","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement (2018). arXiv:1804.02767"},{"key":"1447_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1447_CR12","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolo by ultralytics (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"1447_CR13","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"1447_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107931","volume":"132","author":"K Tong","year":"2024","unstructured":"Tong, K., Wu, Y.: Small object detection using deep feature learning and feature fusion network. Eng. Appl. Artif. Intell. 132, 107931 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1447_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105103","volume":"156","author":"S Kim","year":"2023","unstructured":"Kim, S., Hong, S.H., Kim, H., Lee, M., Hwang, S.: Small object detection (sod) system for comprehensive construction site safety monitoring. Autom. Constr. 156, 105103 (2023)","journal-title":"Autom. Constr."},{"key":"1447_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108490","volume":"105","author":"S-J Ji","year":"2023","unstructured":"Ji, S.-J., Ling, Q.-H., Han, F.: An improved algorithm for small object detection based on yolo v4 and multi-scale contextual information. Comput. Electr. Eng. 105, 108490 (2023)","journal-title":"Comput. Electr. Eng."},{"key":"1447_CR17","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"1447_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1447_CR19","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: Up-detr: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"1447_CR20","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"1447_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: Biformer: vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10323\u201310333 (2023)","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"1447_CR22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.neucom.2023.01.055","volume":"525","author":"S Xu","year":"2023","unstructured":"Xu, S., Gu, J., Hua, Y., Liu, Y.: Dktnet: dual-key transformer network for small object detection. Neurocomputing 525, 29\u201341 (2023)","journal-title":"Neurocomputing"},{"issue":"12","key":"1447_CR23","doi-asserted-by":"publisher","first-page":"15949","DOI":"10.1109\/TPAMI.2023.3311447","volume":"45","author":"J Gao","year":"2023","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15949\u201315963 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3311447","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1447_CR24","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1109\/TCSVT.2021.3075470","volume":"32","author":"J Gao","year":"2022","unstructured":"Gao, J., Xu, C.: Learning video moment retrieval without a single annotated video. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1646\u20131657 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3075470","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"1447_CR25","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2021","unstructured":"Gao, J., Zhang, T., Xu, C.: Learning to model relationships for zero-shot video classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3476\u20133491 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2985708","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1447_CR26","doi-asserted-by":"publisher","first-page":"5410","DOI":"10.1109\/TMM.2023.3333206","volume":"26","author":"Y Hu","year":"2024","unstructured":"Hu, Y., Gao, J., Dong, J., Fan, B., Liu, H.: Exploring rich semantics for open-set action recognition. IEEE Trans. Multimed. 26, 5410\u20135421 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3333206","journal-title":"IEEE Trans. Multimed."},{"key":"1447_CR27","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolo by ultralytics (2022). https:\/\/github.com\/ultralytics\/yolov5"},{"key":"1447_CR28","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: a single-stage object detection framework for industrial applications (2022). arXiv:2209.02976"},{"key":"1447_CR29","unstructured":"Yang, Z., Guan, Q., Zhao, K., Yang, J., Xu, X., Long, H., Tang, Y.: Multi-branch auxiliary fusion yolo with re-parameterization heterogeneous convolutional for accurate object detection (2024). arXiv:2407.04381"},{"key":"1447_CR30","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: Yolo-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16901\u201316911 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"1447_CR31","doi-asserted-by":"crossref","unstructured":"Wang, M., Sun, H., Shi, J., Liu, X., Cao, X., Zhang, L., Zhang, B.: Q-yolo: efficient inference for real-time object detection. In: Asian Conference on Pattern Recognition, pp. 307\u2013321 (2023). Springer","DOI":"10.1007\/978-3-031-47665-5_25"},{"key":"1447_CR32","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1447_CR33","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.-Y.: Dino: detr with improved denoising anchor boxes for end-to-end object detection (2022). arXiv:2203.03605"},{"key":"1447_CR34","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: IEEE CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1447_CR35","unstructured":"Tan, Z., Wang, J., Sun, X., Lin, M., Li, H., et al.: Giraffedet: a heavy-neck paradigm for object detection. In: ICLR (2021)"},{"key":"1447_CR36","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.-h., He, H., Zhuo, W., Wen, S., Lee, C.-H., Chan, S.-H.G.: Run, don\u2019t walk: chasing higher flops for faster neural networks. In: IEEE CVPR, pp. 12021\u201312031 (2023)","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"1447_CR37","doi-asserted-by":"crossref","unstructured":"Nascimento, M.G.d., Fawcett, R., Prisacariu, V.A.: Dsconv: efficient convolution operator. In: IEEE CVPR (2019)","DOI":"10.1109\/ICCV.2019.00525"},{"key":"1447_CR38","doi-asserted-by":"crossref","unstructured":"Cao, J., Li, Y., Sun, M., Chen, Y., Lischinski, D., Cohen-Or, D., Chen, B., Tu, C.: Do-conv: depthwise over-parameterized convolutional layer. In: IEEE TIP, vol. 31 (2022)","DOI":"10.1109\/TIP.2022.3175432"},{"key":"1447_CR39","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y., et al.: Visdrone-det2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)"},{"key":"1447_CR40","doi-asserted-by":"crossref","unstructured":"Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1257\u20131265 (2020)","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"1447_CR41","unstructured":"Everingham, M.: The pascal visual object classes challenge 2007 (2009). http:\/\/www.Pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.Html"},{"issue":"5","key":"1447_CR42","first-page":"2","volume":"8","author":"M Everingham","year":"2011","unstructured":"Everingham, M., Winn, J.: The pascal visual object classes challenge 2012 (voc2012) development kit. pattern analysis, statistical modelling and computational learning. Tech. Rep. 8(5), 2\u20135 (2011)","journal-title":"Tech. Rep."},{"key":"1447_CR43","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: Yolov10: real-time end-to-end object detection (2024). arXiv:2405.14458"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01447-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01447-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01447-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T18:07:18Z","timestamp":1730138838000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01447-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,13]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1447"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01447-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,13]]},"assertion":[{"value":"25 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"241"}}