{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:40:59Z","timestamp":1780638059846,"version":"3.54.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T00:00:00Z","timestamp":1656892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T00:00:00Z","timestamp":1656892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s00371-022-02589-w","type":"journal-article","created":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T15:02:56Z","timestamp":1656946976000},"page":"4267-4277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Multi-level feature fusion pyramid network for object detection"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1203-1213","authenticated-orcid":false,"given":"Zebin","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangcan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,4]]},"reference":[{"key":"2589_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"2589_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2589_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2589_CR4","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et\u00a0al.: Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"issue":"4","key":"2589_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"2589_CR6","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/s00371-020-01831-7","volume":"37","author":"W Chen","year":"2021","unstructured":"Chen, W., Huang, H., Peng, S., Zhou, C., Zhang, C.: Yolo-face: a real-time face detector. Vis. Comput. 37(4), 805\u2013813 (2021)","journal-title":"Vis. Comput."},{"issue":"2","key":"2589_CR7","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, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"2589_CR8","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2589_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"2589_CR10","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":"2589_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"2589_CR12","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2589_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2589_CR14","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2589_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6054\u20136063 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2589_CR16","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2589_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2589_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: European conference on computer vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2589_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2589_CR20","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: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2589_CR21","doi-asserted-by":"crossref","unstructured":"Masi, I., Wu, Y., Hassner, T., Natarajan, P.: Deep face recognition: A survey. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 471\u2013478. IEEE (2018)","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"key":"2589_CR22","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: Towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"2589_CR23","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8026\u20138037 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2589_CR24","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2589_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"2589_CR26","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"2589_CR27","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2589_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2589_CR29","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection snip. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578\u20133587 (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"issue":"1","key":"2589_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0212-5","volume":"6","author":"G Sreenu","year":"2019","unstructured":"Sreenu, G., Durai, M.S.: Intelligent video surveillance: a review through deep learning techniques for crowd analysis. J. Big Data 6(1), 1\u201327 (2019)","journal-title":"J. Big Data"},{"key":"2589_CR31","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2589_CR32","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2589_CR33","doi-asserted-by":"crossref","unstructured":"Tiwari, A.S., Gupta, P., Jain, A., Panjwani, H.V., Malathi, G.: Face recognition with mask using mtcnn and facenet. In: Artificial Intelligence and Technologies, pp. 103\u2013109. Springer (2022)","DOI":"10.1007\/978-981-16-6448-9_12"},{"issue":"1","key":"2589_CR34","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s00371-019-01787-3","volume":"37","author":"L Wei","year":"2021","unstructured":"Wei, L., Cui, W., Hu, Z., Sun, H., Hou, S.: A single-shot multi-level feature reused neural network for object detection. Vis. Comput. 37(1), 133\u2013142 (2021)","journal-title":"Vis. Comput."},{"key":"2589_CR35","doi-asserted-by":"crossref","unstructured":"Yin, X., Tai, Y., Huang, Y., Liu, X.: Fan: Feature adaptation network for surveillance face recognition and normalization. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69532-3_19"},{"key":"2589_CR36","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"2589_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, T., Li, Z., Sun, Z., Zhu, L.: A fully convolutional anchor-free object detector. Vis. Comput., 1\u201312 (2022)","DOI":"10.1007\/s00371-021-02357-2"},{"key":"2589_CR38","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"2589_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02589-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02589-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02589-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:10:54Z","timestamp":1727525454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02589-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,4]]},"references-count":39,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["2589"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02589-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,4]]},"assertion":[{"value":"6 June 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}