{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T12:06:07Z","timestamp":1768651567435,"version":"3.49.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["61471250"],"award-info":[{"award-number":["61471250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"national key project","award":["GJXM92579"],"award-info":[{"award-number":["GJXM92579"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s00371-021-02357-2","type":"journal-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T11:03:23Z","timestamp":1641812603000},"page":"569-580","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A fully convolutional anchor-free object detector"],"prefix":"10.1007","volume":"39","author":[{"given":"Taoshan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhikuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,10]]},"reference":[{"issue":"6","key":"2357_CR1","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s00371-019-01733-3","volume":"36","author":"J Cai","year":"2020","unstructured":"Cai, J., Hu, J.: 3d rans: 3d residual attention networks for action recognition. Visual Comput. 36(6), 1261\u20131270 (2020)","journal-title":"Visual Comput."},{"key":"2357_CR2","doi-asserted-by":"crossref","unstructured":"Cao, J., Cholakkal, H., Anwer, R.\u00a0M., Khan, F.\u00a0S., Pang, Y., Shao, L.: D2det: Towards high quality object detection and instance segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11485\u201311494 (2020)","DOI":"10.1109\/CVPR42600.2020.01150"},{"key":"2357_CR3","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C.\u00a0C., Lin, D.: MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"2357_CR4","doi-asserted-by":"crossref","unstructured":"Chen, W., Huang, H., Peng, S., Zhou, C., Zhang, C.: Yolo-face: a real-time face detector. Visual Comput., pp. 1\u20139 (2020)","DOI":"10.1007\/s00371-020-01831-7"},{"issue":"2","key":"2357_CR5","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s00371-017-1468-4","volume":"35","author":"Y Chu","year":"2019","unstructured":"Chu, Y., Zhao, L., Ahmad, T.: Multiple feature subspaces analysis for single sample per person face recognition. Visual Comput. 35(2), 239\u2013256 (2019)","journal-title":"Visual Comput."},{"key":"2357_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2357_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2357_CR8","doi-asserted-by":"crossref","unstructured":"Du, Q., Da, F.: Block dictionary learning-driven convolutional neural networks for fewshot face recognition. Visual Comput., pp. 1\u201310 (2020)","DOI":"10.1007\/s00371-020-01802-y"},{"key":"2357_CR9","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE International Conference on Computer Vision, pp. 6569\u20136578, (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"issue":"2","key":"2357_CR10","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. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"2357_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q.\u00a0V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2357_CR12","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":"2357_CR13","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":"2357_CR14","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":"2357_CR15","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.\u00a0Q.: Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"issue":"7","key":"2357_CR16","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1007\/s00371-019-01734-2","volume":"36","author":"K Huang","year":"2020","unstructured":"Huang, K., Gao, S.: Image saliency detection via multi-scale iterative cnn. Visual Comput. 36(7), 1355\u20131367 (2020)","journal-title":"Visual Comput."},{"key":"2357_CR17","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: Unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)"},{"key":"2357_CR18","doi-asserted-by":"crossref","unstructured":"Junos, M.\u00a0H., Khairuddin, A.\u00a0S.\u00a0M., Thannirmalai, S., Dahari, M.: Automatic detection of oil palm fruits from uav images using an improved yolo model. Visual Comput., pp. 1\u201315 (2021)","DOI":"10.1049\/ipr2.12181"},{"issue":"6","key":"2357_CR19","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"2357_CR20","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"},{"issue":"1","key":"2357_CR21","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s00371-017-1453-y","volume":"35","author":"J Lim","year":"2019","unstructured":"Lim, J., Lee, K.: 3d object recognition using scale-invariant features. Visual Comput. 35(1), 71\u201384 (2019)","journal-title":"Visual Comput."},{"key":"2357_CR22","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":"2357_CR23","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":"2357_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.\u00a0L.: 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":"2357_CR25","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:1911.09516 (2019)"},{"key":"2357_CR26","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":"2357_CR27","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.\u00a0C.: 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":"2357_CR28","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2357_CR29","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In European conference on computer vision, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2357_CR30","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: Pytorch: An imperative style, high-performance deep learning library. In: H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d\u2019 Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"2357_CR31","unstructured":"Qualcomm\u00a0Korea, Y.: Probabilistic anchor assignment with iou prediction for object detection"},{"key":"2357_CR32","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":"2357_CR33","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":"2357_CR34","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"issue":"6","key":"2357_CR35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intel. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intel."},{"key":"2357_CR36","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2357_CR37","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: Top-down modulation for object detection. arXiv preprint arXiv:1612.06851 (2016)"},{"key":"2357_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2357_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"2357_CR40","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"2357_CR41","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.\u00a0V.: 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":"2357_CR42","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 international conference on computer vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2357_CR43","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: A simple and strong anchor-free object detector. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)","DOI":"10.1109\/TPAMI.2020.3032166"},{"issue":"2","key":"2357_CR44","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"2357_CR45","doi-asserted-by":"crossref","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et\u00a0al.: Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence (2020)","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"2357_CR46","unstructured":"Wang, T., Zhang, X., Sun, J.: Implicit feature pyramid network for object detection. arXiv preprint arXiv:2012.13563 (2020)"},{"key":"2357_CR47","doi-asserted-by":"publisher","first-page":"2876","DOI":"10.1109\/TIP.2021.3055632","volume":"30","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Hou, J., Hou, X., Chau, L.-P.: A self-training approach for point-supervised object detection and counting in crowds. IEEE Trans. Image Process. 30, 2876\u20132887 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"2357_CR48","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. Visual Comput. 37(1), 133\u2013142 (2021)","journal-title":"Visual Comput."},{"key":"2357_CR49","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2357_CR50","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: An advanced object detection network. In Proceedings of the 24th ACM international conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"issue":"4","key":"2357_CR51","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/s00371-017-1354-0","volume":"34","author":"Q Zhang","year":"2018","unstructured":"Zhang, Q., Lin, J., Li, W., Shi, Y., Cao, G.: Salient object detection via compactness and objectness cues. Visual Comput. 34(4), 473\u2013489 (2018)","journal-title":"Visual Comput."},{"key":"2357_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: Faster and better learning for bounding box regression. In AAAI, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"2357_CR53","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"2357_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 850\u2013859 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"2357_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00093"},{"key":"2357_CR56","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 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\/s00371-021-02357-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02357-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02357-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T19:24:56Z","timestamp":1675797896000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02357-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,10]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["2357"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02357-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,10]]},"assertion":[{"value":"9 November 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 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":"The authors have no other conflicts of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}