{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:58:19Z","timestamp":1773511099022,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T00:00:00Z","timestamp":1662163200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T00:00:00Z","timestamp":1662163200000},"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":["SIViP"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11760-022-02342-9","type":"journal-article","created":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T13:31:37Z","timestamp":1662211897000},"page":"1345-1353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-task feature-aligned head in one-stage object detection"],"prefix":"10.1007","volume":"17","author":[{"given":"Zeting","family":"Liu","sequence":"first","affiliation":[]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Yuantao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Zilu","family":"Peng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,3]]},"reference":[{"key":"2342_CR1","unstructured":"Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey (2019). arXiv:1905.05055"},{"issue":"11","key":"2342_CR2","doi-asserted-by":"publisher","first-page":"3782","DOI":"10.1109\/TPAMI.2020.2991457","volume":"43","author":"K Chen","year":"2020","unstructured":"Chen, K., Lin, W., Li, J., See, J., Wang, J., Zou, J.: Ap-loss for accurate one-stage object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3782\u20133798 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2342_CR3","doi-asserted-by":"publisher","first-page":"6917","DOI":"10.1109\/TIP.2021.3099733","volume":"30","author":"ZM Chen","year":"2021","unstructured":"Chen, Z.M., Jin, X., Zhao, B.R., Zhang, X., Guo, Y.: HCE: hierarchical context embedding for region-based object detection. IEEE Trans. Image Process. 30, 6917\u20136929 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2342_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2342_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9300\u20139308 (2019)","DOI":"10.1109\/CVPR.2019.00953"},{"key":"2342_CR6","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1007\/s13042-022-01514-w","volume":"13","author":"B Fan","year":"2022","unstructured":"Fan, B., Shao, M., Li, Y., Li, C.: Global contextual attention for pure regression object detection. Int. J. Mach. Learn. Cybern. 13, 2189\u20132197 (2022)","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"2342_CR7","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/s11760-021-02010-4","volume":"16","author":"Y Li","year":"2022","unstructured":"Li, Y., Shao, M., Fan, B., Zhang, W.: Multi-scale global context feature pyramid network for object detector. Signal Image Video Process 16, 705\u2013713 (2022)","journal-title":"Signal Image Video Process"},{"key":"2342_CR8","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42, 386\u2013397 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2342_CR9","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318\u2013327 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2342_CR10","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., Shi, J.: Foveabox: Beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389\u20137398 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"2342_CR11","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.3390\/rs13112208","volume":"13","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Pan, Z., Hu, Y., Ding, C.: CPS-Det: an anchor-free based rotation detector for ship detection. Remote Sens. 13(11), 2208 (2021)","journal-title":"Remote Sens."},{"key":"2342_CR12","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: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2342_CR13","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J: Deformable detr: deformable transformers for end-to-end object detection (2021). arXiv:2010.04159"},{"key":"2342_CR14","doi-asserted-by":"crossref","unstructured":"Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S.Z., Zou, X.: Selective refinement network for high performance face detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8231\u20138238 (2019)","DOI":"10.1609\/aaai.v33i01.33018231"},{"key":"2342_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2960\u20132969 (2019)","DOI":"10.1109\/CVPR.2019.00308"},{"key":"2342_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.: Single-shot refinement neural network for object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4203\u20134212 (2018)","DOI":"10.1109\/CVPR.2018.00442"},{"key":"2342_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: an iou-aware dense object detector. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8510\u20138519 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"2342_CR18","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: point set representation for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9656\u20139665 (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"2342_CR19","unstructured":"Yang, Y., Li, M., Meng, B., Ren, J., Sun, D., Huang, Z.: Rethinking the aligned and misaligned features in one-stage object detection (2021). arXiv:2108.12176"},{"key":"2342_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103911","volume":"97","author":"S Wu","year":"2020","unstructured":"Wu, S., Li, X., Wang, X.: Iou-aware single-stage object detector for accurate localization. Image Vis. Comput. 97, 103911 (2020)","journal-title":"Image Vis. Comput."},{"key":"2342_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: Proceedings of the European conference on computer vision (ECCV), pp. 784\u2013799 (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"2342_CR22","doi-asserted-by":"crossref","unstructured":"Kim, K., Lee, H.S.: Probabilistic anchor assignment with iou prediction for object detection. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"2342_CR23","doi-asserted-by":"publisher","first-page":"3092","DOI":"10.1109\/TIP.2019.2957850","volume":"29","author":"Y Li","year":"2020","unstructured":"Li, Y., Wang, S.: Har-net: joint learning of hybrid attention for single-stage object detection. IEEE Trans. Image Process. 29, 3092\u20133103 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"2342_CR24","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural. Inf. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2342_CR25","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"2342_CR26","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss v2: learning reliable localization quality estimation for dense object detection. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11627\u201311636 (2021)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"2342_CR27","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"},{"key":"2342_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9756\u20139765 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"2342_CR29","doi-asserted-by":"crossref","unstructured":"Rezatofighi, S.H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2342_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2342_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2342_CR32","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, RB., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2342_CR33","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, LJ., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2342_CR34","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 (2019). arXiv:1906.07155"},{"key":"2342_CR35","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.B., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., He, K.: Accurate, large minibatch SGD: training imagenet in 1 hour (2017). arXiv:1706.02677"},{"key":"2342_CR36","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, Z., Zhu, C., Xiong, C., Socher, R., Davis, L.S.: Learning from noisy anchors for one-stage object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10585\u201310594 (2020)","DOI":"10.1109\/CVPR42600.2020.01060"},{"key":"2342_CR37","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: Freeanchor: learning to match anchors for visual object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)"},{"key":"2342_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, F., Shen, Z., Savvides, M.: Soft anchor-point object detection. In: European Conference on Computer Vision, pp. 91\u2013107. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_6"},{"key":"2342_CR39","doi-asserted-by":"crossref","unstructured":"Ke, W., Zhang, T., Huang, Z., Ye, Q., Liu, J., Huang, D.: Multiple anchor learning for visual object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10203\u201310212 (2020)","DOI":"10.1109\/CVPR42600.2020.01022"},{"key":"2342_CR40","unstructured":"Zhu, B., Wang, J., Jiang, Z., Zong, F., Liu, S., Li, Z., Sun, J.: Autoassign: differentiable label assignment for dense object detection (2020). arXiv:2007.03496"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02342-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-022-02342-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02342-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T05:21:33Z","timestamp":1682313693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-022-02342-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,3]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["2342"],"URL":"https:\/\/doi.org\/10.1007\/s11760-022-02342-9","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,3]]},"assertion":[{"value":"19 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2022","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}