{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:23:35Z","timestamp":1740108215501,"version":"3.37.3"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Sichuan Science and Technology Program","award":["2023NSFSC0503"],"award-info":[{"award-number":["2023NSFSC0503"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00138-023-01481-4","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T05:01:38Z","timestamp":1699333298000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic label assignment object detection mehtod on only one feature map"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7874-6126","authenticated-orcid":false,"given":"Tingsong","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zengxi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nijing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"1481_CR1","doi-asserted-by":"crossref","unstructured":"Lin, T., Dollar, 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":"1481_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, 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"},{"key":"1481_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":"1481_CR4","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K., Dollar, 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":"1481_CR5","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":"1481_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv preprint arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1481_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Sun, J.: You only look one-level feature. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13034\u201313043 (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"1481_CR8","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. arXiv preprint arXiv:1912.02424 (2019)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1481_CR9","unstructured":"Zhu, B., Wang, J., Jiang, Z et al.: AutoAssign: differentiable label assignment for dense object detection. arXiv preprint arXIv: arXiv:2007.03496 (2020)"},{"key":"1481_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S et al: Microsoft coco: common objects in context. In: The European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1481_CR11","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results"},{"key":"1481_CR12","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results"},{"key":"1481_CR13","doi-asserted-by":"crossref","unstructured":"Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, Xiangyu, Li, J., Sun, J.: Objects365: a large-scale, high-quality dataset for object detection. In: The IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"1481_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Y., Sun, H., Liu, N., Bian, Y., Cen, J., Zhou, H.: A lightweight multi-scale context network for salient object detection in optical remote sensing images. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 238\u2013244 (2022)","DOI":"10.1109\/ICPR56361.2022.9956350"},{"key":"1481_CR15","first-page":"1","volume":"60","author":"Z Tu","year":"2022","unstructured":"Tu, Z., Wang, C., Li, C., Fan, M., Zhao, H., Luo, B.: ORSI salient object detection via multiscale joint region and boundary model. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1481_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3123984","volume":"60","author":"R Cong","year":"2022","unstructured":"Cong, R., Zhang, Y., Fang, L., Li, J., Zhao, Y., Kwong, S.: RRNet: relational reasoning network with parallel multiscale attention for salient object detection in optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1481_CR17","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1481_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L et al.: Swin transformer v2: scaling up capacity and resolution. arXiv preprint arXiv:2111.09883 (2021)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1481_CR19","unstructured":"Yuan, L., Chen, D., Chen, Y., Noel, et al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"1481_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, H., Li, F., Liu, S.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv eprints, https:\/\/doi.org\/10.48550\/arXiv.2203.03605 (2022)","DOI":"10.48550\/arXiv.2203.03605"},{"key":"1481_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1481_CR22","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":"1481_CR23","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":"1481_CR24","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, pp. 91\u201399 (2015)"},{"key":"1481_CR25","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"1481_CR26","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":"1481_CR27","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":"1481_CR28","unstructured":"Bochkovskiy, A., C Wang, Liao, H.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1481_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C., Bochkovskiy, A., Mark Liao, H.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1481_CR30","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C.: Pre-trained image processing transformer. arXiv:2012.00364 (2020)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"1481_CR31","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"1481_CR32","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A.: Training data-efficient image transformers and distillation through attention. arXiv:2012.12877 (2020)"},{"key":"1481_CR33","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D., Song, K.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1481_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In The IEEE Conference on Computer Vision and Pattern Recognition, (2019)","DOI":"10.1109\/CVPR.2019.00308"},{"key":"1481_CR35","unstructured":"Yang, T., Zhang, X., Li, Z., Zhang, W., Sun, J.: Metaanchor: learning to detect objects with customized anchors. In: Advances in Neural Information Processing Systems (2018)"},{"key":"1481_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00093"},{"key":"1481_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, F., Shen, Z., Savvides, M.: Soft anchor-point object detection. arXiv preprint arXiv:1911.12448 (2019)","DOI":"10.1007\/978-3-030-58545-7_6"},{"key":"1481_CR38","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: Freeanchor: learning to match anchors for visual object detection. In: Advances in Neural Information Processing Systems (2019)"},{"key":"1481_CR39","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. arXiv preprint arXiv:1912.05086 (2019)","DOI":"10.1109\/CVPR42600.2020.01060"},{"key":"1481_CR40","doi-asserted-by":"crossref","unstructured":"Kim, K., Lee, H.S.: Probabilistic anchor assignment with IOU prediction for object detection. arXiv preprint arXiv:2007.08103 (2020)","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"1481_CR41","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":"1481_CR42","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":"1481_CR43","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: The IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1481_CR44","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Dollar, P.: Rethinking imagenet pre-training. In: The IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"1481_CR45","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. arXiv Preprint arXiv:2103.07461 (2021)"},{"key":"1481_CR46","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., Shen, C.: Twins: Revisiting spatial attention design in vision transformers. arXiv preprint arXiv:2104.13840 (2021)"},{"key":"1481_CR47","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1481_CR48","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dndetr: accelerate DETR training by introducing query denoising. arXiv preprint arXiv:2203.01305 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"1481_CR49","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021, pp. 11627\u201311636 (2021)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"1481_CR50","doi-asserted-by":"crossref","unstructured":"Qiu, H., Ma, Y., Li, Z., Liu, S., Sun, J.: Borderdet: border feature for dense object detection. In: European Conference on Computer Vision, Springer, pp. 549\u2013564 (2020)","DOI":"10.1007\/978-3-030-58452-8_32"},{"key":"1481_CR51","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":"1481_CR52","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., Zhang, L.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7373\u20137382 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"1481_CR53","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1481_CR54","unstructured":"Yang, J., Li, C., Gao, J.: Focal modulation networks. arXiv preprint, arXiv: 2203.11926 (2022)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01481-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01481-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01481-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T09:03:18Z","timestamp":1706000598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01481-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1481"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01481-4","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2023,11,7]]},"assertion":[{"value":"26 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"2"}}