{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:36:02Z","timestamp":1768095362680,"version":"3.49.0"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T00:00:00Z","timestamp":1674604800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T00:00:00Z","timestamp":1674604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100017054","name":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization","doi-asserted-by":"publisher","award":["61572286"],"award-info":[{"award-number":["61572286"]}],"id":[{"id":"10.13039\/100017054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472220"],"award-info":[{"award-number":["61472220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11554-023-01280-0","type":"journal-article","created":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T14:03:13Z","timestamp":1674655393000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["DeoT: an end-to-end encoder-only Transformer object detector"],"prefix":"10.1007","volume":"20","author":[{"given":"Tonghe","family":"Ding","sequence":"first","affiliation":[]},{"given":"Kaili","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Yanjun","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9152-0209","authenticated-orcid":false,"given":"Tianping","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,25]]},"reference":[{"key":"1280_CR1","doi-asserted-by":"publisher","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 visionand pattern recognition, pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"1280_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 1440\u20131448. arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"1280_CR3","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards realtime object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1280_CR4","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. arXiv:1605.06409 (2016)"},{"key":"1280_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, C., Wang, J., Zhao, X., Wu, Y., and Lu, H.: Couplenet: coupling global structure with local parts for object detection. In: IEEE international conference on computer vision, pp. 4126\u20134134. arXiv:1708.02863 (2017)","DOI":"10.1109\/ICCV.2017.444"},{"key":"1280_CR6","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computervision, pp. 2961\u20132969 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"1280_CR7","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":"1280_CR8","doi-asserted-by":"publisher","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 conference on computer vision and pat-tern recognition, pp. 821\u2013830 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00091","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1280_CR9","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1280_CR10","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unifed, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern reco-gnition, pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"1280_CR11","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"1280_CR12","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improveme-nt. arXiv preprint. arXiv:1804.02767 (2018)"},{"key":"1280_CR13","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":"1280_CR14","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":"1280_CR15","doi-asserted-by":"publisher","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. 10778\u201310787 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1280_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S. Z.: Single-shot refinement neural network for object detection. In: IEEE conference on computer vision and pattern recognition, pp. 4203\u20134212. arXiv:1711.06897 (2018)","DOI":"10.1109\/CVPR.2018.00442"},{"key":"1280_CR17","doi-asserted-by":"publisher","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 and pattern recognition, pp. 9626\u20139635 (2020). https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1280_CR18","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271. arXiv:1904.07850 (2019)"},{"key":"1280_CR19","doi-asserted-by":"crossref","unstructured":"Liu, W., Liao, S., Ren, W., Hu, W., Yu, Y.: High-level semantic feature detection: a new perspective for pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp. 5187\u20135196 (2019)","DOI":"10.1109\/CVPR.2019.00533"},{"key":"1280_CR20","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2020","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Int. J. Comput. Vis. 128, 642\u2013656 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"1280_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhuo, J., and 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. arXiv:1901.08043 (2019)","DOI":"10.1109\/CVPR.2019.00094"},{"key":"1280_CR22","doi-asserted-by":"publisher","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: Point set representation for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9657\u20139666 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00975","DOI":"10.1109\/ICCV.2019.00975"},{"key":"1280_CR23","doi-asserted-by":"publisher","unstructured":"Kong, T., Sun, F., Liu, H., Jiang, Y., Shi, J.: Foveabox: Beyond anchor-based object detector. In: IEEE Transactions on Image Processing. 29, 7389\u20137398 (2020). https:\/\/doi,org\/https:\/\/doi.org\/10.1109\/TIP.2020.3002345","DOI":"10.1109\/TIP.2020.3002345"},{"key":"1280_CR24","unstructured":"Wang, X., Chen, K., Huang, Z., Yao, C., Liu, W.: Point linking network for object detection. arXiv:1706.03646 (2017)"},{"key":"1280_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008. arXiv:1706.03762 (2017)"},{"key":"1280_CR26","doi-asserted-by":"publisher","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. Springer, pp. 213\u2013229 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1280_CR27","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159 (2020)"},{"key":"1280_CR28","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., and Kitani, K.: Rethinking transformer-based set prediction for object detection. arXiv:2011.10881 (2020)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"1280_CR29","unstructured":"Wang, Y., Zhang, X., Yang, T., and Sun, J.: Anchor detr: query design for transformer-based object detection. arXiv:2109.07107 (2021)"},{"key":"1280_CR30","unstructured":"Yao, Z., Ai, J., Li, B., and Zhang, C.: Efficient detr: improving end-to-end object detector with dense prior. arXiv:2104.01318 (2021)"},{"key":"1280_CR31","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of detr with spatially modulated coattention. arXiv:2101.07448 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"1280_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep connolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1280_CR33","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1007\/s11554-021-01074-2","volume":"18","author":"J Ma","year":"2021","unstructured":"Ma, J., Wan, H., Wang, J., Xia, H., Bai, C.: An improved one-stage pedestrian detection method based on multi-scale attention feature extraction. J. Real Time Image Process. 18, 1965\u20131978 (2021). https:\/\/doi.org\/10.1007\/s11554-021-01074-2","journal-title":"J. Real Time Image Process."},{"key":"1280_CR34","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: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1280_CR35","doi-asserted-by":"publisher","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. 39(4), 3431\u20133440 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1280_CR36","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.1007\/s11554-021-01136-5","volume":"18","author":"Y Wei","year":"2021","unstructured":"Wei, Y., Zhu, Z., Yu, H., et al.: Aftdnet: real-time anchor-free detection network of threat objects for X-ray baggage screening. J. Real Time Image Process. 18, 1343\u20131356 (2021). https:\/\/doi.org\/10.1007\/s11554-021-01136-5","journal-title":"J. Real Time Image Process."},{"key":"1280_CR37","unstructured":"Fang, Y., Liao, B., Wang, X., Fang, J., Qi, J., Wu, R., Niu, J., Liu, W.: You only look at one sequence: rethinking transformer in vision through object detection. arXiv:2106.00666 (2021)"},{"key":"1280_CR38","unstructured":"Song, H., Sun, D., Chun, S., Jampani, V., Han, D., Heo, B., Kim, W., et al.: Vidt: an efficient and effevtive fully transformer-based object detector. arXiv:2110.03921 (2021)"},{"key":"1280_CR39","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"1280_CR40","unstructured":"Beal, J., Kin, E., Tzeng, E., Dong, H. P., and Kislyuk, D.:Toward transformer-based object detection. arXiv:2012.09958(2020)"},{"key":"1280_CR41","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/ICCV.2017.89","DOI":"10.1109\/ICCV.2017.89"},{"key":"1280_CR42","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learningfor image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778. arXiv: 1512.03385 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1280_CR43","unstructured":"Ba, J. L., Kiros, J. R., Hinton, G. E.: Layer normalization. arXiv.1607.06450 (2016)"},{"key":"1280_CR44","doi-asserted-by":"publisher","first-page":"108485","DOI":"10.1016\/j.asoc.2022.108485","volume":"118","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Feng, W., Yuan, T., Sangaiah, A.K., Wang, J.: Scstcf: spatial-channel selection and temporal regularized correlation filters for visual tracking. Appl. Soft Comput. 118, 108485 (2022). https:\/\/doi.org\/10.1016\/j.asoc.2022.108485","journal-title":"Appl. Soft Comput."},{"key":"1280_CR45","doi-asserted-by":"publisher","first-page":"107730","DOI":"10.1016\/j.compeleceng.2022.107730","volume":"98","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Sun, J., Wang, J., Li, Z., Chen, X.: An object tracking framework with recapture based on correlation filters and siamese networks. Comput. Electr. Eng. 98, 107730 (2022). https:\/\/doi.org\/10.1016\/j.compeleceng.2022.107730","journal-title":"Comput. Electr. Eng."},{"key":"1280_CR46","doi-asserted-by":"publisher","first-page":"6129","DOI":"10.1007\/s10489-021-02694-8","volume":"52","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Liu, Y., Liu, H., et al.: Distractor-aware visual tracking using hierarchical correlation filters adaptive selection. Appl Intell. 52, 6129\u20136147 (2022). https:\/\/doi.org\/10.1007\/s10489-021-02694-8","journal-title":"Appl Intell."},{"issue":"4","key":"1280_CR47","doi-asserted-by":"publisher","first-page":"317","DOI":"10.3233\/AIS-220038","volume":"14","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Zheng, Z., Xie, X., Gui, Y., Kim, G.J.: Reyolo: a traffic sign detector based on network reparameterization and features adaptive weighting. J. Ambient. Intelligence. Smart. Env. 14(4), 317\u2013334 (2022). https:\/\/doi.org\/10.3233\/AIS-220038","journal-title":"J. Ambient. Intelligence. Smart. Env."},{"key":"1280_CR48","doi-asserted-by":"publisher","first-page":"23","DOI":"10.22967\/HCIS.2022.12.023","volume":"12","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Zou, X., Kuang, L.D., Wang, J., et al.: Cctsdb 2021: a more comprehensive traffic sign detection benchmark. Human-Centric. Computing. Inform. Sci. 12, 23 (2022). https:\/\/doi.org\/10.22967\/HCIS.2022.12.023","journal-title":"Human-Centric. Computing. Inform. Sci."},{"key":"1280_CR49","doi-asserted-by":"publisher","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\/CVF conference on computer vision and pattern recognition, pp. 658\u2013666 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00075","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1280_CR50","doi-asserted-by":"publisher","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 co-mputer vision. Springer, pp. 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1280_CR51","doi-asserted-by":"publisher","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"1280_CR52","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 (2017)"},{"key":"1280_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic r-cnn: towards high quality object detection via dynamic training. arXiv:2004.06002 (2020)","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"1280_CR54","doi-asserted-by":"publisher","unstructured":"Wang, C. Y., Bochkovskiy, A., Liao, M. H.: Scaled-yolov4: scaling cross stage partial network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13024\u201313033 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01283","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"1280_CR55","doi-asserted-by":"publisher","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. 9756\u20139765 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00978","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1280_CR56","unstructured":"Chen, Y., Zhang, Z., Cao, Y., Wang, L., Lin, S., Hu, H.: Reppoints v2: verification meets regression for object detection. arXiv:2007.08508 (2020)"},{"key":"1280_CR57","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox:exceeding yolo series in 2021. arXiv:2107.08430 (2021)"},{"key":"1280_CR58","doi-asserted-by":"publisher","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: Up-detr: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1601\u20131610 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00165","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"1280_CR59","doi-asserted-by":"publisher","unstructured":"Wang, T., Yuan, L., Chen, Y., Feng, J., Yan, S.: Pnp-detr: towards efficient visual analysis with transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4641\u20134650 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00462","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"1280_CR60","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., Wang, J.: Conditional detr for fast training convergence. In: Proceedings of the IEEE international conference on computer vision. arXiv:2108.06152 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"1280_CR61","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, J., Cao, Y., Shen, Y., Tao, D.: Towards data-efficient detection transformers. arXiv:2203.09507 (2022)","DOI":"10.1007\/978-3-031-20077-9_6"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01280-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-023-01280-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01280-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T18:30:42Z","timestamp":1677522642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-023-01280-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,25]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["1280"],"URL":"https:\/\/doi.org\/10.1007\/s11554-023-01280-0","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,25]]},"assertion":[{"value":"13 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2023","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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1"}}