{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:03:22Z","timestamp":1748059402287,"version":"3.41.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Department Of Science & Technology (DST) under the Cognitive Science Research Initiative","award":["DST\/CSRI\/2018\/234","DST\/CSRI\/2018\/234"],"award-info":[{"award-number":["DST\/CSRI\/2018\/234","DST\/CSRI\/2018\/234"]}]},{"name":"Department Of Science & Technology (DST) under the Cognitive Science Research Initiative","award":["DST\/CSRI\/2018\/234","DST\/CSRI\/2018\/234"],"award-info":[{"award-number":["DST\/CSRI\/2018\/234","DST\/CSRI\/2018\/234"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10032-024-00498-3","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T08:02:44Z","timestamp":1723795364000},"page":"143-159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust page object detection network for heterogeneous document images"],"prefix":"10.1007","volume":"28","author":[{"given":"Hadia Showkat","family":"Kawoosa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Suhaib","family":"Kanroo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kapil","family":"Rana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puneet","family":"Goyal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Mondal, A., Lipps, P., Jawahar, C.: IIIT-AR-13K: a new dataset for graphical object detection in documents. In: 14th IAPR International workshop, DAS 2020, Wuhan, China., pp. 216\u2013230 (2020)","key":"498_CR1","DOI":"10.1007\/978-3-030-57058-3_16"},{"doi-asserted-by":"crossref","unstructured":"Kawoosa, H.S., Singh, M., Joshi, M.M., Goyal, P.: NCERT5K-IITRPR: a benchmark dataset for non-textual component detection in school books. In: International workshop on document analysis systems (2022)","key":"498_CR2","DOI":"10.1007\/978-3-031-06555-2_31"},{"key":"498_CR3","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1109\/TPAMI.2020.2992028","volume":"43","author":"K Davila","year":"2020","unstructured":"Davila, K., Setlur, S., Doermann, D., Kota, B.U., Govindaraju, V.: Chart mining: a survey of methods for automated chart analysis. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3799 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"498_CR4","doi-asserted-by":"publisher","first-page":"100555","DOI":"10.1016\/j.cosrev.2023.100555","volume":"48","author":"M Singh","year":"2023","unstructured":"Singh, M., Kanroo, M.S., Kawoosa, H.S., Goyal, P.: Towards accessible chart visualizations for the non-visuals: research, applications and gaps. Comput. Sci. Rev. 48, 100555 (2023)","journal-title":"Comput. Sci. Rev."},{"doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International conference on computer vision, pp. 1440\u20131448 (2015)","key":"498_CR5","DOI":"10.1109\/ICCV.2015.169"},{"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)","key":"498_CR6","DOI":"10.1109\/CVPR.2018.00644"},{"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 (2017)","key":"498_CR7","DOI":"10.1109\/ICCV.2017.322"},{"doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7464\u20137475 (2023)","key":"498_CR8","DOI":"10.1109\/CVPR52729.2023.00721"},{"unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon: ultralytics\/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations. Zenodo (2022)","key":"498_CR9"},{"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 (2021)","key":"498_CR10","DOI":"10.1109\/ICCV48922.2021.00349"},{"unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. (2018) arXiv:1804.02767","key":"498_CR11"},{"doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Scaled-yolov4: scaling cross stage partial network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13029\u201313038 (2021)","key":"498_CR12","DOI":"10.1109\/CVPR46437.2021.01283"},{"doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, D., Liu, S., Wang, Y.: Cross-domain object detection through coarse-to-fine feature adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13766\u201313775 (2020)","key":"498_CR13","DOI":"10.1109\/CVPR42600.2020.01378"},{"doi-asserted-by":"crossref","unstructured":"Agarwal, M., Mondal, A., Jawahar, C.: Cdec-net: composite deformable cascade network for table detection in document images. In: 25th International conference on pattern recognition (ICPR), pp. 9491\u20139498 (2021)","key":"498_CR14","DOI":"10.1109\/ICPR48806.2021.9411922"},{"doi-asserted-by":"crossref","unstructured":"Gilani, A., Qasim, S.R., Malik, I., Shafait, F.: Table detection using deep learning. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol. 1, pp. 771\u2013776 (2017)","key":"498_CR15","DOI":"10.1109\/ICDAR.2017.131"},{"key":"498_CR16","doi-asserted-by":"publisher","first-page":"109698","DOI":"10.1016\/j.patcog.2023.109698","volume":"142","author":"A Mondal","year":"2023","unstructured":"Mondal, A., Agarwal, M., Jawahar, C.: Dataset agnostic document object detection. Pattern Recognit. 142, 109698 (2023)","journal-title":"Pattern Recognit."},{"doi-asserted-by":"crossref","unstructured":"Kieninger, T., Dengel, A.: Table recognition and labeling using intrinsic layout features. In: International conference on advances in pattern recognition: proceedings of ICAPR\u201998, Plymouth, UK (1999)","key":"498_CR17","DOI":"10.1007\/978-1-4471-0833-7_31"},{"doi-asserted-by":"crossref","unstructured":"Kieninger, T., Dengel, A.: Applying the T-RECS table recognition system to the business letter domain. In: Proceedings of sixth international conference on document analysis and recognition, pp. 518\u2013522 (2001)","key":"498_CR18","DOI":"10.1109\/ICDAR.2001.953843"},{"doi-asserted-by":"crossref","unstructured":"Shafait, F., Smith, R.: Table detection in heterogeneous documents. In: Proceedings of the 9th IAPR international workshop on document analysis systems, pp. 65\u201372 (2010)","key":"498_CR19","DOI":"10.1145\/1815330.1815339"},{"doi-asserted-by":"crossref","unstructured":"Fang, J., Gao, L., Bai, K., Qiu, R., Tao, X., Tang, Z.: A table detection method for multipage pdf documents via visual seperators and tabular structures. In: 2011 international conference on document analysis and recognition, pp. 779\u2013783 (2011)","key":"498_CR20","DOI":"10.1109\/ICDAR.2011.304"},{"doi-asserted-by":"crossref","unstructured":"Gatos, B., Danatsas, D., Pratikakis, I., Perantonis, S.J.: Automatic table detection in document images. In: Pattern recognition and data mining: third international conference on advances in pattern recognition, ICAPR 2005, Bath, UK (2005). Springer","key":"498_CR21","DOI":"10.1007\/11551188_67"},{"doi-asserted-by":"crossref","unstructured":"Naganjaneyulu, G., Sathwik, N.V., Narasimhadhan, A.: A multi clue heuristic based algorithm for table detection. In: 2016 IEEE region 10 conference (TENCON), pp. 1246\u20131249 (2016)","key":"498_CR22","DOI":"10.1109\/TENCON.2016.7848210"},{"doi-asserted-by":"crossref","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol. 1 (2017)","key":"498_CR23","DOI":"10.1109\/ICDAR.2017.192"},{"key":"498_CR24","doi-asserted-by":"publisher","first-page":"74151","DOI":"10.1109\/ACCESS.2018.2880211","volume":"6","author":"SA Siddiqui","year":"2018","unstructured":"Siddiqui, S.A., Malik, M.I., Agne, S., Dengel, A., Ahmed, S.: Decnt: deep deformable cnn for table detection. IEEE Access 6, 74151\u201374161 (2018)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Arif, S., Shafait, F.: Table detection in document images using foreground and background features. In: 2018 digital image computing: techniques and applications (DICTA), pp. 1\u20138 (2018)","key":"498_CR25","DOI":"10.1109\/DICTA.2018.8615795"},{"doi-asserted-by":"crossref","unstructured":"Saha, R., Mondal, A., Jawahar, C.: Graphical object detection in document images. In: 2019 international conference on document analysis and recognition (ICDAR), pp. 51\u201358 (2019)","key":"498_CR26","DOI":"10.1109\/ICDAR.2019.00018"},{"unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: Tablebank: table benchmark for image-based table detection and recognition. In: Proceedings of the twelfth language resources and evaluation conference, pp. 1918\u20131925 (2020)","key":"498_CR27"},{"key":"498_CR28","first-page":"1","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 Info. Process. Syst. 28, 1 (2015)","journal-title":"Adv. Neural Info. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: Cascadetabnet: An approach for end to end table detection and structure recognition from image-based documents. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 572\u2013573 (2020)","key":"498_CR29","DOI":"10.1109\/CVPRW50498.2020.00294"},{"issue":"10","key":"498_CR30","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3390\/jimaging7100214","volume":"7","author":"KA Hashmi","year":"2021","unstructured":"Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Castabdetectors: cascade network for table detection in document images with recursive feature pyramid and switchable atrous convolution. J. Imaging 7(10), 214 (2021)","journal-title":"J. Imaging"},{"doi-asserted-by":"crossref","unstructured":"Dieu, L.T., Nguyen, T.T., et al.: Parsing digitized Vietnamese paper documents. In: Computer analysis of images and patterns: 19th international conference, CAIP 2021, Virtual Event, September 28\u201330, 2021, Proceedings, Part I 19, pp. 382\u2013392 (2021)","key":"498_CR31","DOI":"10.1007\/978-3-030-89128-2_37"},{"doi-asserted-by":"crossref","unstructured":"Huang, Y., Yan, Q., Li, Y., Chen, Y., Wang, X., Gao, L., Tang, Z.: A yolo-based table detection method. In: 2019 international conference on document analysis and recognition (ICDAR), pp. 813\u2013818 (2019)","key":"498_CR32","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"498_CR33","doi-asserted-by":"publisher","first-page":"109006","DOI":"10.1016\/j.patcog.2022.109006","volume":"133","author":"C Ma","year":"2023","unstructured":"Ma, C., Lin, W., Sun, L., Huo, Q.: Robust table detection and structure recognition from heterogeneous document images. Pattern Recognit. 133, 109006 (2023)","journal-title":"Pattern Recognit."},{"doi-asserted-by":"crossref","unstructured":"Vo, N.D., Nguyen, K., Nguyen, T.V., Nguyen, K.: Ensemble of deep object detectors for page object detection. In: Proceedings of the 12th international conference on ubiquitous information Mmanagement and communication, pp. 1\u20136 (2018)","key":"498_CR34","DOI":"10.1145\/3164541.3164644"},{"issue":"20","key":"498_CR35","doi-asserted-by":"publisher","first-page":"10578","DOI":"10.3390\/app122010578","volume":"12","author":"S Sinha","year":"2022","unstructured":"Sinha, S., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Rethinking learnable proposals for graphical object detection in scanned document images. Appl. Sci. 12(20), 10578 (2022)","journal-title":"Appl. Sci."},{"doi-asserted-by":"crossref","unstructured":"Nguyen, P., Ngo, L., Truong, T., Nguyen, T.T., Vo, N.D., Nguyen, K.: Page object detection with yolof. In: 2021 8th NAFOSTED conference on information and computer science (NICS), pp. 205\u2013210 (2021)","key":"498_CR36","DOI":"10.1109\/NICS54270.2021.9701449"},{"key":"498_CR37","doi-asserted-by":"publisher","first-page":"176","DOI":"10.3390\/fi14060176","volume":"14","author":"G Kallempudi","year":"2022","unstructured":"Kallempudi, G., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Toward semi-supervised graphical object detection in document images. Future Internet 14, 176 (2022)","journal-title":"Future Internet"},{"key":"498_CR38","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s10032-023-00431-0","volume":"26","author":"TT Nguyen","year":"2023","unstructured":"Nguyen, T.T., Le, H., Nguyen, T., Vo, N.D., Nguyen, K.: A brief review of state-of-the-art object detectors on benchmark document images datasets. Int. J. Doc. Anal. Recognit. 26, 433 (2023)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"498_CR39","doi-asserted-by":"publisher","first-page":"7486","DOI":"10.3390\/app12157486","volume":"12","author":"S Naik","year":"2022","unstructured":"Naik, S., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Investigating attention mechanism for page object detection in document images. Appl. Sci. 12, 7486 (2022)","journal-title":"Appl. Sci."},{"doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: 2013 12th international ionference on document analysis and recognition, pp. 1449\u20131453 (2013). IEEE","key":"498_CR40","DOI":"10.1109\/ICDAR.2013.292"},{"doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: ICDAR 2017 competition on page object detection. In: 14th IAPR international conference on document analysis and recognition (ICDAR), pp. 1417\u20131422 (2017). IEEE","key":"498_CR41","DOI":"10.1109\/ICDAR.2017.231"},{"doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, Y., D\u00e9jean, H., Meunier: ICDAR 2019 competition on table detection and recognition (ctdar). In: 2019 international conference on document analysis and recognition (ICDAR) (2019). IEEE","key":"498_CR42","DOI":"10.1109\/ICDAR.2019.00243"},{"doi-asserted-by":"crossref","unstructured":"Jimeno\u00a0Yepes, A., Zhong, P., Burdick, D.: ICDAR 2021 competition on scientific literature parsing. In: ICDAR 2021: 16th international conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part IV 16, pp. 605\u2013617 (2021). Springer","key":"498_CR43","DOI":"10.1007\/978-3-030-86337-1_40"},{"doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, et al.: CSPnet: A new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 390\u2013391 (2020)","key":"498_CR44","DOI":"10.1109\/CVPRW50498.2020.00203"},{"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)","key":"498_CR45","DOI":"10.1109\/CVPR.2017.106"},{"doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., Yu, G., Shen, C.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 8440\u20138449 (2019)","key":"498_CR46","DOI":"10.1109\/ICCV.2019.00853"},{"doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the european conference on computer vision (ECCV), pp. 3\u201319 (2018)","key":"498_CR47","DOI":"10.1007\/978-3-030-01234-2_1"},{"unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. (2017) arXiv:1706.05587","key":"498_CR48"},{"key":"498_CR49","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52, 8574\u20138586 (2021)","journal-title":"IEEE Trans. Cybern."},{"issue":"7","key":"498_CR50","doi-asserted-by":"publisher","first-page":"6154","DOI":"10.1109\/TGRS.2020.3023928","volume":"59","author":"X Sun","year":"2021","unstructured":"Sun, X., Liu, Y., Yan, Z., Wang, P., Diao, W., Fu, K.: SRAF-net: shape robust anchor-free network for garbage dumps in remote sensing imagery. IEEE Trans. Geosci. Remote Sens. 59(7), 6154\u20136168 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13713\u201313722 (2021)","key":"498_CR51","DOI":"10.1109\/CVPR46437.2021.01350"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132\u20137141 (2018)","key":"498_CR52","DOI":"10.1109\/CVPR.2018.00745"},{"unstructured":"Liu, Y., Shao, Z., Teng, Y., Hoffmann, N.: Nam: Normalization-based attention module. (2021) arXiv:2111.12419","key":"498_CR53"},{"unstructured":"Qiao, S., Wang, H., Liu, C., Shen, W., Yuille, A.: Micro-batch training with batch-channel normalization and weight standardization. (2019) arXiv:1903.10520","key":"498_CR54"},{"doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.-C., Yuille, A.: Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10213\u201310224 (2021)","key":"498_CR55","DOI":"10.1109\/CVPR46437.2021.01008"},{"doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14454\u201314463 (2021)","key":"498_CR56","DOI":"10.1109\/CVPR46437.2021.01422"},{"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)","key":"498_CR57","DOI":"10.1109\/ICCV.2019.00615"},{"unstructured":"Vu, T., Jang, H., Pham, T.X., Yoo, C.: Cascade RPN: delving into high-quality region proposal network with adaptive convolution. Adv. Neural Info. Process. Syst. 32, 1 (2019)","key":"498_CR58"},{"doi-asserted-by":"crossref","unstructured":"Cao, Y., Chen, K., Loy, C.C., Lin, D.: Prime sample attention in object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11583\u201311591 (2020)","key":"498_CR59","DOI":"10.1109\/CVPR42600.2020.01160"},{"doi-asserted-by":"crossref","unstructured":"Kim, K., Lee, H.S.: Probabilistic anchor assignment with IOU prediction for object detection. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16, pp. 355\u2013371 (2020)","key":"498_CR60","DOI":"10.1007\/978-3-030-58595-2_22"},{"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 (2020)","key":"498_CR61","DOI":"10.1109\/CVPR42600.2020.00978"},{"unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. (2021) arXiv:2107.08430","key":"498_CR62"},{"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","key":"498_CR63"},{"unstructured":"Li, C., Li, L., Jiang, H., Weng: Yolov6: a single-stage object detection framework for industrial applications. (2022) arXiv:2209.02976","key":"498_CR64"},{"doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., Sun, J.: You only look one-level feature. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13039\u201313048 (2021)","key":"498_CR65","DOI":"10.1109\/CVPR46437.2021.01284"},{"unstructured":"Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: Retain information to enhance channel-spatial interactions. (2021) arXiv:2112.05561","key":"498_CR66"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-024-00498-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-024-00498-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-024-00498-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T10:48:05Z","timestamp":1747997285000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-024-00498-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":66,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["498"],"URL":"https:\/\/doi.org\/10.1007\/s10032-024-00498-3","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"assertion":[{"value":"9 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","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 do not have any Conflict of interest, financial or other.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}