{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:14:21Z","timestamp":1776784461324,"version":"3.51.2"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00371-024-03561-6","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T16:02:21Z","timestamp":1721145741000},"page":"2709-2720","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Dual-branch dilated context convolutional for table detection transformer in the document images"],"prefix":"10.1007","volume":"41","author":[{"given":"Ying","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanghang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonzhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,16]]},"reference":[{"key":"3561_CR1","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: Dit: self-supervised pre-training for document image transformer. In: Proceedings of the 30th ACM international conference on multimedia, pp. 3530\u20133539, (2022)","DOI":"10.1145\/3503161.3547911"},{"key":"3561_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, M., Mondal, A., Jawahar, C.V.: Cdec-net: composite deformable cascade network for table detection in document images. In: 2020 25th International conference on pattern recognition (ICPR), pp. 9491\u20139498. IEEE, (2021)","DOI":"10.1109\/ICPR48806.2021.9411922"},{"key":"3561_CR3","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)","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"3561_CR4","doi-asserted-by":"crossref","unstructured":"Co\u00fcasnon, B., Lemaitre, A.: Recognition of tables and forms, (2014)","DOI":"10.1007\/978-0-85729-859-1_20"},{"key":"3561_CR5","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, pp. 2961\u20132969, (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3561_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022, (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3561_CR7","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.\u00a01, pp. 1162\u20131167. IEEE, (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"issue":"18","key":"3561_CR8","doi-asserted-by":"publisher","first-page":"8969","DOI":"10.3390\/app12188969","volume":"12","author":"M Minouei","year":"2022","unstructured":"Minouei, M., Hashmi, K.A., Soheili, M.R., Afzal, M.Z., Stricker, D.: Continual learning for table detection in document images. Appl. Sci. 12(18), 8969 (2022)","journal-title":"Appl. Sci."},{"issue":"20","key":"3561_CR9","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."},{"key":"3561_CR10","doi-asserted-by":"crossref","unstructured":"Casado-Garc\u00eda, \u00c1., Dom\u00ednguez, C., Heras, J., Mata, E., Pascual, V.: The benefits of close-domain fine-tuning for table detection in document images. In International workshop on document analysis systems, pp. 199\u2013215. Springer, (2020)","DOI":"10.1007\/978-3-030-57058-3_15"},{"key":"3561_CR11","doi-asserted-by":"crossref","unstructured":"Li, M., Xu, Y., Cui, L., Huang, S., Wei, F., Li, Z., Zhou, M.: Docbank: a benchmark dataset for document layout analysis. (2020) arXiv preprint arXiv:2006.01038","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"3561_CR12","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolo by ultralytics. 2023. (2023) https:\/\/github.com\/ultralytics\/ultralytics"},{"issue":"3","key":"3561_CR13","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1109\/TCYB.2020.2988792","volume":"51","author":"B Sheng","year":"2020","unstructured":"Sheng, B., Li, P., Zhang, Y., Mao, L., Chen, C.L.P.: Greensea: visual soccer analysis using broad learning system. IEEE Trans. Cybern. 51(3), 1463\u20131477 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"3561_CR14","doi-asserted-by":"crossref","unstructured":"Yao, J., Chen, J., Niu, L., Sheng, B.: Scene-aware human pose generation using transformer. In: Proceedings of the 31st ACM international conference on multimedia, pp. 2847\u20132855, (2023)","DOI":"10.1145\/3581783.3612439"},{"key":"3561_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s00371-021-02229-9","volume":"38","author":"S Zeghoud","year":"2022","unstructured":"Zeghoud, S., Ali, S.G., Ertugrul, E., Kamel, A., Sheng, B., Li, P., Chi, X., Kim, J., Mao, L.: Real-time spatial normalization for dynamic gesture classification. Vis. Comput. 38, 1345\u20131357 (2022)","journal-title":"Vis. Comput."},{"issue":"10","key":"3561_CR16","doi-asserted-by":"publisher","first-page":"5346","DOI":"10.1109\/TNNLS.2021.3070463","volume":"33","author":"P Li","year":"2021","unstructured":"Li, P., Sheng, B., Chen, C.L.P.: Face sketch synthesis using regularized broad learning system. IEEE Trans. Neural Netw. Learn. Syst. 33(10), 5346\u20135360 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"(5","key":"3561_CR17","first-page":"2774","volume":"51","author":"K Aouaidjia","year":"2019","unstructured":"Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-d joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51((5), 2774\u20132788 (2019)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"4\u20135","key":"3561_CR18","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3d human pose estimation for learning tai chi: a human factor perspective. Int. J. Hum. Comput. Interact. 35(4\u20135), 427\u2013439 (2019)","journal-title":"Int. J. Hum. Comput. Interact."},{"issue":"8","key":"3561_CR19","doi-asserted-by":"publisher","first-page":"2540","DOI":"10.1109\/TBME.2021.3050310","volume":"68","author":"A Nazir","year":"2021","unstructured":"Nazir, A., Cheema, M.N., Sheng, B., Li, P., Kim, J., Lee, T.-Y.: Living donor-recipient pair matching for liver transplant via ternary tree representation with cascade incremental learning. IEEE Trans. Biomed. Eng. 68(8), 2540\u20132551 (2021)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"3561_CR20","doi-asserted-by":"publisher","first-page":"1143947","DOI":"10.3389\/fpubh.2023.1143947","volume":"11","author":"SG Ali","year":"2023","unstructured":"Ali, S.G., Wang, X., Li, P., Jung, Y., Bi, L., Kim, J., Chen, Y., Feng, D.D., Magnenat\u00a0Thalmann, N., Wang, J., et al.: A systematic review: virtual-reality-based techniques for human exercises and health improvement. Front. Public Health 11, 1143947 (2023)","journal-title":"Front. Public Health"},{"key":"3561_CR21","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2022","unstructured":"Karambakhsh, A., Sheng, B., Li, P., Li, H., Kim, J., Jung, Y., Chen, C.L.P.: Sparsevoxnet: 3-d object recognition with sparsely aggregation of 3-d dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35, 532\u2013546 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4\u20135","key":"3561_CR22","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1959","volume":"31","author":"E Ertugrul","year":"2020","unstructured":"Ertugrul, E., Zhang, H., Zhu, F., Ping, L., Li, P., Sheng, B., Enhua, W.: Embedding 3d models in offline physical environments. Comput. Anim. Virtual Worlds 31(4\u20135), e1959 (2020)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"3561_CR23","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection. (2020) arXiv preprint arXiv:2004.10934"},{"key":"3561_CR24","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":"3561_CR25","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":"3561_CR26","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: Dab-detr: dynamic anchor boxes are better queries for detr. (2022) arXiv preprint arXiv:2201.12329"},{"key":"3561_CR27","unstructured":"Cao, J., Chen, Q., Guo, J., Shi, R.: Attention-guided context feature pyramid network for object detection. (2020) arXiv preprint arXiv:2005.11475"},{"key":"3561_CR28","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Cheng, M.-M., Shao, L.: An iterative and cooperative top-down and bottom-up inference network for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5968\u20135977, (2019)","DOI":"10.1109\/CVPR.2019.00612"},{"key":"3561_CR29","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":"3561_CR30","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7036\u20137045, (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"3561_CR31","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":"3561_CR32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp. 618\u2013626, (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3561_CR33","unstructured":"Ramaswamy, H.G.: et\u00a0al. Ablation-cam: visual explanations for deep convolutional network via gradient-free localization. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 983\u2013991, (2020)"},{"key":"3561_CR34","doi-asserted-by":"crossref","unstructured":"Muhammad, M.B., Yeasin, M.: Eigen-cam: class activation map using principal components. In: 2020 International joint conference on neural networks (IJCNN), pp. 1\u20137. IEEE, (2020)","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"3561_CR35","doi-asserted-by":"crossref","unstructured":"Melinda, L., Bhagvati, C.: Parameter-free table detection method. In 2019 International conference on document analysis and recognition (ICDAR), pp. 454\u2013460. IEEE, (2019)","DOI":"10.1109\/ICDAR.2019.00079"},{"key":"3561_CR36","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.neucom.2021.10.023","volume":"468","author":"J Fernandes","year":"2022","unstructured":"Fernandes, J., Simsek, M., Kantarci, B., Khan, S.: Tabledet: an end-to-end deep learning approach for table detection and table image classification in data sheet images. Neurocomputing 468, 317\u2013334 (2022)","journal-title":"Neurocomputing"},{"key":"3561_CR37","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. IEEE, (2019)","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"3561_CR38","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.neucom.2021.11.101","volume":"473","author":"A Abdallah","year":"2022","unstructured":"Abdallah, A., Berendeyev, A., Nuradin, I., Nurseitov, D.: Tncr: table net detection and classification dataset. Neurocomputing 473, 79\u201397 (2022)","journal-title":"Neurocomputing"},{"key":"3561_CR39","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Pubtables-1m: towards comprehensive table extraction from unstructured documents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4634\u20134642, (2022)","DOI":"10.1109\/CVPR52688.2022.00459"},{"issue":"4","key":"3561_CR40","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"M-H Guo","year":"2023","unstructured":"Guo, M.-H., Cheng-Ze, L., Liu, Z.-N., Cheng, M.-M., Shi-Min, H.: Visual attention network. Comput. Vis. Med. 9(4), 733\u2013752 (2023)","journal-title":"Comput. Vis. Med."},{"key":"3561_CR41","doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, Y., D\u00e9jean, H., Meunier, J.-L., Yan, Q., Fang, Y., Kleber, F., Lang, E.: Icdar 2019 competition on table detection and recognition (ctdar). In: 2019 International conference on document analysis and recognition (ICDAR), pp. 1510\u20131515. IEEE, (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"3561_CR42","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 1015\u20131022. IEEE, (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"3561_CR43","doi-asserted-by":"crossref","unstructured":"Nazir, D., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Hybridtabnet: towards better table detection in scanned document images. Appl. Sci. 11(18), 8396 (2021)","DOI":"10.3390\/app11188396"},{"key":"3561_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., Zhong, X., Xin R., Wang, N.: Global table extractor (gte): A framework for joint table identification and cell structure recognition using visual context. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 697\u2013706, (2021)","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"3561_CR45","doi-asserted-by":"publisher","first-page":"8906","DOI":"10.1109\/TMM.2023.3243616","volume":"25","author":"J Jiao","year":"2023","unstructured":"Jiao, J., Tang, Y.M., Lin, K.Y., Gao, Y., Ma, A.J., Wang, Y., Zheng, W.S.: Multi-scale dilated transformer for visual recognition: dilateformer. IEEE Trans. Multimed. 25, 8906\u20138919 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"3561_CR46","doi-asserted-by":"crossref","unstructured":"Li, J., Wen, Y., He, L.: Scconv: spatial and channel reconstruction convolution for feature redundancy. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6153\u20136162, (2023)","DOI":"10.1109\/CVPR52729.2023.00596"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03561-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03561-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03561-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T11:30:16Z","timestamp":1741001416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03561-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,16]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3561"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03561-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,16]]},"assertion":[{"value":"22 June 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}