{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:05:06Z","timestamp":1750680306924,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785100"},{"type":"electronic","value":"9789819785117"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8511-7_25","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:05:15Z","timestamp":1730523915000},"page":"348-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TableRocket: An Efficient and Effective Framework for Table Reconstruction"],"prefix":"10.1007","author":[{"given":"Liucheng","family":"Pang","sequence":"first","affiliation":[]},{"given":"Yaping","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Cong","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1449\u20131453. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"25_CR2","unstructured":"D\u00e9jean, H., Meunier, J. L., Gao, L., Huang, Y., Fang, Y., Kleber, F., Lang, E.M.: Icdar 2019 competition on table detection and recognition (ctdar). In: Proceedings-The 15th IAPR International Conference on Document Analysis and Recognition, pp. 1510\u20131515. IEEE (2019)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Kayal, P., Anand, M., Desai, H., Singh, M.: ICDAR 2021 competition on scientific table image recognition to LaTeX. In: Document Analysis and Recognition-ICDAR 2021: 16th International Conference, Lausanne, Switzerland. Proceedings, Part IV 16, pp. 754\u2013766. Springer International Publishing (2021)","DOI":"10.1007\/978-3-030-86337-1_50"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: European Conference on Computer Vision, pp. 564\u2013580. Cham: Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: Tableformer: Table structure understanding with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4614\u20134623 (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"25_CR6","unstructured":"Ye, J., Qi, X., He, Y., Chen, Y., Gu, D., Gao, P., Xiao, R.: PingAn-VCGroup\u2019s Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML (2021). arXiv preprint arXiv:2105.01848"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lu, N., Chen, D., Li, Y., Xie, Z., Zhu, S., Peng, W.: Improving table structure recognition with visual-alignment sequential coordinate modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11134\u201311143 (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., Zhong, X., Wang, N.X.R.: 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":"25_CR9","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"},{"key":"25_CR10","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":"25_CR11","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, X., Li, Y., Fang, C., Shan, Y., Liu, W.: Instances as queries. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6910\u20136919 (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Luo, P.: 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)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Deng, Y., Rosenberg, D., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 894\u2013901. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., Shao, S.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Lu, N., Yu, W., Qi, X., Chen, Y., Gong, P., Xiao, R., Bai, X.: Master: Multi-aspect non-local network for scene text recognition. Pattern Recogn. 117, 107980 (2021)","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Paliwal, S. S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: Tablenet: Deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 128\u2013133. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"25_CR17","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":"25_CR18","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":"25_CR19","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)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Polosukhin, I.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"25_CR21","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":"25_CR22","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2019.00075"},{"issue":"2","key":"25_CR23","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1145\/128749.128750","volume":"39","author":"MB Dillencourt","year":"1992","unstructured":"Dillencourt, M.B., Samet, H., Tamminen, M.: A general approach to connected-component labeling for arbitrary image representations. J. ACM (JACM) 39(2), 253\u2013280 (1992)","journal-title":"J. ACM (JACM)"},{"key":"25_CR24","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Lin, D.: MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Kuang, Z., Sun, H., Li, Z., Yue, X., Lin, T. H., Chen, J., Lin, D.: MMOCR: a comprehensive toolbox for text detection, recognition and understanding. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3791\u20133794 (2021)","DOI":"10.1145\/3474085.3478328"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-up cues. In: Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, Proceedings, Part XXVIII 16, pp. 70\u201386. Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Liu, B., Jiang, D., Liu, Y., Ren, B.: Neural collaborative graph machines for table structure recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4533\u20134542 (2022)","DOI":"10.1109\/CVPR52688.2022.00449"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Qiao, L., Li, Z., Cheng, Z., Zhang, P., Pu, S., Niu, Y., Wu, F.: LGPMA: complicated table structure recognition with local and global pyramid mask alignment. In: International Conference on Document Analysis and Recognition, pp. 99\u2013114. Springer International Publishing, Cham (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, J., Du, J., Wang, F.: Split, embed and merge: an accurate table structure recognizer. Pattern Recogn. 126, 108565 (2022)","DOI":"10.1016\/j.patcog.2022.108565"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906), vol. 3, pp. 850\u2013855. IEEE (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhuo, Y., Wu, Y., Wang, Y., Zheng, X.: Multi-modal feature fusion based on variational autoencoder for visual question answering. Chinese Conference on Pattern Recognition and Computer Vision (2019)","DOI":"10.1007\/978-3-030-31723-2_56"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Liang, Y., Zhang, Y., Ma, C., Zhang, Z., Zhao, Y., Xiang, L., Zong, C., Zhou, Y.: Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling. North American Chapter of the Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.naacl-long.392"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, Y., Liang, Y., Xiang, L., Zhao, Y., Zhou, Y., Zong, C.: LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder. Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.673"},{"key":"25_CR35","unstructured":"Ma, C., Zhang, Y., Zhang, Z., Liang, Y., Zhao, Y., Zhou, Y., Zong, C.: Born a BabyNet with hierarchical parental supervision for end-to-end text image machine translation. Presented at the (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:12:32Z","timestamp":1730524352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}