{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:00:23Z","timestamp":1781006423610,"version":"3.54.1"},"reference-count":94,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116091","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:47:29Z","timestamp":1777996049000},"page":"116091","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HiTextSpotter: Hierarchical Relation Graph Reasoning Network for Scene Text Spotting"],"prefix":"10.1016","volume":"345","author":[{"given":"Jialiang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9907-6747","authenticated-orcid":false,"given":"Canhui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116091_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112399","article-title":"DPGS: Cross-cooperation guided dynamic points generation for scene text spotting","volume":"302","author":"Sun","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116091_b2","doi-asserted-by":"crossref","unstructured":"P. Lyu, M. Liao, C. Yao, W. Wu, X. Bai, Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 67\u201383.","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"10.1016\/j.knosys.2026.116091_b3","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-020-01369-0","article-title":"Scene text detection and recognition: The deep learning era","volume":"129","author":"Long","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116091_b4","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","article-title":"Text detection and recognition in imagery: A survey","volume":"37","author":"Ye","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126702","article-title":"A survey of text detection and recognition algorithms based on deep learning technology","volume":"556","author":"Wang","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116091_b6","doi-asserted-by":"crossref","unstructured":"Z. Li, R. Guan, Q. Yu, Y.-Y. Chiang, C.A. Knoblock, Synthetic map generation to provide unlimited training data for historical map text detection, in: Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, 2021, pp. 17\u201326.","DOI":"10.1145\/3486635.3491070"},{"key":"10.1016\/j.knosys.2026.116091_b7","series-title":"Using Historical Maps in Scientific Studies: Applications, Challenges, and Best Practices","author":"Chiang","year":"2019"},{"key":"10.1016\/j.knosys.2026.116091_b8","series-title":"International Conference on Document Analysis and Recognition","first-page":"363","article-title":"Icdar 2024 competition on historical map text detection, recognition, and linking","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116091_b9","doi-asserted-by":"crossref","unstructured":"Y. Liu, H. Chen, C. Shen, T. He, L. Jin, L. Wang, Abcnet: Real-time scene text spotting with adaptive bezier-curve network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9809\u20139818.","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"10.1016\/j.knosys.2026.116091_b10","series-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"2963","article-title":"Detecting text in natural scenes with stroke width transform","author":"Epshtein","year":"2010"},{"key":"10.1016\/j.knosys.2026.116091_b11","doi-asserted-by":"crossref","unstructured":"W. Huang, Z. Lin, J. Yang, J. Wang, Text localization in natural images using stroke feature transform and text covariance descriptors, in: Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 1241\u20131248.","DOI":"10.1109\/ICCV.2013.157"},{"issue":"12","key":"10.1016\/j.knosys.2026.116091_b12","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1016\/S0031-3203(98)00067-3","article-title":"Automatic text location in images and video frames","volume":"31","author":"Jain","year":"1998","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116091_b13","series-title":"Computer Vision\u2013ACCV 2010: 10th Asian Conference on Computer Vision, Queenstown, New Zealand, November (2010) 8-12, Revised Selected Papers, Part III 10","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"Neumann","year":"2011"},{"key":"10.1016\/j.knosys.2026.116091_b14","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"Yao","year":"2012"},{"key":"10.1016\/j.knosys.2026.116091_b15","series-title":"2011 International Conference on Document Analysis and Recognition","first-page":"440","article-title":"Text detection and character recognition in scene images with unsupervised feature learning","author":"Coates","year":"2011"},{"issue":"11","key":"10.1016\/j.knosys.2026.116091_b16","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1016\/j.imavis.2013.08.007","article-title":"Integrating multiple character proposals for robust scene text extraction","volume":"31","author":"Lee","year":"2013","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.knosys.2026.116091_b17","series-title":"Proceedings of the 21st International Conference on Pattern Recognition","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"Wang","year":"2012"},{"key":"10.1016\/j.knosys.2026.116091_b18","series-title":"2011 International Conference on Computer Vision","first-page":"1457","article-title":"End-to-end scene text recognition","author":"Wang","year":"2011"},{"key":"10.1016\/j.knosys.2026.116091_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.06.020","article-title":"Seglink++: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping","volume":"96","author":"Tang","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116091_b20","doi-asserted-by":"crossref","unstructured":"W. Feng, W. He, F. Yin, X.-Y. Zhang, C.-L. Liu, Textdragon: An end-to-end framework for arbitrary shaped text spotting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9076\u20139085.","DOI":"10.1109\/ICCV.2019.00917"},{"key":"10.1016\/j.knosys.2026.116091_b21","doi-asserted-by":"crossref","unstructured":"S. Long, J. Ruan, W. Zhang, X. He, W. Wu, C. Yao, Textsnake: A flexible representation for detecting text of arbitrary shapes, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 20\u201336.","DOI":"10.1007\/978-3-030-01216-8_2"},{"issue":"11","key":"10.1016\/j.knosys.2026.116091_b22","doi-asserted-by":"crossref","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","article-title":"Textfield: Learning a deep direction field for irregular scene text detection","volume":"28","author":"Xu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116091_b23","doi-asserted-by":"crossref","unstructured":"B. Shi, X. Bai, S. Belongie, Detecting oriented text in natural images by linking segments, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2550\u20132558.","DOI":"10.1109\/CVPR.2017.371"},{"key":"10.1016\/j.knosys.2026.116091_b24","doi-asserted-by":"crossref","unstructured":"Y. Baek, B. Lee, D. Han, S. Yun, H. Lee, Character region awareness for text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9365\u20139374.","DOI":"10.1109\/CVPR.2019.00959"},{"key":"10.1016\/j.knosys.2026.116091_b25","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Song, Y. Zang, W. Wang, T. Lu, G. Yu, C. Shen, Efficient and accurate arbitrary-shaped text detection with pixel aggregation network, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8440\u20138449.","DOI":"10.1109\/ICCV.2019.00853"},{"key":"10.1016\/j.knosys.2026.116091_b26","doi-asserted-by":"crossref","unstructured":"Z. Tian, M. Shu, P. Lyu, R. Li, C. Zhou, X. Shen, J. Jia, Learning shape-aware embedding for scene text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4234\u20134243.","DOI":"10.1109\/CVPR.2019.00436"},{"issue":"1","key":"10.1016\/j.knosys.2026.116091_b27","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","article-title":"Real-time scene text detection with differentiable binarization and adaptive scale fusion","volume":"45","author":"Liao","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b28","doi-asserted-by":"crossref","unstructured":"S.-X. Zhang, X. Zhu, J.-B. Hou, C. Liu, C. Yang, H. Wang, X.-C. Yin, Deep relational reasoning graph network for arbitrary shape text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9699\u20139708.","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"10.1016\/j.knosys.2026.116091_b29","first-page":"335","article-title":"Centripetaltext: An efficient text instance representation for scene text detection","volume":"34","author":"Sheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116091_b30","doi-asserted-by":"crossref","unstructured":"T. He, Z. Tian, W. Huang, C. Shen, Y. Qiao, C. Sun, An end-to-end textspotter with explicit alignment and attention, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5020\u20135029.","DOI":"10.1109\/CVPR.2018.00527"},{"key":"10.1016\/j.knosys.2026.116091_b31","doi-asserted-by":"crossref","unstructured":"S. Qin, A. Bissacco, M. Raptis, Y. Fujii, Y. Xiao, Towards unconstrained end-to-end text spotting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4704\u20134714.","DOI":"10.1109\/ICCV.2019.00480"},{"key":"10.1016\/j.knosys.2026.116091_b32","doi-asserted-by":"crossref","unstructured":"X. Liu, D. Liang, S. Yan, D. Chen, Y. Qiao, J. Yan, Fots: Fast oriented text spotting with a unified network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5676\u20135685.","DOI":"10.1109\/CVPR.2018.00595"},{"key":"10.1016\/j.knosys.2026.116091_b33","doi-asserted-by":"crossref","unstructured":"H. Li, P. Wang, C. Shen, Towards end-to-end text spotting with convolutional recurrent neural networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5238\u20135246.","DOI":"10.1109\/ICCV.2017.560"},{"key":"10.1016\/j.knosys.2026.116091_b34","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August (2020) 23\u201328, Proceedings, Part XI 16","first-page":"706","article-title":"Mask textspotter v3: Segmentation proposal network for robust scene text spotting","author":"Liao","year":"2020"},{"issue":"11","key":"10.1016\/j.knosys.2026.116091_b35","first-page":"8048","article-title":"Abcnet v2: Adaptive bezier-curve network for real-time end-to-end text spotting","volume":"44","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b36","doi-asserted-by":"crossref","unstructured":"P. Wang, C. Zhang, F. Qi, S. Liu, X. Zhang, P. Lyu, J. Han, J. Liu, E. Ding, G. Shi, Pgnet: Real-time arbitrarily-shaped text spotting with point gathering network, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 2782\u20132790, (4).","DOI":"10.1609\/aaai.v35i4.16383"},{"issue":"20","key":"10.1016\/j.knosys.2026.116091_b37","doi-asserted-by":"crossref","first-page":"24314","DOI":"10.1007\/s10489-023-04782-3","article-title":"Him: hierarchical multimodal network for document layout analysis","volume":"53","author":"Canhui","year":"2023","journal-title":"Appl. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b38","doi-asserted-by":"crossref","unstructured":"L. Qiao, Y. Chen, Z. Cheng, Y. Xu, Y. Niu, S. Pu, F. Wu, Mango: A mask attention guided one-stage scene text spotter, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 2467\u20132476, (3).","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"10.1016\/j.knosys.2026.116091_b39","first-page":"1","article-title":"Lateral feature enhancement network for page object detection","volume":"71","author":"Shi","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"6","key":"10.1016\/j.knosys.2026.116091_b40","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1007\/s11771-021-4731-9","article-title":"End-to-end dilated convolution network for document image semantic segmentation","volume":"28","author":"Xu","year":"2021","journal-title":"J. Cent. South Univ."},{"issue":"143,448\u2013143,457","key":"10.1016\/j.knosys.2026.116091_b41","article-title":"A page object detection method based on mask r-cnn","volume":"9","author":"Xu","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116091_b42","doi-asserted-by":"crossref","unstructured":"M. Huang, Y. Liu, Z. Peng, C. Liu, D. Lin, S. Zhu, N. Yuan, K. Ding, L. Jin, Swintextspotter: Scene text spotting via better synergy between text detection and text recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4593\u20134603.","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"10.1016\/j.knosys.2026.116091_b43","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"4272","article-title":"Spts: Single-point text spotting","author":"Peng","year":"2022"},{"key":"10.1016\/j.knosys.2026.116091_b44","doi-asserted-by":"crossref","unstructured":"Y. Kittenplon, I. Lavi, S. Fogel, Y. Bar, R. Manmatha, P. Perona, Towards weakly-supervised text spotting using a multi-task transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4604\u20134613.","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"10.1016\/j.knosys.2026.116091_b45","doi-asserted-by":"crossref","unstructured":"X. Zhang, Y. Su, S. Tripathi, Z. Tu, Text spotting transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9519\u20139528.","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"10.1016\/j.knosys.2026.116091_b46","doi-asserted-by":"crossref","unstructured":"M. Ye, J. Zhang, S. Zhao, J. Liu, T. Liu, B. Du, D. Tao, Deepsolo: Let transformer decoder with explicit points solo for text spotting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19,348\u201319,357.","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"10.1016\/j.knosys.2026.116091_b47","doi-asserted-by":"crossref","unstructured":"M. Huang, J. Zhang, D. Peng, H. Lu, C. Huang, Y. Liu, X. Bai, L. Jin, Estextspotter: Towards better scene text spotting with explicit synergy in transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 19,495\u201319,505.","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"10.1016\/j.knosys.2026.116091_b48","series-title":"DNTextSpotter: Arbitrary-Shaped scene text spotting via improved denoising training","author":"Xie","year":"2024"},{"key":"10.1016\/j.knosys.2026.116091_b49","article-title":"Mgn-net: Multi-granularity graph fusion network in multi-modal for scene text spotting","author":"Yuan","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.116091_b50","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-025-02428-0","article-title":"Mingxin Huang, Dezhi Peng, Swintextspotter v2: Towards better synergy for scene text spotting","author":"Huang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116091_b51","doi-asserted-by":"crossref","unstructured":"A. Das, S. Biswas, A. Banerjee, J. Llad\u00f3s, U. Pal, S. Bhattacharya, Harnessing the power of multi-lingual datasets for pre-training: Towards enhancing text spotting performance, in: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2024, pp. 707\u2013717.","DOI":"10.1109\/WACV57701.2024.00077"},{"key":"10.1016\/j.knosys.2026.116091_b52","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1109\/TIP.2024.3352399","article-title":"Inverse-like antagonistic scene text spotting via reading-order estimation and dynamic sampling","volume":"33","author":"Zhang","year":"2024","journal-title":"Trans. Img. Proc."},{"key":"10.1016\/j.knosys.2026.116091_b53","series-title":"European Conference on Computer Vision","first-page":"249","article-title":"Glass: Global to local attention for scene-text spotting","author":"Ronen","year":"2022"},{"key":"10.1016\/j.knosys.2026.116091_b54","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2023.3294822","article-title":"Hgr-net: Hierarchical graph reasoning network for arbitrary shape scene text detection","author":"Bi","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116091_b55","doi-asserted-by":"crossref","unstructured":"H. Hu, J. Gu, Z. Zhang, J. Dai, Y. Wei, Relation networks for object detection, in: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 3588\u20133597.","DOI":"10.1109\/CVPR.2018.00378"},{"key":"10.1016\/j.knosys.2026.116091_b56","doi-asserted-by":"crossref","unstructured":"P. Wang, C. Da, C. Yao, Multi-granularity prediction for scene text recognition, in: European Conference on Computer Vision, 2022.","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"10.1016\/j.knosys.2026.116091_b57","doi-asserted-by":"crossref","unstructured":"W. Zhou, D. Du, L. Zhang, T. Luo, Y. Wu, Multi-granularity alignment domain adaptation for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 9581\u20139590.","DOI":"10.1109\/CVPR52688.2022.00936"},{"key":"10.1016\/j.knosys.2026.116091_b58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2021.3069498","article-title":"Robust domain adaptive object detection with unified multi-granularity alignment","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b59","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.knosys.2026.116091_b60","doi-asserted-by":"crossref","unstructured":"S. Long, S. Qin, D. Panteleev, A. Bissacco, Y. Fujii, M. Raptis, Towards end-to-end unified scene text detection and layout analysis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1049\u20131059.","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"10.1016\/j.knosys.2026.116091_b61","article-title":"Hi-sam: Marrying segment anything model for hierarchical text segmentation","author":"Ye","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b62","doi-asserted-by":"crossref","first-page":"3788","DOI":"10.1109\/TMM.2022.3165717","article-title":"Srrv: A novel document object detector based on spatial-related relation and vision","volume":"25","author":"Bi","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116091_b63","first-page":"8291","article-title":"Vision gnn: An image is worth graph of nodes","volume":"35","author":"Han","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116091_b64","doi-asserted-by":"crossref","DOI":"10.1016\/j.simpat.2022.102653","article-title":"Graph-based convolution feature aggregation for retinal vessel segmentation","volume":"121","author":"Shi","year":"2022","journal-title":"Simul. Model. Pract. Theory"},{"key":"10.1016\/j.knosys.2026.116091_b65","unstructured":"K. Xu, W. Hu, J. Leskovec, S. Jegelka, How powerful are graph neural networks?, in: International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.knosys.2026.116091_b66","doi-asserted-by":"crossref","unstructured":"M. Ye, J. Zhang, S. Zhao, J. Liu, B. Du, D. Tao, Dptext-detr: Towards better scene text detection with dynamic points in transformer, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 3241\u20133249, (3).","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"10.1016\/j.knosys.2026.116091_b67","series-title":"2015 13th International Conference on Document Analysis and Recognition","first-page":"1156","article-title":"Icdar 2015 competition on robust reading","author":"Karatzas","year":"2015"},{"key":"10.1016\/j.knosys.2026.116091_b68","series-title":"Detecting curve text in the wild: New dataset and new solution","author":"Yuliang","year":"2017"},{"key":"10.1016\/j.knosys.2026.116091_b69","series-title":"2017 14th IAPR International Conference on Document Analysis and Recognition","first-page":"935","article-title":"Total-text: A comprehensive dataset for scene text detection and recognition","volume":"Vol. 1","author":"Ch\u2019ng","year":"2017"},{"key":"10.1016\/j.knosys.2026.116091_b70","doi-asserted-by":"crossref","unstructured":"Y. Liu, L. Jin, Deep matching prior network: Toward tighter multi-oriented text detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1962\u20131969.","DOI":"10.1109\/CVPR.2017.368"},{"key":"10.1016\/j.knosys.2026.116091_b71","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","article-title":"Curved scene text detection via transverse and longitudinal sequence connection","volume":"90","author":"Liu","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116091_b72","doi-asserted-by":"crossref","unstructured":"X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, J. Liang, East: an efficient and accurate scene text detector, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 5551\u20135560.","DOI":"10.1109\/CVPR.2017.283"},{"issue":"8","key":"10.1016\/j.knosys.2026.116091_b73","doi-asserted-by":"crossref","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","article-title":"Textboxes++: A single-shot oriented scene text detector","volume":"27","author":"Liao","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"10.1016\/j.knosys.2026.116091_b74","doi-asserted-by":"crossref","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","article-title":"Arbitrary-oriented scene text detection via rotation proposals","volume":"20","author":"Ma","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116091_b75","series-title":"Msr: multi-scale shape regression for scene text detection","author":"Xue","year":"2019"},{"key":"10.1016\/j.knosys.2026.116091_b76","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Li, W. Hou, T. Lu, G. Yu, S. Shao, Shape robust text detection with progressive scale expansion network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9336\u20139345.","DOI":"10.1109\/CVPR.2019.00956"},{"key":"10.1016\/j.knosys.2026.116091_b77","doi-asserted-by":"crossref","unstructured":"C. Zhang, B. Liang, Z. Huang, M. En, J. Han, E. Ding, X. Ding, Look more than once: An accurate detector for text of arbitrary shapes, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10,552\u201310,561.","DOI":"10.1109\/CVPR.2019.01080"},{"key":"10.1016\/j.knosys.2026.116091_b78","doi-asserted-by":"crossref","first-page":"2918","DOI":"10.1109\/TIP.2019.2954218","article-title":"Arbitrarily shaped scene text detection with a mask tightness text detector","volume":"29","author":"Liu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116091_b79","doi-asserted-by":"crossref","unstructured":"Y. Wang, H. Xie, Z.-J. Zha, M. Xing, Z. Fu, Y. Zhang, Contournet: Taking a further step toward accurate arbitrary-shaped scene text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11,753\u201311,762.","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"10.1016\/j.knosys.2026.116091_b80","doi-asserted-by":"crossref","unstructured":"H. Wang, P. Lu, H. Zhang, M. Yang, X. Bai, Y. Xu, M. He, Y. Wang, W. Liu, All you need is boundary: Toward arbitrary-shaped text spotting, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, 2020, pp. 12,160\u201312,167, (07).","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"10.1016\/j.knosys.2026.116091_b81","doi-asserted-by":"crossref","unstructured":"P. Dai, S. Zhang, H. Zhang, X. Cao, Progressive contour regression for arbitrary-shape scene text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7393\u20137402.","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"10.1016\/j.knosys.2026.116091_b82","doi-asserted-by":"crossref","unstructured":"Y. Zhu, J. Chen, L. Liang, Z. Kuang, L. Jin, W. Zhang, Fourier contour embedding for arbitrary-shaped text detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3123\u20133131.","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"10.1016\/j.knosys.2026.116091_b83","doi-asserted-by":"crossref","unstructured":"Z. Raisi, M.A. Naiel, G. Younes, S. Wardell, J.S. Zelek, Transformer-based text detection in the wild, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3162\u20133171.","DOI":"10.1109\/CVPRW53098.2021.00353"},{"key":"10.1016\/j.knosys.2026.116091_b84","doi-asserted-by":"crossref","first-page":"4076","DOI":"10.1109\/TIP.2022.3167919","article-title":"Ace: Anchor-free corner evolution for real-time arbitrarily-oriented object detection","volume":"31","author":"Dai","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116091_b85","doi-asserted-by":"crossref","unstructured":"S.-X. Zhang, X. Zhu, C. Yang, H. Wang, X.-C. Yin, Adaptive boundary proposal network for arbitrary shape text detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 1305\u20131314.","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"10.1016\/j.knosys.2026.116091_b86","doi-asserted-by":"crossref","unstructured":"L. Qiao, S. Tang, Z. Cheng, Y. Xu, Y. Niu, S. Pu, F. Wu, Text perceptron: Towards end-to-end arbitrary-shaped text spotting, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 11,899\u201311,907, (3).","DOI":"10.1609\/aaai.v34i07.6864"},{"issue":"9","key":"10.1016\/j.knosys.2026.116091_b87","first-page":"5349","article-title":"Pan++: Towards efficient and accurate end-to-end spotting of arbitrarily-shaped text","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116091_b88","series-title":"Single shot self-reliant scene text spotter by decoupled yet collaborative detection and recognition","author":"Wu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116091_b89","doi-asserted-by":"crossref","unstructured":"W. Wang, Y. Zhou, J. Lv, D. Wu, G. Zhao, N. Jiang, W. Wang, Tpsnet: Reverse thinking of thin plate splines for arbitrary shape scene text representation, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 5014\u20135025.","DOI":"10.1145\/3503161.3547882"},{"issue":"6","key":"10.1016\/j.knosys.2026.116091_b90","doi-asserted-by":"crossref","first-page":"7123","DOI":"10.1109\/TPAMI.2022.3223908","article-title":"Abinet++: Autonomous, bidirectional and iterative language modeling for scene text spotting","volume":"45","author":"Fang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.knosys.2026.116091_b91","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph cnn for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph. (Tog)"},{"key":"10.1016\/j.knosys.2026.116091_b92","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116091_b93","doi-asserted-by":"crossref","unstructured":"G. Li, M. Muller, A. Thabet, B. Ghanem, Deepgcns: Can gcns go as deep as cnns?, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9267\u20139276.","DOI":"10.1109\/ICCV.2019.00936"},{"key":"10.1016\/j.knosys.2026.116091_b94","unstructured":"P. Barcel\u00f3, E.V. Kostylev, M. Monet, J. P\u00e9rez, J. Reutter, J.-P. Silva, The logical expressiveness of graph neural networks, in: 8th International Conference on Learning Representations, 2020."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008178?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008178?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:23:32Z","timestamp":1781004212000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":94,"alternative-id":["S0950705126008178"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116091","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HiTextSpotter: Hierarchical Relation Graph Reasoning Network for Scene Text Spotting","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116091","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116091"}}