{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T19:40:09Z","timestamp":1769283609778,"version":"3.49.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Research Foundation of Korea (NRF) funded by the Ministry of Education","award":["NRF- 2018R1D1A3B05049058"],"award-info":[{"award-number":["NRF- 2018R1D1A3B05049058"]}]},{"name":"National Research Foundation of Korea (NRF) funded by the Ministry of Education","award":["NRF- 2018R1D1A3B05049058"],"award-info":[{"award-number":["NRF- 2018R1D1A3B05049058"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00530-025-01782-w","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T09:50:56Z","timestamp":1744797056000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Occluded scene text detection via context-awareness from sketch-level image representations"],"prefix":"10.1007","volume":"31","author":[{"given":"Minh-Trieu","family":"Tran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guee-Sang","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,16]]},"reference":[{"key":"1782_CR1","doi-asserted-by":"publisher","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Du, B., Tao, D.: Dptext-detr: towards better scene text detection with dynamic points in transformer. In: Paper Presented at the AAAI Conference on Artificial Intelligence, pp. 3241\u20133249 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i3.25430","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"1782_CR2","doi-asserted-by":"publisher","unstructured":"Dinh, M.T., Tran, M..T., Dang, Q.V., Lee, G.S.: Robust scene text detection under occlusion via multi-scale adaptive deep network. In: Paper Presented at International Workshop on Frontiers of Computer Vision, pp. 122\u2013134 (2023). https:\/\/doi.org\/10.1007\/978-981-99-4914-4_10","DOI":"10.1007\/978-981-99-4914-4_10"},{"key":"1782_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116512","volume":"100","author":"A Mittal","year":"2022","unstructured":"Mittal, A., Shivakumara, P., Pal, U., Lu, T., Blumenstein, M.: A new method for detection and prediction of occluded text in natural scene images. Signal Process. Image Commun. 100, 116512 (2022). https:\/\/doi.org\/10.1016\/j.image.2021.116512","journal-title":"Signal Process. Image Commun."},{"key":"1782_CR4","doi-asserted-by":"publisher","unstructured":"Geovanna\u00a0Soares, B.A., Dantas\u00a0Bezerra, L., Baptista\u00a0Lima, E.: How far deep learning systems for text detection and recognition in natural scenes are affected by occlusion? In: Paper Presented at International Conference on Document Analysis and Recognition, pp. 198\u2013212 (2021). https:\/\/doi.org\/10.1007\/978-3-030-86198-8_15","DOI":"10.1007\/978-3-030-86198-8_15"},{"key":"1782_CR5","doi-asserted-by":"publisher","unstructured":"Raisi, Z., Zelek, J.: Occluded text detection and recognition in the wild. In: Paper Presented at Conference on Robots and Vision (CRV), pp. 140\u2013150 (2022). https:\/\/doi.org\/10.1109\/CRV55824.2022.00026","DOI":"10.1109\/CRV55824.2022.00026"},{"key":"1782_CR6","doi-asserted-by":"publisher","unstructured":"Neves, R.B.D., Nascimento, S., Bezerra, B.L.D.: A robust approach to detect occlusions during camera-based document scanning. In: Paper Presented at IEEE Latin American Conference on Computational Intelligence, pp. 1\u20136 (2023). https:\/\/doi.org\/10.1109\/LA-CCI58595.2023.10409375","DOI":"10.1109\/LA-CCI58595.2023.10409375"},{"key":"1782_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TVCG.2023.3342119","volume":"100","author":"D Yu","year":"2023","unstructured":"Yu, D., Xiao, C., Lau, M., Fu, H.: Sketch2stress: sketching with structural stress awareness. IEEE Trans. Vis. Comput. Graph. 100, 1\u201315 (2023). https:\/\/doi.org\/10.1109\/TVCG.2023.3342119","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"1782_CR8","doi-asserted-by":"publisher","unstructured":"Lee, H., Hwang, I., Go, H., Choi, W.S., Kim, K., Zhang, B.T.: Learning geometry-aware representations by sketching. In: Paper Presented at the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23315\u201323326 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02233","DOI":"10.1109\/CVPR52729.2023.02233"},{"key":"1782_CR9","doi-asserted-by":"publisher","unstructured":"Bhunia, A.K., Koley, S., Khilji, A.F.U.R., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.Z.: Sketching without worrying: Noise-tolerant sketch-based image retrieval. In: Paper Presented at the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 999\u20131008 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00107","DOI":"10.1109\/CVPR52688.2022.00107"},{"key":"1782_CR10","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, S.Z., Li, : Occlusion-aware r-cnn: detecting pedestrians in a crowd. In: Paper Presented at the European Conference on Computer Vision (ECCV), pp. 637\u2013653 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_39","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"1782_CR11","doi-asserted-by":"publisher","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., Wang, M.: Swin-unet: Unet-like pure transformer for medical image segmentation. In: Paper Presented at the European Conference on Computer Vision (ECCV), pp. 205\u2013218 (2022). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"1782_CR12","doi-asserted-by":"publisher","unstructured":"CFan, C.M., Liu, T.J., Liu, K.H.: Sunet: swin transformer unet for image denoising. In: Paper Presented at the International Symposium on Circuits and Systems (ISCAS), pp. 2333\u20132337 (2022). https:\/\/doi.org\/10.1109\/ISCAS48785.2022.9937486","DOI":"10.1109\/ISCAS48785.2022.9937486"},{"key":"1782_CR13","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159 (2020)"},{"key":"1782_CR14","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022).  https:\/\/scholar.googleusercontent.com\/scholar.bib?q=info:jpO53eH9at8J:scholar.google.com\/&output=citation&scisdr=ClFw7v2CEPHk8UG0hKs:AFWwaeYAAAAAZ_uynKvXlWt-6stIu4JNjNuUWvc&scisig=AFWwaeYAAAAAZ_uynIdkDr38YtoT_HWdDwbtOWw&scisf=4&ct=citation&cd=-1&hl=en"},{"key":"1782_CR15","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Paper Presented at the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"1782_CR16","doi-asserted-by":"publisher","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Paper Presented at the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_2","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"1782_CR17","doi-asserted-by":"publisher","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: Paper Presented at the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00956","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1782_CR18","doi-asserted-by":"publisher","unstructured":"Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., Li, G.: Scene text detection with supervised pyramid context network. In: Paper Presented at the AAAI Conference on Artificial Intelligence, pp. 9038\u20139045 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33019038","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"1782_CR19","doi-asserted-by":"publisher","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Paper Presented at the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00959","DOI":"10.1109\/CVPR.2019.00959"},{"key":"1782_CR20","doi-asserted-by":"publisher","DOI":"10.3390\/s23135889","author":"MT Dinh","year":"2023","unstructured":"Dinh, M.T., Choi, D.J., Lee, G.S.: Densetextpvt: pyramid vision transformer with deep multi-scale feature refinement network for dense text detection. Sensors (2023). https:\/\/doi.org\/10.3390\/s23135889","journal-title":"Sensors"},{"key":"1782_CR21","doi-asserted-by":"publisher","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Paper Presented at the AAAI Conference on Artificial Intelligence, pp. 11474\u201311481 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6812","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"1782_CR22","doi-asserted-by":"publisher","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: Paper Presented at the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00853","DOI":"10.1109\/ICCV.2019.00853"},{"key":"1782_CR23","doi-asserted-by":"publisher","unstructured":"Dai, P., Zhang, S., Zhang, H., Cao, X.: Progressive contour regression for arbitrary-shape scene text detection. In: Paper Presented at the IEEE\/CVF International Conference on Computer Vision, pp. 7393\u20137402 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00731","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"1782_CR24","doi-asserted-by":"publisher","unstructured":"Ye, J., Chen, Z., Liu, J., Du, B.: Textfusenet: scene text detection with richer fused features. In: Paper Presented at the International Joint Conference on Artificial Intelligence (IJCAI), pp. 516\u2013522 (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/72","DOI":"10.24963\/ijcai.2020\/72"},{"key":"1782_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01616-6","author":"B Du","year":"2022","unstructured":"Du, B., Ye, J., Zhang, J., Liu, J., Tao, D.: I3cl: intra-and inter-instance collaborative learning for arbitrary-shaped scene text detection. Int. J. Comput. Vis. (2022). https:\/\/doi.org\/10.1007\/s11263-022-01616-6","journal-title":"Int. J. Comput. Vis."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01782-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01782-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01782-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T15:03:40Z","timestamp":1756998220000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01782-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,16]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1782"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01782-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,16]]},"assertion":[{"value":"24 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"192"}}