{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T14:07:44Z","timestamp":1744812464431,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819949137"},{"type":"electronic","value":"9789819949144"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-4914-4_10","type":"book-chapter","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T21:02:35Z","timestamp":1690837355000},"page":"122-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust Scene Text Detection Under Occlusion via Multi-scale Adaptive Deep Network"],"prefix":"10.1007","author":[{"given":"My-Tham","family":"Dinh","sequence":"first","affiliation":[]},{"given":"Minh-Trieu","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Quang-Vinh","family":"Dang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-1382","authenticated-orcid":false,"given":"Guee-Sang","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"10_CR2","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2022","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Trans. Pattern Anal. Mach. Intell. 45, 919\u2013931 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Chen, L., Hou, J., Yin, X.: Arbitrary shape text detection via segmentation with probability map. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Few could be better than all: feature sampling and grouping for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4563\u20134572 (2022)","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"10_CR5","first-page":"970","volume":"36","author":"X Yin","year":"2013","unstructured":"Yin, X., Yin, X., Huang, K., Hao, H.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36, 970\u2013983 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR6","unstructured":"Chen, Z., Wang, W., Xie, E., Yang, Z., Lu, T., Luo, P.: FAST: searching for a faster arbitrarily-shaped text detector with minimalist kernel representation. in arXiv preprint arXiv:2111.02394 (2021)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Ayush, M., Palaiahnakote, S., Umapada, P., Tong, L., Michael, B.: A new method for detection and prediction of occluded text in natural scene images. In: Signal Processing: Image Communication, p. 116512 (2022)","DOI":"10.1016\/j.image.2021.116512"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Aline, G.S., Byron, L.D.B., Estanislau, B.L.: How far deep learning systems for text detection and recognition in natural scenes are affected by occlusion?. In: International Conference on Document Analysis and Recognition, pp. 198\u2013212 (2021)","DOI":"10.1007\/978-3-030-86198-8_15"},{"key":"10_CR9","unstructured":"Bolei, Z., Aditya, K., Agata, L., Aude, O., Antonio, T.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Ayush, M., Palaiahnakote, S., Umapada, P., Tong, L., Michael, B., Daniel, L.: A new context-based method for restoring occluded text in natural scene images. In: International Workshop on Document Analysis Systems, pp. 466\u2013480 (2020)","DOI":"10.1007\/978-3-030-57058-3_33"},{"key":"10_CR11","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":"10_CR12","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"10_CR14","unstructured":"Dinh, M., Lee, G.: Arbitrary-shaped scene text detection based on multi-scale feature enhancement network. In: Korea Computer Congress, pp. 669\u2013671 (2022)"},{"key":"10_CR15","unstructured":"Aditya, C., Anirban, S., Prantik, H., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839\u2013847 (2018)"},{"key":"10_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, S., Zhang, H., Cao, X.: Progressive contour regression for arbitrary-shape scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7393\u20137402 (2021)","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X., Yin, F., Liu, C.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 745\u2013753 (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"10_CR19","unstructured":"Sheng, T., Chen, J., Lian, Z.: Centripetaltext: an efficient text instance representation for scene text detection. In: Advances in Neural Information Processing Systems, pp. 335\u2013346 (2021)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Learning shape-aware embedding for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4234\u20134243 (2019)","DOI":"10.1109\/CVPR.2019.00436"},{"key":"10_CR21","unstructured":"Ramprasaath, R.S., Michael, C., Abhishek, D., Ramakrishna, V., Devi, P., Dhruv, B.: 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)"},{"key":"10_CR22","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":"10_CR23","unstructured":"Andrew, G.h., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications, pp. 770\u2013778. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Carole, H.S., Li, W., Tom, V., Sebastien, O., Cardoso, M.J.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 240\u2013248 (2017)","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Dimosthenis, K., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10_CR26","unstructured":"Jia, D., Wei, D., Richard, S., Li, L., Li, K., Li, F.F.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)"},{"key":"10_CR27","doi-asserted-by":"publisher","first-page":"36924","DOI":"10.1109\/ACCESS.2021.3062904","volume":"9","author":"QV Dang","year":"2021","unstructured":"Dang, Q.V., Lee, G.-S.: Document image binarization with stroke boundary feature guided network. IEEE Access 9, 36924\u201336936 (2021)","journal-title":"IEEE Access"},{"key":"10_CR28","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation (2016). arXiv preprint arXiv:1609.08144"},{"key":"10_CR29","unstructured":"Dang, Q.-V., Lee, G.-S.: Document image binarization by GAN with unpaired data training. Int. J. Contents, 8\u201318 (2020)"},{"key":"10_CR30","first-page":"5349","volume":"44","author":"W Wang","year":"2021","unstructured":"Wang, W., et al.: Pan++: towards efficient and accurate end-to-end spotting of arbitrarily-shaped text. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5349\u20135367 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR31","unstructured":"Aviad, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15302\u201315312 (2021)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, Z., Wang, Z., Price, B., Wang, Z., Shi, H.: Rethinking text segmentation: A novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12045\u201312055 (2021)","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"10_CR33","unstructured":"Dan, D., Liu, H., Li, X., Cai, D.: Pixellink: detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)"}],"container-title":["Communications in Computer and Information Science","Frontiers of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4914-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T11:59:58Z","timestamp":1729857598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4914-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819949137","9789819949144"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4914-4_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IW-FCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Frontiers of Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Yeozu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 February 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 February 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwfcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwfcv2023.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}