{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:11:35Z","timestamp":1758089495939,"version":"3.44.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046239"},{"type":"electronic","value":"9783032046246"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04624-6_11","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:34:09Z","timestamp":1758000849000},"page":"180-199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A New Fourier-Attention Guided Approach for Domain-Agnostic Text Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8834-8022","authenticated-orcid":false,"given":"Arnab","family":"Halder","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9026-4613","authenticated-orcid":false,"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5426-2618","authenticated-orcid":false,"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9908-3744","authenticated-orcid":false,"given":"Michael","family":"Blumenstein","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8784-4657","authenticated-orcid":false,"given":"Yue","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Asadzadehkaljahi, M., Halder, A., Pal, U., Shivakumara, P.: Spatiotemporal edges for arbitrarily moving video classification in protected and sensitive scenes. Artif. Intell. Appl. (2023). https:\/\/doi.org\/10.47852\/bonviewAIA3202526","DOI":"10.47852\/bonviewAIA3202526"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Asadzadehkaljahi, M., Halder, A., Shivkumara, P., Pal, U.: Spatio-temporal FFT-based approach for arbitrarily moving object classification videos of protected and sensitive scenes. Artif. Intell. Appl. (2023)","DOI":"10.47852\/bonviewAIA3202553"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Banerjee, A., Shivakumara, P., Bhattacharya, S., Pal, U., Liu, C.L.: An end-to-end model for multi-view scene text recognition. Pattern Recogn. 149, 110206 (2024)","DOI":"10.1016\/j.patcog.2023.110206"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Banerjee, A., Shivakumara, P., Pal, S., Pal, U., Liu, C.L.: DCT-DWT-FFT based method for text detection in underwater images. In: Proceedings of ACPR, pp 218\u2013233 (2021)","DOI":"10.1007\/978-3-031-02444-3_16"},{"key":"11_CR104","doi-asserted-by":"crossref","unstructured":"Banerjee, A., Shivakumara, P., Acharya, P., Pal, U., Canet, J.L.: TWD: a new deep E2E model for text watermark\/captionand scene text detection in video. In: 26th International Conference on Pattern Recognition, 1492\u20131498 (2022)","DOI":"10.1109\/ICPR56361.2022.9956279"},{"key":"11_CR100","unstructured":"Chen, Z., et al.: FAST: faster arbitrarily-shaped text detector with minimalist kernel representation (2021). ArXiv. https:\/\/arxiv.org\/abs\/2111.02394"},{"key":"11_CR5","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-Text dataset (2017). https:\/\/github.com\/cs-chan\/Total-Text-Dataset. Accessed 14 June 2023"},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Halder, A., Palaiahnakote, S., Pal, U., Blumenstein, M., Gornale, S.S.: A new HourGlass network for detecting text in shaky and non-shaky video frames. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds.) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol. 15320. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-78498-9_9","DOI":"10.1007\/978-3-031-78498-9_9"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Halder, A., Palaiahnakote, S., Pal, U., Blumenstein, M., Liu, C.L.: A new unsupervised approach for text localization in shaky and non-shaky scene video. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) Document Analysis and Recognition - ICDAR 2024. ICDAR 2024. Lecture Notes in Computer Science, vol. 14808. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70549-6_10","DOI":"10.1007\/978-3-031-70549-6_10"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Halder, A., Shivakumara, P., Blumenstein, M.: A comprehensive review on text detection and recognition in scene images (U. Pal, Trans.). Artif. Intell. Appl. 2(4), 229\u2013249 (2024)","DOI":"10.47852\/bonviewAIA42022755"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Halder, A., Shivakumara, P., Pal, U., Blumenstein, M., Ghosal, P.: A locally weighted linear regression-based approach for arbitrary moving shaky and nonshaky video classification. Int. J. Pattern Recognit. Artif. Intell. (2024)","DOI":"10.1142\/S0218001423510199"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Halder, A., Shivakumara, P., Pal, U., Lu, T., Blumenstein, M.: A new transformer-based approach for text detection in shaky and non-shaky day-night video. In: Proceedings of ACPR (2023)","DOI":"10.1007\/978-3-031-47637-2_3"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition. arXiv (2022). https:\/\/arxiv.org\/abs\/2203.10209","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of ICDAR, pp. 1156\u20131160 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333942","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Kong, L., Dong, J., Ge, J., Li, M., Pan, J.: Efficient frequency domain-based transformers for high-quality image deblurring. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5886\u20135895 (2023)","DOI":"10.1109\/CVPR52729.2023.00570"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: SPTS v2: Single-Point Scene Text Spotting. arXiv (2023). https:\/\/arxiv.org\/abs\/2301.01635","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Lu, N., et al.: Master: multi-aspect non-local network for scene text recognition. Pattern Recog.  117, 107980 (2021). https:\/\/doi.org\/10.1016\/j.patcog.2021.107980","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"11_CR101","doi-asserted-by":"crossref","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia  20(11), 3111\u20133122 (2018). https:\/\/www.ieeexplore.ieee.org\/document\/8323240","DOI":"10.1109\/TMM.2018.2818020"},{"key":"11_CR102","unstructured":"Ma, J., Guo, S., Zhang, L.: Text prior guided scene text image super-resolution. ArXiv (2021). https:\/\/arxiv.org\/abs\/2106.15368"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Maoyuan, Y., et al.: Deepsolo: let transformer decoder with explicit points solo for text spotting. In: Proceedings of CVPR, pp. 19348\u201319357 (2023)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Mokayed, H., Shivakumara, P., Alkhaled, L., Al-Masr, A.N.: License plate number detection in drone images. Artif. Intell. Appl. 1\u20138 (2022)","DOI":"10.47852\/bonviewAIA2202421"},{"key":"11_CR105","doi-asserted-by":"publisher","unstructured":"Mokayed, H., Shivakumara, P., Liwicki, M.,  U. Pal, U.: A New Defect Detection Method for Improving Text Detection and Recognition Performances in Natural Scene Images, In: 2020 Swedish Workshop on Data Science (SweDS), Lulea, Sweden, 2020, pp. 1\u20137 (2019). https:\/\/doi.org\/10.1109\/SweDS51247.2020.9275589","DOI":"10.1109\/SweDS51247.2020.9275589"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Mokayed, H., Shivakumara, P., Woon, H.H., Kankanhalli, M., Lu, T., Pal, U.: A new DCT-PCM method for license plate number detection in drone images. Pattern Recogn. Lett. 148, 45\u201353 (2021)","DOI":"10.1016\/j.patrec.2021.05.002"},{"key":"11_CR106","doi-asserted-by":"publisher","unstructured":"Roy, A., Shivakumara, P., Pal, U., Mokayed, H., Liwicki, M.: Fourier feature-based CBAM and vision transformer for text detection in drone images. In: Coustaty, M., Forn\u00e9s, A. (eds) Document Analysis and Recognition \u2013 ICDAR 2023 Workshops. ICDAR 2023. Lecture Notes in Computer Science, vol 14194. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41501-2_18","DOI":"10.1007\/978-3-031-41501-2_18"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Pal, S., Roy, A., Shivakumara, P., Pal, U.: Adapting a swim transformer for license plate number detection and text detection in drone images. Artif. Intell. Appl. 145\u2013154 (2023)","DOI":"10.47852\/bonviewAIA3202549"},{"key":"11_CR107","doi-asserted-by":"crossref","unstructured":"Pal, U., Halder, A., Shivakumara, P., Blumenstein, M.: A comprehensive review on text detection and recognition in scene images. Artif. Intel. Appl. 2(4), 229\u2013249 (2024)","DOI":"10.47852\/bonviewAIA42022755"},{"key":"11_CR103","doi-asserted-by":"publisher","unstructured":"Purkayastha, K., Sarkar, S., Palaiahnakote, S., Pal, U., Ghosal, P.: DATR: Domain Agnostic Text Recognizer. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15317. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-78447-7_15","DOI":"10.1007\/978-3-031-78447-7_15"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Shikha, N., Pranav, R., Singh, N.R., Umadevi, V., Hussain, M.: Kannada word detection in heterogeneous scene images. In: Proceedings of SPIN, pp. 379\u2013383 (2023)","DOI":"10.1109\/SPIN57001.2023.10117096"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Shivakumara, P., Banerjee, A., Pal, U., Nandanwar, L., Lu, T., Liu, C.-L.: A new language-independent deep CNN for scene text detection and style transfer in social media images. IEEE Trans. Image Proc, 32, 3552\u20133566 (2023). https:\/\/ieeexplore.ieee.org\/document\/10159272","DOI":"10.1109\/TIP.2023.3287038"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: Explicit relational reasoning network for scene text detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 7, pp. 7069\u20137077 (2025)","DOI":"10.1609\/aaai.v39i7.32759"},{"key":"11_CR23","unstructured":"Wang, F., Xu, G.: Scene text detection based on progressive multi-scale feature fusion and contextual information enhancement. In: Proceedings of the International Conference on Computer Applications and Information Development (ICCAID), vol. 13560, p. 135602Q (2024)"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Xue, M., Huang, Z., Liu, R. -z.  Lu, T.: A novel attention enhanced residual-in-residual dense network for text image super-resolution. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), Shenzhen, China, 2021, pp. 1\u20136 (2021) https:\/\/doi.org\/10.1109\/ICME51207.2021.9428128","DOI":"10.1109\/ICME51207.2021.9428128"},{"key":"11_CR25","unstructured":"Yang, C., Chen, M., Yuan, Y., Wang, Q.: Zoom Text Detector. arXiv (2022). https:\/\/arxiv.org\/abs\/2209.03014"},{"key":"11_CR26","unstructured":"Yang, C., Han, X., Han, T., Han, H., Zhao, B., Wang, Q.: Edge Approximation Text Detector. arXiv (2025). https:\/\/arxiv.org\/abs\/2504.04001"},{"key":"11_CR27","unstructured":"Ye, M., et al.: DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting. arXiv (2022). https:\/\/arxiv.org\/abs\/2211.10772"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Chen, L., Hou, J.B., Yin, X.C.: Arbitrarily shape text detection via segmentation with probability maps. IEEE Trans. Pattern Anal. Mach. Intell. 2736\u20132750 (2023)","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text Spotting Transformers. arXiv (2022). https:\/\/arxiv.org\/abs\/2204.01918","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, J., Fan, H., Zhang, L.: Kernel adaptive convolution for scene text detection via distance map prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5957\u20135966 (2024)","DOI":"10.1109\/CVPR52733.2024.00569"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: TransText: improving scene text detection via transformer. Digit. Signal Process. 130, 103698 (2022)","DOI":"10.1016\/j.dsp.2022.103698"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04624-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:34:21Z","timestamp":1758000861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04624-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032046239","9783032046246"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04624-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}