{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T12:10:21Z","timestamp":1770898221825,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093677","type":"print"},{"value":"9783032093684","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-09368-4_7","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:25Z","timestamp":1763921665000},"page":"108-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A New Multimodal Cross-Domain Network for Classification of Challenging Scene Images"],"prefix":"10.1007","author":[{"given":"Shashwat","family":"Sarkar","sequence":"first","affiliation":[]},{"given":"Kunal","family":"Purkayastha","sequence":"additional","affiliation":[]},{"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[]},{"given":"Muhammad Hammad","family":"Saleem","sequence":"additional","affiliation":[]},{"given":"Palash","family":"Ghosal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"issue":"6","key":"7_CR1","first-page":"2526","volume":"33","author":"SX Zhang","year":"2022","unstructured":"Zhang, S.X., et al.: Kernel proposal network for arbitrary shape text detection. IEEE Trans. Neural Netw. Learn. Syst. 33(6), 2526\u20132538 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2022.3201467","volume":"32","author":"F Wang","year":"2023","unstructured":"Wang, F., Xu, X., Chen, Y., Wu, F., Bai, X.: Fuzzy semantics for arbitrary-shaped scene text detection. IEEE Trans. Image Process. 32, 1\u201312 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108608","volume":"127","author":"Y Cai","year":"2022","unstructured":"Cai, Y., Liu, Y., Shen, C., Chen, Q.: Arbitrarily shaped scene text detection with dynamic convolution. Pattern Recogn. 127, 108608 (2022)","journal-title":"Pattern Recogn."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. arXiv preprint arXiv:2207.12382 (2022)","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"7_CR5","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. arXiv preprint arXiv:2111.02394 (2021)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: ODM: a text-image further alignment pre-training approach for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01476"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Qin, X., et al.: Towards robust real-time scene text detection: from semantic to instance representation learning. arXiv preprint arXiv:2308.07202 (2023)","DOI":"10.1145\/3581783.3611801"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xie, H., Gao, Z., Wang, Y.: Choose what you need: disentangled representation learning for scene text recognition, removal and editing. arXiv preprint arXiv:2405.04377 (2024)","DOI":"10.1109\/CVPR52733.2024.02679"},{"key":"7_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109696","volume":"142","author":"S Uchigasaki","year":"2023","unstructured":"Uchigasaki, S., Miyazaki, T., Omachi, S.: Deep image compression using scene text quality assessment. Pattern Recogn. 142, 109696 (2023)","journal-title":"Pattern Recogn."},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s10489-023-05251-7","volume":"54","author":"L Yu","year":"2024","unstructured":"Yu, L., Li, X., Yu, Q., Li, G., Jin, D., Qi, M.: Scene text image super-resolution via textual reasoning and multiscale cross-convolution. Appl. Intell. 54, 1997\u20132008 (2024)","journal-title":"Appl. Intell."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, Z., Zhang, L.: A text attention network for spatial deformation robust scene text image super-resolution. arXiv preprint arXiv:2203.09388 (2022)","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"7_CR12","unstructured":"Ye, X., Du, Y., Tao, Y., Chen, Z.: TextSSR: diffusion-based data synthesis for scene text recognition. arXiv preprint arXiv:2412.01137 (2024)"},{"key":"7_CR13","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, C.L., Bhattacharya, S., Pal, U. (eds.) ICPR 2024. LNCS, 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":"7_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., Zhang, S., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognit. 90, 337\u2013345 (2019). arXiv preprint arXiv:1712.02170 (2017)","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of the 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Chng, C.K., Chan, C.S.: Total-Text: a comprehensive dataset for scene text detection and recognition. In: Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). arXiv preprint arXiv:1710.10400 (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"7_CR17","unstructured":"Xie, Y., et al.: DNTextSpotter: arbitrary-shaped scene text spotting via improved denoising training. arXiv preprint arXiv:2408.00355 (2024)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: DeepSolo: let transformer decoder with explicit points solo for text spotting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023). arXiv preprint arXiv:2211.10772 (2022)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. arXiv preprint arXiv:2201.03545 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"7_CR21","unstructured":"DosoViTskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2021)"},{"key":"7_CR22","unstructured":"Ali, M., Touvron, H., Synnaeve, G., J\u00e9gou, H., Cord, M.: XCiT: cross-covariance image transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)"},{"key":"7_CR23","unstructured":"Hatamizadeh, A., Yin, H., Heinrich, G., Kautz, J., Molchanov, P.: Global context vision transformers. arXiv preprint arXiv:2206.09959 (2023)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09368-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:37Z","timestamp":1763921677000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09368-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032093677","9783032093684"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09368-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 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"}}]}}