{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:28:48Z","timestamp":1756384128190,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601189"},{"type":"electronic","value":"9789819601196"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0119-6_42","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:16:19Z","timestamp":1731780979000},"page":"450-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DeepTTS: Enhanced Transformer-Based Text Spotter via\u00a0Deep Interaction Between Detection and\u00a0Recognition Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1623-1949","authenticated-orcid":false,"given":"Yu","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9907-6747","authenticated-orcid":false,"given":"Canhui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2748-5557","authenticated-orcid":false,"given":"Cao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyi","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6154-1411","authenticated-orcid":false,"given":"Qian","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"42_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-58526-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Baek","year":"2020","unstructured":"Baek, Y., et al.: Character region attention for text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXIX. LNCS, vol. 12374, pp. 504\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_30"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Bi, H., et al.: SRRV: a novel document object detector based on spatial-related relation and vision. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3165717"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Bi, H., Xu, C., Shi, C., Liu, G., Zhang, H., Li, Y., Dong, J.: HGR-Net: hierarchical graph reasoning network for arbitrary shape scene text detection. IEEE Trans. Image Process.(2023)","DOI":"10.1109\/TIP.2023.3294822"},{"key":"42_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"42_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Feng, W., He, W., Yin, F., Zhang, X.Y., Liu, C.L.: Textdragon: An end-to-end framework for arbitrary shaped text spotting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9076\u20139085 (2019)","DOI":"10.1109\/ICCV.2019.00917"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: 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, pp. 4593\u20134603 (2022)","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Kittenplon, Y., Lavi, I., Fogel, S., Bar, Y., Manmatha, R., Perona, P.: Towards weakly-supervised text spotting using a multi-task transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134613 (2022)","DOI":"10.1109\/CVPR52688.2022.00456"},{"issue":"1\u20132","key":"42_CR10","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Quart. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quart."},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5238\u20135246 (2017)","DOI":"10.1109\/ICCV.2017.560"},{"key":"42_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-030-58621-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liao","year":"2020","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 706\u2013722. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_41"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: Fots: fast oriented text spotting with a unified network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: ABCNET: real-time scene text spotting with adaptive bezier-curve network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"issue":"11","key":"42_CR16","first-page":"8048","volume":"44","author":"Y Liu","year":"2021","unstructured":"Liu, Y., et al.: Abcnet v2: adaptive Bezier-curve network for real-time end-to-end text spotting. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8048\u20138064 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Spts v2: single-point scene text spotting. arXiv preprint arXiv:2301.01635 (2023)","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"42_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-01264-9_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Lyu","year":"2018","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 71\u201388. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_5"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: Mango: a mask attention guided one-stage scene text spotter. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: Text perceptron: towards end-to-end arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11899\u201311907 (2020)","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Qiao, Q., Xie, Y., Zeng, Z., Li, F.: Talds-Net: task-aware adaptive local descriptors selection for few-shot image classification. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3750\u20133754. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448167"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"42_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-031-19815-1_15","volume-title":"ECCV 2022","author":"R Ronen","year":"2022","unstructured":"Ronen, R., Tsiper, S., Anschel, O., Lavi, I., Markovitz, A., Manmatha, R.: GLASS: global to local attention for scene-text spotting. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 249\u2013266. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_15"},{"key":"42_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: All you need is boundary: toward arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12160\u201312167 (2020)","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: PGNet: real-time arbitrarily-shaped text spotting with point gathering network. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16383"},{"issue":"9","key":"42_CR28","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(9), 5349\u20135367 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR29","unstructured":"Xie, Y., et\u00a0al.: DNTextSpotter: arbitrary-shaped scene text spotting via improved denoising training. arXiv preprint arXiv:2408.00355 (2024)"},{"key":"42_CR30","first-page":"28522","volume":"34","author":"Y Xu","year":"2021","unstructured":"Xu, Y., Zhang, Q., Zhang, J., Tao, D.: Vitae: vision transformer advanced by exploring intrinsic inductive bias. Adv. Neural. Inf. Process. Syst. 34, 28522\u201328535 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: DeepSolo: let transformer decoder with explicit points solo for text spotting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19348\u201319357 (2023)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: Vitaev2: vision transformer advanced by exploring inductive bias for image recognition and beyond. Int. J. Comput. Vis. 1\u201322 (2023)","DOI":"10.1007\/s11263-022-01739-w"},{"key":"42_CR33","doi-asserted-by":"crossref","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, pp. 9519\u20139528 (2022)","DOI":"10.1109\/CVPR52688.2022.00930"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0119-6_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T12:34:15Z","timestamp":1737635655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0119-6_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601189","9789819601196"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0119-6_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}