{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:10:16Z","timestamp":1743099016661,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781247"},{"type":"electronic","value":"9783031781254"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-78125-4_22","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T06:08:11Z","timestamp":1733292491000},"page":"316-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MPGTSRN: Scene Text Image Super-Resolution Guided by\u00a0Multiple Visual-Semantic Prompts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8831-1191","authenticated-orcid":false,"given":"Mingjun","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3129-6015","authenticated-orcid":false,"given":"Zeming","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1394-3550","authenticated-orcid":false,"given":"Shuo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8426-9634","authenticated-orcid":false,"given":"Feng","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: EECV, pp. 178\u2013196. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Wang, X., Xu, X., Gu, J., Loy, C.C.: GLEAN: generative latent bank for large-factor image super-resolution. In: CVPR, pp. 14240\u201314249 (2021)","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Li, B., Xue, X.: Scene text telescope: text-focused scene image super-resolution. In: CVPR, pp. 12021\u201312030 (2021)","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Yu, H., Ma, J., Li, B., Xue, X.: Text gestalt: stroke-aware scene text image super-resolution. In: AAAI. vol.\u00a036, pp. 285\u2013293 (2022)","DOI":"10.1609\/aaai.v36i1.19904"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: CVPR, pp. 11030\u201311039 (2020)","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Dong, C., Chen, C.L., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: ECCV, pp. 184\u2013199 (2014)","DOI":"10.1007\/978-3-319-10593-2_13"},{"issue":"2","key":"22_CR7","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2016","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE TPAMI 38(2), 295\u2013307 (2016)","journal-title":"IEEE TPAMI"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: CVPR, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Guo, H., Dai, T., Meng, G., Xia, S.T.: Towards robust scene text image super-resolution via explicit location enhancement. In: IJCAI, pp. 782\u2013790 (2023)","DOI":"10.24963\/ijcai.2023\/87"},{"issue":"1","key":"22_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. IJCV 116(1), 1\u201320 (2016)","journal-title":"IJCV"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Ledig, C., et\u00a0al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Liang, J., Zeng, H., Zhang, L.: Details or artifacts: a locally discriminative learning approach to realistic image super-resolution. In: CVPR, pp. 5647\u20135656 (2022)","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: CVPRW, pp. 1132\u20131140 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. PR 90, 109\u2013118 (2019)","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"22_CR15","first-page":"1341","volume":"32","author":"J Ma","year":"2023","unstructured":"Ma, J., Guo, S., Zhang, L.: Text prior guided scene text image super-resolution. TIP 32, 1341\u20131353 (2023)","journal-title":"TIP"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, Z., Zhang, L.: A text attention network for spatial deformation robust scene text image super-resolution. In: CVPR, pp. 5901\u20135910 (2022)","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Na, B., Kim, Y., Park, S.: Multi-modal text recognition networks: interactive enhancements between visual and semantic features. In: ECCV, pp. 446\u2013463. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Niu, B., et al.: Single image super-resolution via a holistic attention network. In: ECCV, pp. 191\u2013207. Springer (2020)","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Peyrard, C., Baccouche, M., Mamalet, F., Garcia, C.: ICDAR2015 competition on text image super-resolution. In: ICDAR, pp. 1201\u20131205 (2015)","DOI":"10.1109\/ICDAR.2015.7333951"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Qi, Y., He, Y., Qi, X., Zhang, Y., Yang, G.: Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation. In: ICCV, pp. 6070\u20136079 (2023)","DOI":"10.1109\/ICCV51070.2023.00558"},{"issue":"11","key":"22_CR21","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"IEEE TPAMI"},{"issue":"9","key":"22_CR22","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE TPAMI 41(9), 2035\u20132048 (2018)","journal-title":"IEEE TPAMI"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"22_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Scene text image super-resolution in the wild. In: ECCV, pp. 650\u2013666. Springer International Publishing, Cham (2020)","DOI":"10.1007\/978-3-030-58607-2_38"},{"issue":"4","key":"22_CR26","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Pixel adapter: a graph-based post-processing approach for scene text image super-resolution. In: ACM MM, pp. 2168\u20132179 (2023)","DOI":"10.1145\/3581783.3611913"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: CVPR, pp. 2472\u20132481 (2018)","DOI":"10.1109\/CVPR.2018.00262"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Scene text image super-resolution via parallelly contextual attention network. In: ACM MM, pp. 2908\u20132917 (2021)","DOI":"10.1145\/3474085.3475469"},{"key":"22_CR30","unstructured":"Zhao, G., Lin, J., Zhang, Z., Ren, X., Su, Q., Sun, X.: Explicit sparse transformer: Concentrated attention through explicit selection (2019)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, M., Bai, F., Li, B., Wang, J., Zhou, S.: C3-STISR: scene text image super-resolution with triple clues. In: IJCAI, pp. 1707\u20131713 (2022)","DOI":"10.24963\/ijcai.2022\/238"},{"key":"22_CR32","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Gao, L., Tang, Z., Wei, B.: Recognition-guided diffusion model for scene text image super-resolution. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2940\u20132944 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447585","DOI":"10.1109\/ICASSP48485.2024.10447585"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, X., Guo, K., Fang, H., Ding, R., Wu, Z., Schaefer, G.: Gradient-based graph attention for scene text image super-resolution. In: AAAI. vol.\u00a037, pp. 3861\u20133869 (2023)","DOI":"10.1609\/aaai.v37i3.25499"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78125-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:07:42Z","timestamp":1733296062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78125-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781247","9783031781254"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78125-4_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}