{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:55:45Z","timestamp":1743094545357,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785100"},{"type":"electronic","value":"9789819785117"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8511-7_26","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:03:08Z","timestamp":1730523788000},"page":"363-377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Not All Texts Are the Same: Dynamically Querying Texts for Scene Text Detection"],"prefix":"10.1007","author":[{"given":"Linjie","family":"Tang","sequence":"first","affiliation":[]},{"given":"Pengfei","family":"Yi","sequence":"additional","affiliation":[]},{"given":"Mingrui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"MingKun","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Liu, Y., Shen, C., et al.: Arbitrarily shaped scene text detection with dynamic convolution. Pattern Recogn. 127, 108608 (2022)","DOI":"10.1016\/j.patcog.2022.108608"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al.: End-to-end object detection with transformers. In: Proceedings of European Conference on Computer Vision, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, R., Zhu, Y., Zhu, Z., Hei, J., Xu, J., Ding, Y.: Semantic-information space sharing interaction network for arbitrary shape text detection. In: Proceedings of Chinese Conference on Pattern Recognition and Computer Vision, pp. 39\u201351. Springer (2023)","DOI":"10.1007\/978-981-99-8540-1_4"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., et\u00a0al.: Dynamic convolution: Attention over convolution kernels. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 11030\u201311039 (2020)","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"26_CR7","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Proc. Adv. Neural Inf. Process. Syst. 34, 17864\u201317875 (2021)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: A comprehensive dataset for scene text detection and recognition. In: Proceedings of International Conference on Document Analysis and Recognition. vol.\u00a01, pp. 935\u2013942 (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., et\u00a0al.: Deformable convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"26_CR10","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 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 7393\u20137402 (2021)","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Dikubab, W., Liang, D., Liao, M., Bai, X.: Comprehensive benchmark datasets for amharic scene text detection and recognition. SCIENCE CHINA Inf. Sci. 65(6), 160106 (2022)","DOI":"10.1007\/s11432-021-3447-9"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"He, M., Liao, M., Yang, Z., et\u00a0al.: Most: A multi-oriented scene text detector with localization refinement. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 8813\u20138822 (2021)","DOI":"10.1109\/CVPR46437.2021.00870"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., et\u00a0al.: Icdar 2015 competition on robust reading. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Kuang, J., Hua, W., Liang, D., Yang, M., Jiang, D., Ren, B., Bai, X.: Visual information extraction in the wild: practical dataset and end-to-end solution. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 36\u201353. Springer (2023)","DOI":"10.1007\/978-3-031-41731-3_3"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Li, B., Yuan, Y., Liang, D., Liu, X., Ji, Z., Bai, J., Liu, W., Bai, X.: When counting meets hmer: counting-aware network for handwritten mathematical expression recognition. In: Proceedings of European Conference on Computer Vision, pp. 197\u2013214. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_12"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Liang, D., Chen, X., Xu, W., Zhou, Y., Bai, X.: Transcrowd: weakly-supervised crowd counting with transformers. SCIENCE CHINA Inf. Sci. 65(6), 160104 (2022)","DOI":"10.1007\/s11432-021-3445-y"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Liang, D., Xie, J., Zou, Z., Ye, X., Xu, W., Bai, X.: Crowdclip: Unsupervised crowd counting via vision-language model. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2893\u20132903 (2023)","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Liang, D., Xu, W., Bai, X.: An end-to-end transformer model for crowd localization. In: Proceedings of European Conference on Computer Vision, pp. 38\u201354. Springer (2022)","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., et\u00a0al.: Textboxes: A fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a031 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"issue":"1","key":"26_CR23","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(1), 919\u2013931 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et\u00a0al.: Ssd: Single shot multibox detector. In: Proceedings of European Conference on Computer Vision, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"26_CR25","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 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., et\u00a0al.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: A flexible representation for detecting text of arbitrary shapes. In: Proceedings of European Conference on Computer Vision, pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"26_CR28","unstructured":"Loshchilov, I., Hutter, F., et\u00a0al.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.051015 (2017)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Ma, H., Yang, C., Yuan, Y., Wang, Q.: Optimal kernel for real-time arbitrary-shaped text detection. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10094734"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., Wang, J.: Conditional detr for fast training convergence. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Nayef, N., Yin, F., Bizid, I., et\u00a0al.: Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt. In: Proceedings of International Conference on Document Analysis and Recognition. vol.\u00a01, pp. 1454\u20131459 (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Su, Y., Shao, Z., Zhou, Y., et\u00a0al.: Textdct: Arbitrary-shaped text detection via discrete cosine transform mask. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3186431"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Sun, X., Lyu, J., Zhang, Y., Zeng, G., Fang, B., Zhou, Y., Xie, E., Ma, C.: Feature enhancement with text-specific region contrast for scene text detection. In: Proceedings of Chinese Conference on Pattern Recognition and Computer Vision, pp. 3\u201314. Springer (2023)","DOI":"10.1007\/978-981-99-8540-1_1"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhang, W., Liu, H., et\u00a0al.: Few could be better than all: Feature sampling and grouping for scene text detection. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 4563\u20134572 (2022)","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Tang, J., Yang, Z., Wang, Y., Zheng, Q., Xu, Y., Bai, X.: Seglink++: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recogn. 96, 106954 (2019)","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"26_CR37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Proc. Adv. Neural Info. Process. Syst. 30 (2017)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., et\u00a0al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., et\u00a0al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of IEEE International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"issue":"11","key":"26_CR40","doi-asserted-by":"publisher","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","volume":"28","author":"Y Xu","year":"2019","unstructured":"Xu, Y., Wang, Y., Zhou, W., Wang, Y., Yang, Z., Bai, X.: Textfield: Learning a deep direction field for irregular scene text detection. IEEE Trans. Image Process. 28(11), 5566\u20135579 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR41","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1083\u20131090 (2012)"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Chen, L., Hou, J.B., Yin, X.C.: Arbitrary shape text detection via segmentation with probability maps. IEEE Transa. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Hou, J.B., et\u00a0al.: Deep relational reasoning graph network for arbitrary shape text detection. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 9699\u20139708 (2020)","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Yang, C., Wang, H., Yin, X.C.: Adaptive boundary proposal network for arbitrary shape text detection. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1305\u20131314 (2021)","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"26_CR45","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., et\u00a0al.: Fourier contour embedding for arbitrary-shaped text detection. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:12:18Z","timestamp":1730524338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}