{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:11:12Z","timestamp":1757455872254,"version":"3.40.3"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416781"},{"type":"electronic","value":"9783031416798"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41679-8_15","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"261-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Decoupling Visual-Semantic Features Learning with\u00a0Dual Masked Autoencoder for\u00a0Self-Supervised Scene Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8942-5907","authenticated-orcid":false,"given":"Zhi","family":"Qiao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8799-3409","authenticated-orcid":false,"given":"Zhilong","family":"Ji","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2822-1564","authenticated-orcid":false,"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8940-480X","authenticated-orcid":false,"given":"Jinfeng","family":"Bai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: CVPR, pp. 15302\u201315312 (2021)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: What if we only use real datasets for scene text recognition? Toward scene text recognition with fewer labels. In: CVPR, pp. 3113\u20133122 (2021)","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"15_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: ICLR (2022)"},{"key":"15_CR4","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19815-1_11","volume-title":"Computer Vision \u2013 ECCV 2022","author":"D Bautista","year":"2022","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13688, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Sain, A., Kumar, A., Ghose, S., Chowdhury, P.N., Song, Y.Z.: Joint visual semantic reasoning: multi-stage decoder for text recognition. In: ICCV, pp. 14940\u201314949 (2021)","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-030-58604-1_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Chao","year":"2020","unstructured":"Chao, L., Chen, J., Chu, W.: Variational connectionist temporal classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 460\u2013476. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_28"},{"key":"15_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. ACM (2020)"},{"key":"15_CR8","unstructured":"Chen, X., et al.: Context autoencoder for self-supervised representation learning. arXiv preprint arXiv:2202.03026 (2022)"},{"key":"15_CR9","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-031-20056-4_7","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Y Chen","year":"2022","unstructured":"Chen, Y., et al.: SdAE: self-distillated masked autoencoder. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13690, pp. 108\u2013124. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_7"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV, pp. 5076\u20135084. IEEE (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"15_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-031-19815-1_19","volume-title":"Computer Vision \u2013 ECCV 2022","author":"C Da","year":"2022","unstructured":"Da, C., Wang, P., Yao, C.: Levenshtein OCR. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13688, pp. 322\u2013338. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_19"},{"key":"15_CR12","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-031-19815-1_20","volume-title":"Computer Vision \u2013 ECCV 2022","author":"C Da","year":"2022","unstructured":"Da, C., Wang, P., Yao, C.: Multi-granularity prediction for scene text recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13688, pp. 339\u2013355. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_20"},{"key":"15_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"15_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-031-20056-4_15","volume-title":"Computer Vision \u2013 ECCV 2022","author":"X Dong","year":"2022","unstructured":"Dong, X., et al.: Bootstrapped masked autoencoders for vision BERT pretraining. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13690, pp. 247\u2013264. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_15"},{"key":"15_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: SVTR: scene text recognition with a single visual model. In: IJCAI, pp. 884\u2013890 (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"key":"15_CR17","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":"15_CR18","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2021)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR, pp. 2315\u20132324. IEEE (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Chen, C.L., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI, pp. 3501\u20133508. AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Visual semantics allow for textual reasoning better in scene text recognition. In: AAAI. AAAI (2021)","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"15_CR24","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., Lin, Z.: GTC: guided training of CTC towards efficient and accurate scene text recognition. In: AAAI, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"issue":"1","key":"15_CR26","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":"15_CR27","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"15_CR29","unstructured":"Krylov, I., Nosov, S., Sovrasov, V.: Open images V5 text annotation and yet another mask text spotter. In: ACML, vol. 157, pp. 379\u2013389. PMLR (2021)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR, pp. 2231\u20132239. IEEE (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: AAAI, pp. 8610\u20138617. AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI, pp. 8714\u20138721 (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Perceiving stroke-semantic context: hierarchical contrastive learning for robust scene text recognition. In: AAAI, pp. 1702\u20131710. AAAI (2021)","DOI":"10.1609\/aaai.v36i2.20062"},{"key":"15_CR34","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"15_CR35","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2016)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Chen, J.: SimAN: exploring self-supervised representation learning of scene text via similarity-aware normalization. In: CVPR, pp. 1039\u20131048 (2022)","DOI":"10.1109\/CVPR52688.2022.00111"},{"key":"15_CR37","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":"15_CR38","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC. BMVA (2012)","DOI":"10.5244\/C.26.127"},{"key":"15_CR39","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-031-21648-0_14","volume-title":"ICFHR 2022","author":"Z Qiao","year":"2022","unstructured":"Qiao, Z., Ji, Z., Yuan, Y., Bai, J.: A vision transformer based scene text recognizer with multi-grained encoding and decoding. In: Porwal, U., Forn\u00e9s, A., Shafait, F. (eds.) ICFHR 2022. LNCS, pp. 198\u2013212. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_14"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Qin, X., Zhou, Y., Yang, F., Wang, W.: Gaussian constrained attention network for scene text recognition. In: ICPR, pp. 3328\u20133335 (2020)","DOI":"10.1109\/ICPR48806.2021.9412806"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Qiao, Z., et al.: PIMNet: a parallel, iterative and mimicking network for scene text recognition. In: MM, pp. 2046\u20132055. ACM (2021)","DOI":"10.1145\/3474085.3475238"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: SEED: semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR, pp. 13525\u201313534. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: ICCV, pp. 569\u2013576. IEEE (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"15_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, vol. 139, pp. 8748\u20138763. PMLR (2021)"},{"issue":"18","key":"15_CR45","first-page":"8027","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. ESA 41(18), 8027\u20138048 (2014)","journal-title":"ESA"},{"issue":"11","key":"15_CR46","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. TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"TPAMI"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168\u20134176. IEEE (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"9","key":"15_CR48","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. TPAMI 41(9), 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: CVPR, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Su, B., Lu, S.: Accurate recognition of words in scenes without character segmentation using recurrent neural network. In: PR, pp. 397\u2013405 (2017)","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Wan, Z., He, M., Chen, H., Bai, X., Yao, C.: TextScanner: reading characters in order for robust scene text recognition. In: AAAI, pp. 12120\u201312127. AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"15_CR52","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464. IEEE (2011)"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network. In: ICCV, pp. 14194\u201314203 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"15_CR55","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-031-20056-4_20","volume-title":"Computer Vision \u2013 ECCV 2022","author":"L Wei","year":"2022","unstructured":"Wei, L., Xie, L., Zhou, W., Li, H., Tian, Q.: MVP: multimodality-guided visual pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13690, pp. 337\u2013353. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_20"},{"key":"15_CR56","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/978-3-031-19815-1_18","volume-title":"Computer Vision \u2013 ECCV 2022","author":"X Xie","year":"2022","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X.: Toward understanding wordArt: corner-guided transformer for scene text recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13688, pp. 303\u2013321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_18"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: CVPR, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Yan, R., Peng, L., Xiao, S., Yao, G.: Primitive representation learning for scene text recognition. In: CVPR, pp. 284\u2013293 (2021)","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Reading and Writing: discriminative and generative modeling for self-supervised text recognition. In: MM, pp. 4214\u20134223. ACM (2022)","DOI":"10.1145\/3503161.3547784"},{"issue":"7","key":"15_CR60","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. TPAMI 37(7), 1480\u20131500 (2014)","journal-title":"TPAMI"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12110\u201312119. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"15_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58529-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yue","year":"2020","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 135\u2013151. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_9"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. In: CVPR, pp. 2059\u20132068. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00216"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: SPIN: structure-preserving inner offset network for scene text recognition. In: AAAI, pp. 3305\u20133314 (2021)","DOI":"10.1609\/aaai.v35i4.16442"},{"key":"15_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41679-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:42:16Z","timestamp":1729935736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}