@article{bb365400,
AUTHOR = "Zheng, T.L. and Chen, Z.N. and Fang, S.C. and Xie, H.T. and Jiang, Y.G.",
TITLE = "CDistNet: Perceiving Multi-domain Character Distance for Robust Text
Recognition",
JOURNAL = IJCV,
VOLUME = "132",
YEAR = "2024",
NUMBER = "2",
MONTH = "February",
PAGES = "300-318",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359594"}
@article{bb365401,
AUTHOR = "Banerjee, A. and Shivakumara, P. and Bhattacharya, S. and Pal, U. and Liu, C.L.",
TITLE = "An end-to-end model for multi-view scene text recognition",
JOURNAL = PR,
VOLUME = "149",
YEAR = "2024",
PAGES = "110206",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359595"}
@article{bb365402,
AUTHOR = "Li, J.N. and Liu, X.Q. and Luo, X. and Xu, X.S.",
TITLE = "VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text
Recognition",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6437-6448",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359596"}
@article{bb365403,
AUTHOR = "Yang, X.M. and Qiao, Z. and Wei, J. and Yang, D. and Zhou, Y.",
TITLE = "Masked and Permuted Implicit Context Learning for Scene Text
Recognition",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "964-968",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359597"}
@article{bb365404,
AUTHOR = "Xiong, L. and Mao, Y.C. and Wang, Z.C. and Nie, B.B. and Li, C.",
TITLE = "Cross-modal knowledge learning with scene text for fine-grained image
classification",
JOURNAL = IET-IPR,
VOLUME = "18",
YEAR = "2024",
NUMBER = "6",
PAGES = "1447-1459",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359598"}
@article{bb365405,
AUTHOR = "Zhou, J.Q. and Dai, P.W. and Li, Y. and Hu, M.J. and Cao, X.C.",
TITLE = "Explicitly-Decoupled Text Transfer With Minimized Background
Reconstruction for Scene Text Editing",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "5921-5935",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359599"}
@article{bb365406,
AUTHOR = "Zhou, D. and Zhang, J.X. and Li, C.",
TITLE = "DiZNet: An end-to-end text detection and recognition algorithm with
detail in text zone",
JOURNAL = JVCIR,
VOLUME = "104",
YEAR = "2024",
PAGES = "104261",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359600"}
@inproceedings{bb365407,
AUTHOR = "Peng, M.Z. and Cheng, H.C. and Le, P.T. and Wang, C.C. and Wang, C.Y. and Wang, J.C.",
TITLE = "Scene Text Recognition Using Progressive Rectification Network And
Spelling Error Correction Language Model",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "2008-2014",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359601"}
@article{bb365408,
AUTHOR = "Wan, H.Y. and Liu, R. and Yu, L.",
TITLE = "Double supervision for scene text detection and recognition based on
BMINet",
JOURNAL = SP:IC,
VOLUME = "130",
YEAR = "2025",
PAGES = "117226",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359602"}
@article{bb365409,
AUTHOR = "Xue, F. and Sun, J. and Xue, Y.Q. and Wu, Q. and Zhu, L. and Chang, X.J. and Cheung, S.C.",
TITLE = "Attention Guidance by Cross-Domain Supervision Signals for Scene Text
Recognition",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "717-728",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359603"}
@article{bb365410,
AUTHOR = "Du, Y.K. and Chen, Z. and Su, Y.C. and Jia, C.Y. and Jiang, Y.G.",
TITLE = "Instruction-Guided Scene Text Recognition",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "2723-2738",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359604"}
@article{bb365411,
AUTHOR = "Guan, T.K. and Shen, W. and Yang, X.K.",
TITLE = "CCDPlus: Towards Accurate Character to Character Distillation for
Text Recognition",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3546-3562",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359605"}
@inproceedings{bb365412,
AUTHOR = "Guan, T.K. and Shen, W. and Yang, X. and Feng, Q. and Jiang, Z.K. and Yang, X.K.",
TITLE = "Self-supervised Character-to-Character Distillation for Text
Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "19416-19427",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359606"}
@article{bb365413,
AUTHOR = "Zhang, Z.Y. and Zhang, Y.P. and Liang, Y. and Ma, C. and Xiang, L. and Zhao, Y. and Zhou, Y. and Zong, C.Q.",
TITLE = "Understand Layout and Translate Text: Unified Feature-Conductive
End-to-End Document Image Translation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3358-3376",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359607"}
@article{bb365414,
AUTHOR = "Du, Y.K. and Chen, Z.N. and Jia, C.Y. and Yin, X.T. and Li, C.X. and Du, Y.N. and Jiang, Y.G.",
TITLE = "Context Perception Parallel Decoder for Scene Text Recognition",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "6",
MONTH = "June",
PAGES = "4668-4683",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359608"}
@article{bb365415,
AUTHOR = "Yang, X.M. and Qiao, Z. and Zhou, Y.",
TITLE = "IPAD: Iterative, Parallel, and Diffusion-Based Network for Scene Text
Recognition",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5589-5609",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359609"}
@article{bb365416,
AUTHOR = "Liu, X.Q. and Chen, Z.D. and Luo, X. and Xu, X.S.",
TITLE = "Self-Supervised Discovery of Cross-Lingual Shared Knowledge for
Continual Text Recognition",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "6524-6536",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359610"}
@article{bb365417,
AUTHOR = "Fang, C.Y. and Jiang, W.H. and Fang, Y.M. and Peng, Y.X. and Liu, Y.",
TITLE = "Separate, Locate, and Align: Determine Context Relation of Scene Text
From Multiple Perspectives in TextVQA",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11172-11185",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359611"}
@article{bb365418,
AUTHOR = "Da, C. and Wang, P. and Yao, C.",
TITLE = "Multi-Granularity Prediction with Learnable Fusion for Scene Text
Recognition",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "47",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359612"}
@inproceedings{bb365419,
AUTHOR = "Wang, P. and Da, C. and Yao, C.",
TITLE = "Multi-granularity Prediction for Scene Text Recognition",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:339-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359613"}
@article{bb365420,
AUTHOR = "Liu, D. and Wang, T.L. and Lin, Z.P. and Cao, J.W.",
TITLE = "Summarize Before Glimpse: Brain-Inspired Non-Autoregressive Scene
Text Recognizer",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "3131-3144",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359614"}
@article{bb365421,
AUTHOR = "Chen, H.H. and Qiu, Y.H. and Wang, J. and Chen, P.P. and Ling, N.",
TITLE = "HAAP: Vision-Context Hierarchical Attention Autoregressive With
Adaptive Permutation for Scene Text Recognition",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "1523-1533",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359615"}
@article{bb365422,
AUTHOR = "Tang, Z. and Mitsui, Y. and Miyazaki, T. and Omachi, S.",
TITLE = "Multi-masking strategies for self-supervised Low- and High-level text
representation learning",
JOURNAL = PR,
VOLUME = "177",
YEAR = "2026",
PAGES = "113273",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359616"}
@article{bb365423,
AUTHOR = "Yu, W.W. and Yang, Z.B. and Wan, J.Q. and Song, S. and Tang, J. and Cheng, W.Q. and Liu, Y.L. and Bai, X.",
TITLE = "OmniParser V2: Structured-Points-of-Thought for Unified Visual Text
Parsing and Its Generality to Multimodal Large Language Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "9210-9227",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359617"}
@inproceedings{bb365424,
AUTHOR = "Maracani, A. and Ozkan, S. and Cho, S. and Kim, H.W. and Noh, E. and Min, J. and Min, C.J. and Park, D. and Ozay, M.",
TITLE = "Accurate Scene Text Recognition with Efficient Model Scaling and
Cloze Self-Distillation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14516-14526",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359618"}
@inproceedings{bb365425,
AUTHOR = "Le, K.N. and Nguyen, H.T. and Tran, H.T. and Ngo, T.D.",
TITLE = "Stratified Domain Adaptation: A Progressive Self-Training Approach
for Scene Text Recognition",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8990-9000",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359619"}
@inproceedings{bb365426,
AUTHOR = "Wang, P. and Li, Z. and Tang, J. and Zhong, H. and Huang, F. and Yang, Z.B. and Yao, C.",
TITLE = "Platypus: A Generalized Specialist Model for Reading Text in Various
Forms",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXV: 165-183",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359620"}
@inproceedings{bb365427,
AUTHOR = "Xu, J.J. and Wang, Y.X. and Xie, H.T. and Zhang, Y.D.",
TITLE = "OTE: Exploring Accurate Scene Text Recognition Using One Token",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28327-28336",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359621"}
@inproceedings{bb365428,
AUTHOR = "Liang, M. and Ma, J.W. and Zhu, X.B. and Qin, J.Y. and Yin, X.C.",
TITLE = "LayoutFormer: Hierarchical Text Detection Towards Scene Text
Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15665-15674",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359622"}
@inproceedings{bb365429,
AUTHOR = "Rang, M. and Bi, Z. and Liu, C. and Wang, Y.H. and Han, K.",
TITLE = "An Empirical Study of Scaling Law for Scene Text Recognition",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15619-15629",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359623"}
@inproceedings{bb365430,
AUTHOR = "Zhao, Z. and Tang, J.Q. and Lin, C.H. and Wu, B.H. and Huang, C. and Liu, H. and Tan, X. and Zhang, Z.Z. and Xie, Y.",
TITLE = "Multi-modal In-Context Learning Makes an Ego-evolving Scene Text
Recognizer",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15567-15576",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359624"}
@inproceedings{bb365431,
AUTHOR = "Nguyen, C.M. and Chan, E.R. and Bergman, A.W. and Wetzstein, G.",
TITLE = "Diffusion in the Dark:
A Diffusion Model for Low-Light Text Recognition",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4134-4145",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359625"}
@inproceedings{bb365432,
AUTHOR = "Deshmukh, G. and Susladkar, O. and Makwana, D. and Mittal, S. and Teja, R.S.C.",
TITLE = "Textual Alchemy: CoFormer for Scene Text Understanding",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "2919-2929",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359626"}
@inproceedings{bb365433,
AUTHOR = "Santoso, J. and Simon, C. and Williem",
TITLE = "On Manipulating Scene Text in the Wild with Diffusion Models",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5190-5199",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359627"}
@inproceedings{bb365434,
AUTHOR = "Kim, D. and Kim, Y. and Kim, D. and Lim, Y.M. and Kim, G. and Kil, T.",
TITLE = "SCOB: Universal Text Understanding via Character-wise Supervised
Contrastive Learning with Online Text Rendering for Bridging Domain
Gap",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "19505-19516",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359628"}
@inproceedings{bb365435,
AUTHOR = "Jiang, Q. and Wang, J.P. and Peng, D.Z. and Liu, C.Y. and Jin, L.W.",
TITLE = "Revisiting Scene Text Recognition: A Data Perspective",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20486-20497",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359629"}
@inproceedings{bb365436,
AUTHOR = "Cheng, C.X. and Wang, P. and Da, C. and Zheng, Q. and Yao, C.",
TITLE = "LISTER: Neighbor Decoding for Length-Insensitive Scene Text
Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "19484-19494",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359630"}
@inproceedings{bb365437,
AUTHOR = "Aberdam, A. and Bensaid, D. and Golts, A. and Ganz, R. and Nuriel, O. and Tichauer, R. and Mazor, S. and Litman, R.",
TITLE = "CLIPTER: Looking at the Bigger Picture in Scene Text Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "21649-21660",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359631"}
@inproceedings{bb365438,
AUTHOR = "Zheng, T.L. and Chen, Z. and Huang, B.C. and Zhang, W. and Jiang, Y.G.",
TITLE = "MRN: Multiplexed Routing Network for Incremental Multilingual Text
Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "18598-18607",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359632"}
@inproceedings{bb365439,
AUTHOR = "Fujitake, M.",
TITLE = "DiffusionSTR: Diffusion Model for Scene Text Recognition",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1585-1589",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359633"}
@inproceedings{bb365440,
AUTHOR = "Orihashi, S. and Yamazaki, Y. and Uchida, M. and Takashima, A. and Masumura, R.",
TITLE = "Distilling Knowledge of Bidirectional Language Model for Scene Text
Recognition",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2165-2169",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359634"}
@inproceedings{bb365441,
AUTHOR = "Tien, H.T. and Ngo, T.D.",
TITLE = "Unsupervised Domain Adaptation with Imbalanced Character Distribution
for Scene Text Recognition",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "3493-3497",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359635"}
@inproceedings{bb365442,
AUTHOR = "Ty, M.V. and Atienza, R.",
TITLE = "Scene Text Recognition Models Explainability Using Local Features",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "645-649",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359636"}
@inproceedings{bb365443,
AUTHOR = "Slossberg, R. and Anschel, O. and Markovitz, A. and Litman, R. and Aberdam, A. and Tsiper, S. and Mazor, S. and Wu, J. and Manmatha, R.",
TITLE = "On Calibration of Scene-text Recognition Models",
BOOKTITLE = TextEvery22,
YEAR = "2022",
PAGES = "263-279",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359637"}
@inproceedings{bb365444,
AUTHOR = "Gao, M. and Wu, S. and Wang, Z.F.",
TITLE = "A Length-sensitive Language-bound Recognition Network for Multilingual
Text Recognition",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "II: 139-150",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359638"}
@inproceedings{bb365445,
AUTHOR = "Patel, G. and Allebach, J. and Qiu, Q.",
TITLE = "Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for
Semi-Supervised Text Recognition",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "6169-6179",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359639"}
@inproceedings{bb365446,
AUTHOR = "Chu, X.J. and Wang, Y.T.",
TITLE = "IterVM: Iterative Vision Modeling Module for Scene Text Recognition",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1393-1399",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359640"}
@inproceedings{bb365447,
AUTHOR = "Fu, J.M. and Xu, S.Y. and Liu, H.D. and Liu, Y. and Xie, N. and Wang, C.C. and Liu, J. and Sun, Y. and Wang, B.",
TITLE = "CMA-CLIP: Cross-Modality Attention Clip for Text-Image Classification",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2846-2850",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359641"}
@inproceedings{bb365448,
AUTHOR = "Na, B. and Kim, Y. and Park, S.",
TITLE = "Multi-modal Text Recognition Networks:
Interactive Enhancements Between Visual and Semantic Features",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:446-463",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359642"}
@inproceedings{bb365449,
AUTHOR = "Nuriel, O. and Fogel, S. and Litman, R.",
TITLE = "TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:427-445",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359643"}
@inproceedings{bb365450,
AUTHOR = "Tang, J.Q. and Qian, W.M. and Song, L. and Dong, X. and Li, L. and Bai, X.",
TITLE = "Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting
Annotated Bounding Boxes via Reinforcement Learning",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:233-248",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359644"}
@inproceedings{bb365451,
AUTHOR = "Bautista, D. and Atienza, R.",
TITLE = "Scene Text Recognition with Permuted Autoregressive Sequence Models",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:178-196",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359645"}
@inproceedings{bb365452,
AUTHOR = "Zhao, L. and Wu, Z.Y. and Wu, X. and Wilsbacher, G. and Wang, S.",
TITLE = "Background-Insensitive Scene Text Recognition with Text Semantic
Segmentation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXV:163-182",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359646"}
@inproceedings{bb365453,
AUTHOR = "Chang, Y.C. and Chen, Y.C. and Chang, Y.C. and Yeh, Y.R.",
TITLE = "Smile: Sequence-to-Sequence Domain Adaptation with Minimizing Latent
Entropy for Text Image Recognition",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "431-435",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359647"}
@inproceedings{bb365454,
AUTHOR = "Tan, Y.L. and Kong, A.W.K. and Kim, J.J.",
TITLE = "Pure Transformer with Integrated Experts for Scene Text Recognition",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:481-497",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359648"}
@inproceedings{bb365455,
AUTHOR = "Xie, X.D. and Fu, L. and Zhang, Z.F. and Wang, Z.W. and Bai, X.",
TITLE = "Toward Understanding WordArt: Corner-Guided Transformer for Scene Text
Recognition",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:303-321",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359649"}
@inproceedings{bb365456,
AUTHOR = "Xue, C.H. and Zhang, W.Q. and Hao, Y. and Lu, S.J. and Torr, P.H.S. and Bai, S.",
TITLE = "Language Matters: A Weakly Supervised Vision-Language Pre-training
Approach for Scene Text Detection and Spotting",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:284-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359650"}
@inproceedings{bb365457,
AUTHOR = "Orihashi, S. and Yamazaki, Y. and Uchida, M. and Takashima, A. and Masumura, R.",
TITLE = "Fully Shareable Scene Text Recognition Modeling for Horizontal and
Vertical Writing",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2636-2640",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359651"}
@inproceedings{bb365458,
AUTHOR = "Zheng, C. and Li, H. and Rhee, S.M. and Han, S. and Han, J.J. and Wang, P.",
TITLE = "Pushing the Performance Limit of Scene Text Recognizer without Human
Annotation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "14096-14105",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359652"}
@inproceedings{bb365459,
AUTHOR = "Wang, H. and Liao, J.C. and Cheng, T.H. and Gao, Z. and Liu, H. and Ren, B. and Bai, X. and Liu, W.Y.",
TITLE = "Knowledge Mining with Scene Text for Fine-Grained Recognition",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "4614-4623",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359653"}
@inproceedings{bb365460,
AUTHOR = "Long, S.B. and Qin, S.Y. and Panteleev, D. and Bissacco, A. and Fujii, Y. and Raptis, M.",
TITLE = "Towards End-to-End Unified Scene Text Detection and Layout Analysis",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "1039-1049",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359654"}
@inproceedings{bb365461,
AUTHOR = "Gomez, A.S. and Castano, J.G. and Leskovsky, P. and Madurga, O.O.",
TITLE = "PolygloNet: Multilingual Approach for Scene Text Recognition Without
Language Constraints",
BOOKTITLE = CIAP22,
YEAR = "2022",
PAGES = "II:479-490",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359655"}
@inproceedings{bb365462,
AUTHOR = "Shuai, X. and Wang, X. and Wang, W. and Yuan, X. and Xu, X.",
TITLE = "SAM: Self Attention Mechanism for Scene Text Recognition Based on Swin
Transformer",
BOOKTITLE = MMMod22,
YEAR = "2022",
PAGES = "I:443-454",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359656"}
@inproceedings{bb365463,
AUTHOR = "Bhunia, A.K. and Sain, A. and Kumar, A. and Ghose, S. and Chowdhury, P.N. and Song, Y.Z.",
TITLE = "Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text
Recognition",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14920-14929",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359657"}
@inproceedings{bb365464,
AUTHOR = "Yang, M.K. and Zheng, H. and Bai, X. and Luo, J.B.",
TITLE = "Cost-Effective Adversarial Attacks against Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "2368-2374",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359658"}
@inproceedings{bb365465,
AUTHOR = "Dasgupta, K. and Das, S. and Bhattacharya, U.",
TITLE = "Stratified Multi-Task Learning for Robust Spotting of Scene Texts",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3130-3137",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359659"}
@inproceedings{bb365466,
AUTHOR = "Qiao, Z. and Qin, X. and Zhou, Y. and Yang, F. and Wang, W.P.",
TITLE = "Gaussian Constrained Attention Network for Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3328-3335",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359660"}
@inproceedings{bb365467,
AUTHOR = "Zhou, J.W. and Gao, H.C. and Dai, J. and Liu, D.Q. and Han, J.Z.",
TITLE = "A Multi-head Self-relation Network for Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3969-3976",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359661"}
@inproceedings{bb365468,
AUTHOR = "Yan, R.J. and Peng, L.R. and Xiao, S. and Yao, G. and Min, J.",
TITLE = "MEAN: Multi - Element Attention Network for Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359662"}
@inproceedings{bb365469,
AUTHOR = "Meng, G.H. and Dai, T. and Wu, S.D. and Chen, B. and Lu, J. and Jiang, Y. and Xia, S.T.",
TITLE = "Sample-aware Data Augmentor for Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3978-3985",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359663"}
@inproceedings{bb365470,
AUTHOR = "Gu, C.Y. and Wang, S.L. and Zhu, Y.W. and Huang, Z. and Chen, K.",
TITLE = "Weakly Supervised Attention Rectification for Scene Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "779-786",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359664"}
@inproceedings{bb365471,
AUTHOR = "Bhunia, A.K. and Chowdhury, P.N. and Sain, A. and Song, Y.Z.",
TITLE = "Towards the Unseen:
Iterative Text Recognition by Distilling from Errors",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14930-14939",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359665"}
@inproceedings{bb365472,
AUTHOR = "Wang, Y.X. and Xie, H.T. and Fang, S.C. and Wang, J. and Zhu, S.G. and Zhang, Y.D.",
TITLE = "From Two to One: A New Scene Text Recognizer with Visual Language
Modeling Network",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14174-14183",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359666"}
@inproceedings{bb365473,
AUTHOR = "Bhunia, A.K. and Sain, A. and Chowdhury, P.N. and Song, Y.Z.",
TITLE = "Text is Text, No Matter What: Unifying Text Recognition using
Knowledge Distillation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "963-972",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359667"}
@inproceedings{bb365474,
AUTHOR = "Gupta, K. and Lazarow, J. and Achille, A. and Davis, L. and Mahadevan, V. and Shrivastava, A.",
TITLE = "LayoutTransformer: Layout Generation and Completion with
Self-attention",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "984-994",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359668"}
@inproceedings{bb365475,
AUTHOR = "Bhunia, A.K. and Khan, S. and Cholakkal, H. and Anwer, R.M. and Khan, F.S. and Shah, M.",
TITLE = "Handwriting Transformers",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1066-1074",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359669"}
@inproceedings{bb365476,
AUTHOR = "Zheng, Y. and Wang, Q.T. and Betke, M.",
TITLE = "Semantic-Based Sentence Recognition in Images Using Bimodal Deep
Learning",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "2753-2757",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359670"}
@inproceedings{bb365477,
AUTHOR = "Huang, Y.L. and Wang, S.L. and Gu, C.Y. and Huang, Z. and Chen, K.",
TITLE = "A Seq2seq-based Model with Global Semantic Context for Scene Text
Recognition",
BOOKTITLE = DICTA21,
YEAR = "2021",
PAGES = "01-06",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359671"}
@inproceedings{bb365478,
AUTHOR = "Kim, Y.G. and Kim, H. and Kang, M. and Lee, H.J. and Lee, R. and Park, G.",
TITLE = "Analysis of the Novel Transformer Module Combination for Scene Text
Recognition",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "1229-1233",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359672"}
@inproceedings{bb365479,
AUTHOR = "Atienza, R.",
TITLE = "Data Augmentation for Scene Text Recognition",
BOOKTITLE = ILDAV21,
YEAR = "2021",
PAGES = "1561-1570",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359673"}
@inproceedings{bb365480,
AUTHOR = "Aberdam, A. and Litman, R. and Tsiper, S. and Anschel, O. and Slossberg, R. and Mazor, S. and Manmatha, R. and Perona, P.",
TITLE = "Sequence-to-Sequence Contrastive Learning for Text Recognition",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "15297-15307",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359674"}
@inproceedings{bb365481,
AUTHOR = "Nguyen, N. and Nguyen, T. and Tran, V. and Tran, M.T. and Ngo, T.D. and Nguyen, T.H. and Hoai, M.",
TITLE = "Dictionary-guided Scene Text Recognition",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "7379-7388",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359675"}
@inproceedings{bb365482,
AUTHOR = "Baek, J. and Matsui, Y. and Aizawa, K.",
TITLE = "What If We Only Use Real Datasets for Scene Text Recognition?
Toward Scene Text Recognition With Fewer Labels",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "3112-3121",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359676"}
@inproceedings{bb365483,
AUTHOR = "Yan, R. and Peng, L.R. and Xiao, S. and Yao, G.",
TITLE = "Primitive Representation Learning for Scene Text Recognition",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "284-293",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359677"}
@inproceedings{bb365484,
AUTHOR = "Charles, J. and Bucciarelli, S. and Cipolla, R.",
TITLE = "Scaling digital screen reading with one-shot learning and
re-identification",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "2634-2642",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359678"}
@inproceedings{bb365485,
AUTHOR = "Xu, Z.L. and Zhou, S.G. and Bai, F. and Cheng, Z.Z. and Niu, Y. and Pu, S.L.",
TITLE = "Recognizing Multiple Text Sequences from an Image by Pure End-to-End
Learning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7058-7065",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359679"}
@inproceedings{bb365486,
AUTHOR = "Bulatov, K. and Fedotova, N. and Arlazarov, V.V.",
TITLE = "Fast Approximate Modelling of the Next Combination Result for
Stopping the Text Recognition in a Video",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "239-246",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359680"}
@inproceedings{bb365487,
AUTHOR = "Song, Q. and Jiang, Q.Y. and Li, N. and Zhang, R. and Wei, X.L.",
TITLE = "ReADS: A Rectified Attentional Double Supervised Network for Scene
Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "1649-1656",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359681"}
@inproceedings{bb365488,
AUTHOR = "Janouskova, K. and Matas, J.G. and Gomez, L. and Karatzas, D.",
TITLE = "Text Recognition - Real World Data and Where to Find Them",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "4489-4496",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359682"}
@article{bb365489,
AUTHOR = "Chen, Z. and Yin, F. and Yang, Q. and Liu, C.L.",
TITLE = "Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal
Mimic",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4830-4841",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359683"}
@inproceedings{bb365490,
AUTHOR = "Chen, Z. and Yin, F. and Zhang, X.Y. and Yang, Q. and Liu, C.L.",
TITLE = "Cross-Lingual Text Image Recognition via Multi-Task Sequence to
Sequence Learning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3122-3129",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359684"}
@inproceedings{bb365491,
AUTHOR = "Song, Q. and Jiang, Q.Y. and Zhang, R. and Wei, X.L.",
TITLE = "Robust Lexicon-Free Confidence Prediction for Text Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3232-3239",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359685"}
@inproceedings{bb365492,
AUTHOR = "Liu, T.F. and Hu, Y.L. and Gao, J.B. and Sun, Y.F. and Yin, B.C.",
TITLE = "Zero-Shot Text Classification with Semantically Extended Graph
Convolutional Network",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "8352-8359",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359686"}
@inproceedings{bb365493,
AUTHOR = "Lin, J.H. and Cheng, Z.Z. and Bai, F. and Niu, Y. and Pu, S.L. and Zhou, S.G.",
TITLE = "Text Recognition in Real Scenarios with a Few Labeled Samples",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "370-377",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359687"}
@inproceedings{bb365494,
AUTHOR = "Li, L.C. and Gao, F.Y. and Bu, J.J. and Wang, Y.P. and Yu, Z. and Zheng, Q.",
TITLE = "An End-to-end OCR Text Re-organization Sequence Learning for Rich-text
Detail Image Comprehension",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXV:85-100",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359688"}
@inproceedings{bb365495,
AUTHOR = "Mou, Y.Q. and Tan, L. and Yang, H. and Chen, J.Y. and Liu, L.Y. and Yan, R. and Huang, Y.H.",
TITLE = "Plugnet: Degradation Aware Scene Text Recognition Supervised by a
Pluggable Super-resolution Unit",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XV:158-174",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359689"}
@inproceedings{bb365496,
AUTHOR = "Chang, M.C. and Zhao, G. and Pandey, A.K. and Pulver, A. and Tu, P.",
TITLE = "Railcar Detection, Identification and Tracking for Rail Yard
Management",
BOOKTITLE = ICIP20,
YEAR = "2020",
PAGES = "2271-2275",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359690"}
@inproceedings{bb365497,
AUTHOR = "Yue, X.Y. and Kuang, Z.H. and Lin, C.H. and Sun, H.B. and Zhang, W.",
TITLE = "Robustscanner: Dynamically Enhancing Positional Clues for Robust Text
Recognition",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XIX:135-151",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359691"}
@inproceedings{bb365498,
AUTHOR = "Yang, Q. and Huang, J. and Lin, W.",
TITLE = "SwapText: Image Based Texts Transfer in Scenes",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "14688-14697",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359692"}
@inproceedings{bb365499,
AUTHOR = "Wang, Q. and Zheng, Y. and Betke, M.",
TITLE = "A method for detecting text of arbitrary shapes in natural scenes
that improves text spotting",
BOOKTITLE = WTDDL20,
YEAR = "2020",
PAGES = "2296-2305",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT359693"}
Last update:Aug 19, 2026 at 13:26:35