@inproceedings{bb368800,
AUTHOR = "Raisi, Z. and Naiel, M.A. and Younes, G. and Wardell, S. and Zelek, J.",
TITLE = "2LSPE: 2D Learnable Sinusoidal Positional Encoding using Transformer
for Scene Text Recognition",
BOOKTITLE = CRV21,
YEAR = "2021",
PAGES = "119-126",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362976"}
@article{bb368801,
AUTHOR = "Gomez, L. and Biten, A.F. and Tito, R. and Mafla, A. and Rusinol, M. and Valveny, E. and Karatzas, D.",
TITLE = "Multimodal grid features and cell pointers for scene text visual
question answering",
JOURNAL = PRL,
VOLUME = "150",
YEAR = "2021",
PAGES = "242-249",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362977"}
@inproceedings{bb368802,
AUTHOR = "Biten, A.F. and Tito, R. and Mafla, A. and Gomez, L. and Rusinol, M. and Jawahar, C.V. and Valveny, E. and Karatzas, D.",
TITLE = "Scene Text Visual Question Answering",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4290-4300",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362978"}
@article{bb368803,
AUTHOR = "Chmielewski, S.",
TITLE = "Towards Managing Visual Pollution: A 3D Isovist and Voxel Approach to
Advertisement Billboard Visual Impact Assessment",
JOURNAL = IJGI,
VOLUME = "10",
YEAR = "2021",
NUMBER = "10",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362979"}
@article{bb368804,
AUTHOR = "Rong, X.J. and Yi, C.C. and Tian, Y.L.",
TITLE = "Unambiguous Text Localization, Retrieval, and Recognition for
Cluttered Scenes",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "3",
MONTH = "March",
PAGES = "1638-1652",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362980"}
@inproceedings{bb368805,
AUTHOR = "Rong, X.J. and Yi, C.C. and Tian, Y.L.",
TITLE = "Unambiguous Text Localization and Retrieval for Cluttered Scenes",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "3279-3287",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362981"}
@inproceedings{bb368806,
AUTHOR = "Rong, X.J. and Yi, C.C. and Tian, Y.L.",
TITLE = "Recognizing Text-Based Traffic Guide Panels with Cascaded Localization
Network",
BOOKTITLE = CVRoads16,
YEAR = "2016",
PAGES = "I: 109-121",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362982"}
@article{bb368807,
AUTHOR = "Li, B.C. and Tang, X. and Qi, X.B. and Chen, Y.H. and Li, C.G. and Xiao, R.",
TITLE = "EMU: Effective Multi-Hot Encoding Net for Lightweight Scene Text
Recognition With a Large Character Set",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "8",
MONTH = "August",
PAGES = "5374-5385",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362983"}
@article{bb368808,
AUTHOR = "Wang, Y.X. and Xie, H.T. and Fang, S.C. and Xing, M.T. and Wang, J. and Zhu, S.G. and Zhang, Y.D.",
TITLE = "PETR: Rethinking the Capability of Transformer-Based Language Model
in Scene Text Recognition",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "5585-5598",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362984"}
@article{bb368809,
AUTHOR = "Liu, C. and Yang, C. and Qin, H.B. and Zhu, X.B. and Liu, C.L. and Yin, X.C.",
TITLE = "Towards open-set text recognition via label-to-prototype learning",
JOURNAL = PR,
VOLUME = "134",
YEAR = "2023",
PAGES = "109109",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362985"}
@inproceedings{bb368810,
AUTHOR = "Liu, C. and Yang, C. and Yin, X.C.",
TITLE = "Open-Set Text Recognition via Character-Context Decoupling",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "4513-4522",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362986"}
@article{bb368811,
AUTHOR = "Liu, C. and Yang, C. and Fang, Z.Y. and Qin, H.B. and Yin, X.C.",
TITLE = "CFOR: Character-First Open-Set Text Recognition via Context-Free
Learning",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "6497-6507",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362987"}
@inproceedings{bb368812,
AUTHOR = "Tan, Y.L. and Chew, E.Y.K. and Kong, A.W.K. and Kim, J.J. and Lim, J.H.",
TITLE = "Portmanteauing Features for Scene Text Recognition",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1499-1505",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362988"}
@article{bb368813,
AUTHOR = "Li, M. and Fu, B. and Zhang, Z.F. and Qiao, Y.",
TITLE = "Character-Aware Sampling and Rectification for Scene Text Recognition",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "649-661",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362989"}
@article{bb368814,
AUTHOR = "Fang, S.C. and Mao, Z.D. and Xie, H.T. and Wang, Y.X. and Yan, C.G. and Zhang, Y.D.",
TITLE = "ABINet++: Autonomous, Bidirectional and Iterative Language Modeling
for Scene Text Spotting",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7123-7141",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362990"}
@inproceedings{bb368815,
AUTHOR = "Fang, S.C. and Xie, H.T. and Wang, Y.X. and Mao, Z.D. and Zhang, Y.D.",
TITLE = "Read Like Humans: Autonomous, Bidirectional and Iterative Language
Modeling for Scene Text Recognition",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "7094-7103",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362991"}
@article{bb368816,
AUTHOR = "Yang, J.Y. and Kwon, Y.",
TITLE = "Novel CNN-Based Approach for Reading Urban Form Data in 2D Images:
An Application for Predicting Restaurant Location in Seoul, Korea",
JOURNAL = IJGI,
VOLUME = "12",
YEAR = "2023",
NUMBER = "9",
PAGES = "373",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362992"}
@article{bb368817,
AUTHOR = "Li, M. and Fu, B. and Chen, H. and He, J.J. and Qiao, Y.",
TITLE = "Dual Relation Network for Scene Text Recognition",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4094-4107",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362993"}
@article{bb368818,
AUTHOR = "Liu, X.Q. and Ding, X.Y. and Luo, X. and Xu, X.S.",
TITLE = "Unsupervised Domain Adaptation via Class Aggregation for Text
Recognition",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "5617-5630",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362994"}
@article{bb368819,
AUTHOR = "Liu, X.Q. and Zhang, P.F. and Luo, X. and Huang, Z. and Xu, X.S.",
TITLE = "TextAdapter: Self-Supervised Domain Adaptation for Cross-Domain Text
Recognition",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9854-9865",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362995"}
@article{bb368820,
AUTHOR = "Zhang, J.Y. and Liu, X.Q. and Xue, Z.Y. and Luo, X. and Xu, X.S.",
TITLE = "MAGIC: Multi-granularity domain adaptation for text recognition",
JOURNAL = PR,
VOLUME = "161",
YEAR = "2025",
PAGES = "111229",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362996"}
@article{bb368821,
AUTHOR = "Liu, X.Q. and Zhang, P.F. and Luo, X. and Huang, Z. and Xu, X.S.",
TITLE = "Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "6550-6563",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362997"}
@article{bb368822,
AUTHOR = "Liang, M. and Zhu, X.B. and Zhou, H.Y. and Qin, J.Y. and Yin, X.C.",
TITLE = "HFENet: Hybrid Feature Enhancement Network for Detecting Texts in
Scenes and Traffic Panels",
JOURNAL = ITS,
VOLUME = "24",
YEAR = "2023",
NUMBER = "12",
MONTH = "December",
PAGES = "14200-14212",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362998"}
@article{bb368823,
AUTHOR = "Ding, X.Y. and Liu, X.Q. and Luo, X. and Xu, X.S.",
TITLE = "DOC: Text Recognition via Dual Adaptation and Clustering",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9071-9081",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT362999"}
@article{bb368824,
AUTHOR = "Li, B.Y. and Zou, D.P. and Huang, Y. and Niu, X.H. and Pei, L. and Yu, W.X.",
TITLE = "TextSLAM: Visual SLAM With Semantic Planar Text Features",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "593-610",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT363000"}
@article{bb368825,
AUTHOR = "Yang, M.K. and Yang, B. and Liao, M.H. and Zhu, Y.Y. and Bai, X.",
TITLE = "Sequential visual and semantic consistency for semi-supervised text
recognition",
JOURNAL = PRL,
VOLUME = "178",
YEAR = "2024",
PAGES = "174-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT363001"}
@article{bb368826,
AUTHOR = "Tian, S. and Zhu, K.X. and Qin, H.B. and Yang, C.",
TITLE = "Dynamic receptive field adaptation for scene text recognition",
JOURNAL = PRL,
VOLUME = "178",
YEAR = "2024",
PAGES = "55-61",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT363002"}
@article{bb368827,
AUTHOR = "Yao, M.H. and Liu, Z.G. and Zhuang, L.S. and Wang, L.W. and Li, H.Q.",
TITLE = "A Robust Framework for One-Shot Key Information Extraction via Deep
Partial Graph Matching",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1070-1079",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT363003"}
@article{bb368828,
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#TT363004"}
@article{bb368829,
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#TT363005"}
@article{bb368830,
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#TT363006"}
@article{bb368831,
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#TT363007"}
@article{bb368832,
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#TT363008"}
@article{bb368833,
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#TT363009"}
@article{bb368834,
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#TT363010"}
@inproceedings{bb368835,
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#TT363011"}
@article{bb368836,
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#TT363012"}
@article{bb368837,
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#TT363013"}
@article{bb368838,
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#TT363014"}
@article{bb368839,
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#TT363015"}
@inproceedings{bb368840,
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#TT363016"}
@article{bb368841,
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#TT363017"}
@article{bb368842,
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#TT363018"}
@article{bb368843,
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#TT363019"}
@article{bb368844,
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#TT363020"}
@article{bb368845,
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#TT363021"}
@article{bb368846,
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#TT363022"}
@inproceedings{bb368847,
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#TT363023"}
@article{bb368848,
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#TT363024"}
@article{bb368849,
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#TT363025"}
@article{bb368850,
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#TT363026"}
@article{bb368851,
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#TT363027"}
@article{bb368852,
AUTHOR = "Xin, Q.Y. and Zhang, C. and Lang, Q. and Wu, X.P. and Ye, J. and Jin, L.W. and Qi, H.N.",
TITLE = "LOG: Local Feature-Guided Global Linguistic Sequence Reconstruction
for Chinese Scene Text Recognition",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114431",
BIBSOURCE = "http://www.visionbib.com/bibliography/char966s1.html#TT363028"}
@inproceedings{bb368853,
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#TT363029"}
@inproceedings{bb368854,
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#TT363030"}
@inproceedings{bb368855,
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#TT363031"}
@inproceedings{bb368856,
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#TT363032"}
@inproceedings{bb368857,
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#TT363033"}
@inproceedings{bb368858,
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#TT363034"}
@inproceedings{bb368859,
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#TT363035"}
@inproceedings{bb368860,
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#TT363036"}
@inproceedings{bb368861,
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#TT363037"}
@inproceedings{bb368862,
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#TT363038"}
@inproceedings{bb368863,
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#TT363039"}
@inproceedings{bb368864,
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#TT363040"}
@inproceedings{bb368865,
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#TT363041"}
@inproceedings{bb368866,
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#TT363042"}
@inproceedings{bb368867,
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#TT363043"}
@inproceedings{bb368868,
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#TT363044"}
@inproceedings{bb368869,
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#TT363045"}
@inproceedings{bb368870,
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#TT363046"}
@inproceedings{bb368871,
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#TT363047"}
@inproceedings{bb368872,
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#TT363048"}
@inproceedings{bb368873,
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#TT363049"}
@inproceedings{bb368874,
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#TT363050"}
@inproceedings{bb368875,
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#TT363051"}
@inproceedings{bb368876,
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#TT363052"}
@inproceedings{bb368877,
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#TT363053"}
@inproceedings{bb368878,
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#TT363054"}
@inproceedings{bb368879,
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#TT363055"}
@inproceedings{bb368880,
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#TT363056"}
@inproceedings{bb368881,
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#TT363057"}
@inproceedings{bb368882,
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#TT363058"}
@inproceedings{bb368883,
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#TT363059"}
@inproceedings{bb368884,
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#TT363060"}
@inproceedings{bb368885,
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#TT363061"}
@inproceedings{bb368886,
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#TT363062"}
@inproceedings{bb368887,
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#TT363063"}
@inproceedings{bb368888,
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#TT363064"}
@inproceedings{bb368889,
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#TT363065"}
@inproceedings{bb368890,
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#TT363066"}
@inproceedings{bb368891,
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#TT363067"}
@inproceedings{bb368892,
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#TT363068"}
@inproceedings{bb368893,
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#TT363069"}
@inproceedings{bb368894,
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#TT363070"}
@inproceedings{bb368895,
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#TT363071"}
@inproceedings{bb368896,
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#TT363072"}
@inproceedings{bb368897,
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#TT363073"}
@inproceedings{bb368898,
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#TT363074"}
@inproceedings{bb368899,
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#TT363075"}
Last update:Sep 30, 2026 at 11:45:00