{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T17:02:30Z","timestamp":1789837350202,"version":"4.0.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52130403"],"award-info":[{"award-number":["52130403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.ins.2026.123242","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:17:23Z","timestamp":1771373843000},"page":"123242","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Mamba-STR: Efficient context-aware scene text recognition framework with selective state space modeling"],"prefix":"10.1016","volume":"741","author":[{"given":"Shahid","family":"Ali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0272-194X","authenticated-orcid":false,"given":"Tianhan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zakir","family":"Hussain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maqsood","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.ins.2026.123242_bib0005","article-title":"An OCR engine for printed receipt images using deep learning techniques","volume":"14","author":"Sayallar","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"10.1016\/j.ins.2026.123242_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2024.101330","article-title":"A two-stage road sign detection and text recognition system based on yolov7","volume":"27","author":"Hsieh","year":"2024","journal-title":"Internet of Things"},{"issue":"11","key":"10.1016\/j.ins.2026.123242_bib0015","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123242_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7098","article-title":"Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition","author":"Fang","year":"2021"},{"key":"10.1016\/j.ins.2026.123242_bib0025","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"13094","article-title":"Trocr: transformer-based optical character recognition with pre-trained models","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0030","doi-asserted-by":"crossref","first-page":"6893","DOI":"10.1109\/TIP.2024.3512354","article-title":"Clip4str: a simple baseline for scene text recognition with pre-trained vision-language model","volume":"33","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ins.2026.123242_bib0035","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123242_bib0040","series-title":"International Conference on Document Analysis and Recognition","first-page":"319","article-title":"Vision transformer for fast and efficient scene text recognition","author":"Atienza","year":"2021"},{"key":"10.1016\/j.ins.2026.123242_bib0045","series-title":"European Conference on Computer Vision","first-page":"178","article-title":"Scene text recognition with permuted autoregressive sequence models","author":"Bautista","year":"2022"},{"key":"10.1016\/j.ins.2026.123242_bib0050","series-title":"First Conference on Language Modeling","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.ins.2026.123242_bib0055","series-title":"International Conference on Learning Representations","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.ins.2026.123242_bib0060","series-title":"Proceedings of the 41st International Conference on Machine Learning, Vol. 235 of Proceedings of Machine Learning Research","first-page":"62429","article-title":"Vision mamba: efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.ins.2026.123242_bib0065","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.ins.2026.123242_bib0070","article-title":"Enhancing multimodal large language models with efficient feature alignment and processing using state space models","author":"Huang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ins.2026.123242_bib0075","series-title":"A New Approach to Linear Filtering and Prediction Problems","author":"Kalman","year":"1960"},{"key":"10.1016\/j.ins.2026.123242_bib0080","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123242_bib0085","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123242_bib0090","series-title":"Proceedings of the 23rd International Conference on Machine Learning","first-page":"369","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"Graves","year":"2006"},{"key":"10.1016\/j.ins.2026.123242_bib0095","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"20147","article-title":"Svtrv2: ctc beats encoder-decoder models in scene text recognition","author":"Du","year":"2025"},{"key":"10.1016\/j.ins.2026.123242_bib0100","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12120","article-title":"Textscanner: reading characters in order for robust scene text recognition","volume":"vol. 34","author":"Wan","year":"2020"},{"key":"10.1016\/j.ins.2026.123242_bib0105","series-title":"European Conference on Computer Vision","first-page":"446","article-title":"Multi-modal text recognition networks: interactive enhancements between visual and semantic features","author":"Na","year":"2022"},{"key":"10.1016\/j.ins.2026.123242_bib0110","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2231","article-title":"Recursive recurrent nets with attention modeling for OCR in the wild","author":"Lee","year":"2016"},{"key":"10.1016\/j.ins.2026.123242_bib0115","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1109\/TIP.2020.3045602","article-title":"Sloan: scale-adaptive orientation attention network for scene text recognition","volume":"30","author":"Dai","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ins.2026.123242_bib0120","author":"Yang"},{"issue":"4","key":"10.1016\/j.ins.2026.123242_bib0125","doi-asserted-by":"crossref","first-page":"2723","DOI":"10.1109\/TPAMI.2025.3525526","article-title":"Instruction-guided scene text recognition","volume":"47","author":"Du","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123242_bib0130","series-title":"BMVC-British Machine Vision Conference","article-title":"Scene text recognition using higher order language priors","author":"Mishra","year":"2012"},{"key":"10.1016\/j.ins.2026.123242_bib0135","series-title":"2011 International Conference on Computer Vision","first-page":"1457","article-title":"End-to-end scene text recognition","author":"Wang","year":"2011"},{"key":"10.1016\/j.ins.2026.123242_bib0140","series-title":"2013 12th International Conference on Document Analysis and Recognition","first-page":"1484","article-title":"Icdar 2013 robust reading competition","author":"Karatzas","year":"2013"},{"key":"10.1016\/j.ins.2026.123242_bib0145","series-title":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","first-page":"1156","article-title":"Icdar 2015 competition on robust reading","author":"Karatzas","year":"2015"},{"key":"10.1016\/j.ins.2026.123242_bib0150","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4715","article-title":"What is wrong with scene text recognition model comparisons? Dataset and model analysis","author":"Baek","year":"2019"},{"issue":"18","key":"10.1016\/j.ins.2026.123242_bib0155","doi-asserted-by":"crossref","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","article-title":"A robust arbitrary text detection system for natural scene images","volume":"41","author":"Risnumawan","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123242_bib0160","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"569","article-title":"Recognizing text with perspective distortion in natural scenes","author":"Phan","year":"2013"},{"key":"10.1016\/j.ins.2026.123242_bib0165","article-title":"Coco-text: dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016","journal-title":"Scene Underst. Workshop at CVPR (SUNw)"},{"key":"10.1016\/j.ins.2026.123242_bib0170","series-title":"2019 International Conference on Document Analysis and Recognition (ICDAR)","first-page":"1571","article-title":"Icdar2019 robust reading challenge on arbitrary-shaped text-rrc-art","author":"Chng","year":"2019"},{"key":"10.1016\/j.ins.2026.123242_bib0175","series-title":"SUNw: Scene Understanding Workshop-CVPR","first-page":"5","article-title":"Uber-text: a large-scale dataset for optical character recognition from street-level imagery","volume":"vol. 2017","author":"Zhang","year":"2017"},{"key":"10.1016\/j.ins.2026.123242_bib0180","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2315","article-title":"Synthetic data for text localisation in natural images","author":"Gupta","year":"2016"},{"key":"10.1016\/j.ins.2026.123242_bib0185","author":"Jaderberg"},{"key":"10.1016\/j.ins.2026.123242_bib0190","unstructured":"I. Krasin, T. Duerig, N. Alldrin, V. Ferrari, S. Abu-El-Haija, A. Kuznetsova, et al., Openimages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification, Dataset available from, https:\/\/github.com\/openimages 2017, 2 (3) 18."},{"key":"10.1016\/j.ins.2026.123242_bib0195","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15619","article-title":"An empirical study of scaling law for scene text recognition","author":"Rang","year":"2024"},{"key":"10.1016\/j.ins.2026.123242_bib0200","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"20543","article-title":"Revisiting scene text recognition: a data perspective","author":"Jiang","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0205","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"4214","article-title":"Reading and writing: discriminative and generative modeling for self-supervised text recognition","author":"Yang","year":"2022"},{"key":"10.1016\/j.ins.2026.123242_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15285","article-title":"Self-supervised implicit glyph attention for text recognition","author":"Guan","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0215","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"509","article-title":"Symmetrical linguistic feature distillation with CLIP for scene text recognition","author":"Wang","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0220","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"19541","article-title":"Lister: neighbor decoding for length-insensitive scene text recognition","author":"Cheng","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0225","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21706","article-title":"Clipter: looking at the bigger picture in scene text recognition","author":"Aberdam","year":"2023"},{"key":"10.1016\/j.ins.2026.123242_bib0230","author":"Chu"},{"key":"10.1016\/j.ins.2026.123242_bib0235","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"9318","article-title":"Linguistics-aware masked image modeling for self-supervised scene text recognition","author":"Zhang","year":"2025"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526001738?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526001738?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T04:52:17Z","timestamp":1777438337000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526001738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":47,"alternative-id":["S0020025526001738"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123242","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mamba-STR: Efficient context-aware scene text recognition framework with selective state space modeling","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123242","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123242"}}