{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:17:49Z","timestamp":1783210669125,"version":"3.54.6"},"reference-count":73,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2408085Y032"],"award-info":[{"award-number":["2408085Y032"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002729","name":"Anhui University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002729","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102205"],"award-info":[{"award-number":["62102205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134311","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:23:12Z","timestamp":1782404592000},"page":"134311","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ESTR-CoT: Towards explainable and accurate event stream based scene text recognition with chain-of-thought reasoning"],"prefix":"10.1016","volume":"699","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134311_bib0005","author":"Achiam"},{"key":"10.1016\/j.neucom.2026.134311_bib0010","author":"Hurst"},{"key":"10.1016\/j.neucom.2026.134311_bib0015","author":"Bi"},{"key":"10.1016\/j.neucom.2026.134311_bib0020","author":"Bai"},{"key":"10.1016\/j.neucom.2026.134311_bib0025","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2425","article-title":"VQA: visual question answering","author":"Antol","year":"2015"},{"key":"10.1016\/j.neucom.2026.134311_bib0030","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134311_bib0035","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134311_bib0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2256","article-title":"Bliva: a simple multimodal LLM for better handling of text-rich visual questions","volume":"vol. 38","author":"Hu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0045","author":"Jing"},{"key":"10.1016\/j.neucom.2026.134311_bib0050","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"277","article-title":"MMTN: multi-modal memory transformer network for image-report consistent medical report generation","volume":"vol. 37","author":"Cao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134311_bib0055","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"2404","article-title":"Medblip: bootstrapping language-image pre-training from 3D medical images and texts","author":"Chen","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0060","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)","first-page":"5123","article-title":"CXPMRG-bench: pre-training and benchmarking for X-ray medical report generation on CheXpert plus dataset","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134311_bib0065","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134311_bib0070","author":"Feng"},{"key":"10.1016\/j.neucom.2026.134311_bib0075","series-title":"European Conference on Computer Vision","first-page":"408","article-title":"Vary: scaling up the vision vocabulary for large vision-language model","author":"Wei","year":"2025"},{"key":"10.1016\/j.neucom.2026.134311_bib0080","author":"Hu"},{"key":"10.1016\/j.neucom.2026.134311_bib0085","author":"Wei"},{"key":"10.1016\/j.neucom.2026.134311_bib0090","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134311_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13884","article-title":"Recurrent vision transformers for object detection with event cameras","author":"Gehrig","year":"2023"},{"issue":"12","key":"10.1016\/j.neucom.2026.134311_bib0100","doi-asserted-by":"crossref","first-page":"19397","DOI":"10.1109\/JSEN.2024.3392973","article-title":"Spatiotemporal aggregation transformer for object detection with neuromorphic vision sensors","volume":"24","author":"Guo","year":"2024","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.neucom.2026.134311_bib0105","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16794","article-title":"Scene adaptive sparse transformer for event-based object detection","author":"Peng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0110","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"29321","article-title":"Object detection using event camera: a moe heat conduction based detector and a new benchmark dataset","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134311_bib0115","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134311_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9781","article-title":"Frame-event alignment and fusion network for high frame rate tracking","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134311_bib0125","series-title":"Proceedings of the 27th ACM International Conference on Multimedia","first-page":"473","article-title":"Asynchronous tracking-by-detection on adaptive time surfaces for event-based object tracking","author":"Chen","year":"2019"},{"key":"10.1016\/j.neucom.2026.134311_bib0130","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13043","article-title":"Object tracking by jointly exploiting frame and event domain","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134311_bib0135","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19248","article-title":"Event stream-based visual object tracking: a high-resolution benchmark dataset and a novel baseline","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0140","author":"Sun"},{"key":"10.1016\/j.neucom.2026.134311_bib0145","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.134311_bib0150","series-title":"Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134311_bib0155","series-title":"European Conference on Computer Vision","first-page":"303","article-title":"Toward understanding wordart: corner-guided transformer for scene text recognition","author":"Xie","year":"2022"},{"key":"10.1016\/j.neucom.2026.134311_bib0160","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.neucom.2026.134311_bib0165","series-title":"2011 International Conference on Computer Vision","first-page":"1457","article-title":"End-to-end scene text recognition","author":"Wang","year":"2011"},{"issue":"11","key":"10.1016\/j.neucom.2026.134311_bib0170","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.neucom.2026.134311_bib0175","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 33","first-page":"8714","article-title":"Scene text recognition from two-dimensional perspective","author":"Liao","year":"2019"},{"key":"10.1016\/j.neucom.2026.134311_bib0180","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1109\/TMM.2024.3521824","article-title":"Spotlight text detector: spotlight on candidate regions like a camera","volume":"27","author":"Han","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134311_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15567","article-title":"Multi-modal in-context learning makes an ego-evolving scene text recognizer","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0190","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"19416","article-title":"Self-supervised character-to-character distillation for text recognition","author":"Guan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134311_bib0195","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"},{"issue":"2","key":"10.1016\/j.neucom.2026.134311_bib0200","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s11263-023-01880-0","article-title":"Cdistnet: perceiving multi-domain character distance for robust text recognition","volume":"132","author":"Zheng","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134311_bib0205","doi-asserted-by":"crossref","first-page":"6437","DOI":"10.1109\/TMM.2024.3350916","article-title":"VOLTER: visual collaboration and dual-stream fusion for scene text recognition","volume":"26","author":"Li","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134311_bib0210","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 38","first-page":"5885","article-title":"Image as a language: revisiting scene text recognition via balanced, unified and synchronized vision-language reasoning network","author":"Wei","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0215","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.neucom.2026.134311_bib0220","series-title":"European Conference on Computer Vision","first-page":"322","article-title":"Levenshtein OCR","author":"Da","year":"2022"},{"key":"10.1016\/j.neucom.2026.134311_bib0225","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"},{"issue":"8","key":"10.1016\/j.neucom.2026.134311_bib0230","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"10.1016\/j.neucom.2026.134311_bib0235","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"240","key":"10.1016\/j.neucom.2026.134311_bib0240","first-page":"1","article-title":"Palm: scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134311_bib0245","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134311_bib0250","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TMM.2024.3521709","article-title":"LININ: logic integrated neural inference network for explanatory visual question answering","volume":"27","author":"Xue","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134311_bib0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130986","article-title":"Key-concept thinking prompting for improved reasoning in large language models","author":"Tang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134311_bib0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129219","article-title":"Improving intermediate reasoning in zero-shot chain-of-thought for large language models with filter supervisor-self correction","volume":"620","author":"Sun","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134311_bib0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129903","article-title":"RECoT: relation-enhanced chains-of-thoughts for knowledge-intensive multi-hop questions answering","volume":"637","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134311_bib0270","doi-asserted-by":"crossref","first-page":"22199","DOI":"10.52202\/068431-1613","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134311_bib0275","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2087","article-title":"Llava-cot: let vision language models reason step-by-step","author":"Xu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134311_bib0280","doi-asserted-by":"crossref","first-page":"11809","DOI":"10.52202\/075280-0517","article-title":"Tree of thoughts: deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134311_bib0285","series-title":"Topologies of reasoning: demystifying chains, trees, and graphs of thoughts","author":"Besta","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0290","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134311_bib0295","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134311_bib0300","author":"Zhu"},{"issue":"1","key":"10.1016\/j.neucom.2026.134311_bib0305","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: a survey","volume":"44","author":"Gallego","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134311_bib0310","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/TMM.2024.3521750","article-title":"EvCSLR: event-guided continuous sign language recognition and benchmark","volume":"27","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134311_bib0315","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/TMM.2023.3314973","article-title":"Masked autoencoders in 3D point cloud representation learning","volume":"27","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134311_bib0320","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 38","first-page":"5615","article-title":"Hardvs: revisiting human activity recognition with dynamic vision sensors","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134311_bib0325","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111080","article-title":"Semantic-aware frame-event fusion based pattern recognition via large vision\u2013language models","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134311_bib0330","series-title":"Conference on Robot Learning","first-page":"969","article-title":"ESIM: an open event camera simulator","author":"Rebecq","year":"2018"},{"key":"10.1016\/j.neucom.2026.134311_bib0335","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.134311_bib0340","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.neucom.2026.134311_bib0345","series-title":"European Conference on Computer Vision","first-page":"339","article-title":"Multi-granularity prediction for scene text recognition","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134311_bib0350","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.neucom.2026.134311_bib0355","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.neucom.2026.134311_bib0360","author":"Jaderberg"},{"key":"10.1016\/j.neucom.2026.134311_bib0365","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"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017091?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017091?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:51:55Z","timestamp":1783209115000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226017091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":73,"alternative-id":["S0925231226017091"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134311","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ESTR-CoT: Towards explainable and accurate event stream based scene text recognition with chain-of-thought reasoning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134311","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134311"}}