{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T15:14:30Z","timestamp":1788621270314,"version":"build-2803163510"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100009110","name":"Xinjiang Uygur Autonomous Region Natural Science Foundation","doi-asserted-by":"publisher","award":["2024D01A20"],"award-info":[{"award-number":["2024D01A20"]}],"id":[{"id":"10.13039\/100009110","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004753","name":"Southwest Petroleum University","doi-asserted-by":"publisher","award":["2024JGYB027"],"award-info":[{"award-number":["2024JGYB027"]}],"id":[{"id":"10.13039\/501100004753","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.jvcir.2026.104907","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:58:50Z","timestamp":1785772730000},"page":"104907","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TibSTR-Former: Multi-scale feature integration and attention mechanisms for Tibetan scene text recognition"],"prefix":"10.1016","volume":"120","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5119-8060","authenticated-orcid":false,"given":"Gyaltsan","family":"Lhundrub","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3705-5684","authenticated-orcid":false,"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3105-3473","authenticated-orcid":false,"given":"Mohan","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2068-3198","authenticated-orcid":false,"given":"Wuping","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianshu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Desheng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104907_b1","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.jvcir.2026.104907_b2","doi-asserted-by":"crossref","first-page":"142642","DOI":"10.1109\/ACCESS.2020.3012542","article-title":"Handwritten optical character recognition (ocr): A comprehensive systematic literature review (slr)","volume":"8","author":"Memon","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104907_b3","series-title":"A survey on optical character recognition system","author":"Islam","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104907_b4","series-title":"2015 International Conference on Innovations in Information, Embedded and Communication Systems","first-page":"1","article-title":"Text recognition from images","author":"Manwatkar","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104907_b5","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.jvcir.2026.104907_b6","series-title":"Tibetan Language for Non-Tibetans","first-page":"15","article-title":"Origin and invention of tibetan script","author":"Tashi","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104907_b7","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1515\/9783110519082-006","article-title":"Digital encoding, preservation, translation, and research for tibetan buddhist texts","author":"Hackett","year":"2019","journal-title":"Digit. Humanit. Buddhism"},{"key":"10.1016\/j.jvcir.2026.104907_b8","unstructured":"Qianji Di, Ekaterina Vylomova, Timothy Baldwin, Modelling tibetan verbal morphology, in: Proceedings of the 17th Annual Workshop of the Australasian Language Technology Association, 2019, pp. 35\u201340."},{"key":"10.1016\/j.jvcir.2026.104907_b9","doi-asserted-by":"crossref","first-page":"72896","DOI":"10.1109\/ACCESS.2019.2919328","article-title":"Morphological verb-aware tibetan language model","volume":"7","author":"Khysru","year":"2019","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.jvcir.2026.104907_b10","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1007\/s42979-022-01246-2","article-title":"Problems of semantic and syntactic modeling of verbs in the tibetan corpus","volume":"3","author":"Kramskova","year":"2022","journal-title":"SN Comput. Sci."},{"issue":"15","key":"10.1016\/j.jvcir.2026.104907_b11","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/electronics12153337","article-title":"A fine-tuned hybrid stacked cnn to improve bengali handwritten digit recognition","volume":"12","author":"Amin","year":"2023","journal-title":"Electronics"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104907_b12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.55630\/sjc.2023.17.107-116","article-title":"Recognition of handwritten mathematical expressions using systems of convolutional neural networks","volume":"17","author":"Rowney","year":"2023","journal-title":"Serdica J. Comput."},{"issue":"12","key":"10.1016\/j.jvcir.2026.104907_b13","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A survey of convolutional neural networks: analysis, applications, and prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104907_b14","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","article-title":"A review of convolutional neural networks in computer vision","volume":"57","author":"Zhao","year":"2024","journal-title":"Artif. Intell. Rev."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104907_b15","doi-asserted-by":"crossref","first-page":"369","DOI":"10.3390\/info14070369","article-title":"Scene text recognition based on improved crnn","volume":"14","author":"Yu","year":"2023","journal-title":"Information"},{"issue":"16","key":"10.1016\/j.jvcir.2026.104907_b16","doi-asserted-by":"crossref","first-page":"7034","DOI":"10.3390\/s23167034","article-title":"Text recognition model based on multi-scale fusion crnn","volume":"23","author":"Zou","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.jvcir.2026.104907_b17","series-title":"2022 8th International Conference on Contemporary Information Technology and Mathematics","first-page":"329","article-title":"Handwritten text recognition using crnn","author":"Idris","year":"2022"},{"issue":"3","key":"10.1016\/j.jvcir.2026.104907_b18","doi-asserted-by":"crossref","first-page":"520","DOI":"10.3390\/forecast3030033","article-title":"Attention-based cnn-rnn arabic text recognition from natural scene images","volume":"3","author":"Butt","year":"2021","journal-title":"Forecasting"},{"key":"10.1016\/j.jvcir.2026.104907_b19","series-title":"2017 14th IAPR International Conference on Document Analysis and Recognition","first-page":"79","article-title":"Handwritten chinese text recognition using separable multi-dimensional recurrent neural network","volume":"Vol. 1","author":"Wu","year":"2017"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104907_b20","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/CC.2017.7839765","article-title":"Offline urdu nastaleeq optical character recognition based on stacked denoising autoencoder","volume":"14","author":"Ahmad","year":"2017","journal-title":"China Commun."},{"key":"10.1016\/j.jvcir.2026.104907_b21","doi-asserted-by":"crossref","first-page":"10062","DOI":"10.1109\/ACCESS.2022.3144844","article-title":"Cursive text recognition in natural scene images using deep convolutional recurrent neural network","volume":"10","author":"Chandio","year":"2022","journal-title":"IEEE Access"},{"issue":"12","key":"10.1016\/j.jvcir.2026.104907_b22","doi-asserted-by":"crossref","first-page":"276","DOI":"10.3390\/jimaging9120276","article-title":"Vitstr-transducer: Cross-attention-free vision transformer transducer for scene text recognition","volume":"9","author":"Buoy","year":"2023","journal-title":"J. Imaging"},{"key":"10.1016\/j.jvcir.2026.104907_b23","series-title":"2024 7th International Conference on Algorithms, Computing and Artificial Intelligence","first-page":"01","article-title":"Compressed vision transformer for scene text recognition","author":"Ren","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104907_b24","series-title":"2025 International Conference on Electrical, Computer and Communication Engineering","first-page":"1","article-title":"An optical character recognition technique for extracting text from blurred and low-quality images using trocr","author":"Ayrin","year":"2025"},{"issue":"3","key":"10.1016\/j.jvcir.2026.104907_b25","doi-asserted-by":"crossref","first-page":"3444","DOI":"10.1007\/s10489-022-03728-5","article-title":"Str transformer: a cross-domain transformer for scene text recognition","volume":"53","author":"Wu","year":"2023","journal-title":"Appl. Intell."},{"key":"10.1016\/j.jvcir.2026.104907_b26","doi-asserted-by":"crossref","first-page":"48322","DOI":"10.1109\/ACCESS.2023.3276628","article-title":"Time series prediction based on lstm-attention-lstm model","volume":"11","author":"Wen","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104907_b27","series-title":"2019 IEEE International Conference on Artificial Intelligence and Computer Applications","first-page":"352","article-title":"Research on text classification based on cnn and lstm","author":"Luan","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104907_b28","series-title":"ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7080","article-title":"End-to-end speech recognition using a high rank lstm-ctc based model","author":"Shi","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104907_b29","doi-asserted-by":"crossref","unstructured":"Ranjila Shrestha, Oshin Shrestha, Monika Shakya, Urja Bajracharya, Subash Panday, Offline handwritten text extraction and recognition using cnn-blstm-ctc network, Int. J. Eng. Technol. 1, 166\u2013180.","DOI":"10.3126\/injet.v1i1.60941"},{"key":"10.1016\/j.jvcir.2026.104907_b30","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104907_b31","doi-asserted-by":"crossref","unstructured":"Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai, Robust scene text recognition with automatic rectification, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4168\u20134176.","DOI":"10.1109\/CVPR.2016.452"},{"key":"10.1016\/j.jvcir.2026.104907_b32","doi-asserted-by":"crossref","unstructured":"Xunjian Yin, Xiaojun Wan, How do seq2seq models perform on end-to-end data-to-text generation?, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 7701\u20137710.","DOI":"10.18653\/v1\/2022.acl-long.531"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104907_b33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3543826","article-title":"Turkish data-to-text generation using sequence-to-sequence neural networks","volume":"22","author":"Demir","year":"2022","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"10.1016\/j.jvcir.2026.104907_b34","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104907_b35","series-title":"International Conference on Document Analysis and Recognition","first-page":"112","article-title":"Transformer for handwritten text recognition using bidirectional post-decoding","author":"Wick","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104907_b36","doi-asserted-by":"crossref","unstructured":"Minghao Li, Tengchao Lv, Jingye Chen, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei, Trocr: Transformer-based optical character recognition with pre-trained models, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 13094\u201313102.","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"10.1016\/j.jvcir.2026.104907_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110244","article-title":"Class-aware mask-guided feature refinement for scene text recognition","volume":"149","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104907_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111909","article-title":"Improving the transferability of adversarial examples through neighborhood attribution","volume":"296","author":"Ke","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jvcir.2026.104907_b39","doi-asserted-by":"crossref","unstructured":"Desheng Zheng, Wuping Ke, Xiaoyu Li, Yaoxin Duan, Guangqiang Yin, Fan Min, Enhancing the transferability of adversarial attacks via multi-feature attention, IEEE Trans. Inf. Forensics Secur. 2025.","DOI":"10.1109\/TIFS.2025.3526067"},{"key":"10.1016\/j.jvcir.2026.104907_b40","doi-asserted-by":"crossref","unstructured":"Xinzhu Li, Juepeng Zheng, Yikun Chen, Xudong Mao, Guanghui Yue, Wei Zhou, Chenlei Lv, Ruomei Wang, Fan Zhou, Baoquan Zhao, Depthgait: Multi-scale cross-level feature fusion of rgb-derived depth and silhouette sequences for robust gait recognition, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 2333\u20132341.","DOI":"10.1145\/3746027.3755876"},{"key":"10.1016\/j.jvcir.2026.104907_b41","series-title":"2021 IEEE International Symposium on Circuits and Systems","first-page":"1","article-title":"Deep multi-scale features learning for distorted image quality assessment","author":"Zhou","year":"2021"},{"issue":"10","key":"10.1016\/j.jvcir.2026.104907_b42","doi-asserted-by":"crossref","first-page":"10299","DOI":"10.1109\/TCSVT.2024.3405789","article-title":"Blind image quality assessment via adaptive graph attention","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104907_b43","series-title":"2024 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Deep bi-directional attention network for image super-resolution quality assessment","author":"Li","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104907_b44","series-title":"Perception-oriented bidirectional attention network for image super-resolution quality assessment","author":"Li","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104907_b45","doi-asserted-by":"crossref","unstructured":"Jiaquan Shen, Ningzhong Liu, Han Sun, Shang Wu, Zongzheng Liang, Lulu Han, Yongxin Zhang, Deguang Li, Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection, IEEE Trans. Intell. Transp. Syst. 2025.","DOI":"10.1109\/TITS.2025.3642410"},{"issue":"12","key":"10.1016\/j.jvcir.2026.104907_b46","doi-asserted-by":"crossref","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","article-title":"An anchor-free lightweight deep convolutional network for vehicle detection in aerial images","volume":"23","author":"Shen","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.jvcir.2026.104907_b47","first-page":"1","article-title":"Finger vein recognition algorithm based on lightweight deep convolutional neural network","volume":"71","author":"Shen","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.jvcir.2026.104907_b48","first-page":"1","article-title":"An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features","volume":"73","author":"Shen","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.jvcir.2026.104907_b49","series-title":"Southwest Data Science Conference","first-page":"158","article-title":"A scene tibetan text detection by combining multi-scale and dual-channel features","author":"Dangzhi","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104907_b50","series-title":"International Conference on Document Analysis and Recognition","first-page":"296","article-title":"The research on end-to-end tibetan text detection and recognition in natural scenes","author":"Peiran","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104907_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112548","article-title":"Enhance and read: Scene tibetan text recognition with cross-sequence reasoning","volume":"169","author":"Ke","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.jvcir.2026.104907_b52","series-title":"Tibetan str dataset for natural scene text","author":"Lhundrub","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104907_b53","doi-asserted-by":"crossref","unstructured":"Jeonghun Baek, Geewook Kim, Junyeop Lee, Sungrae Park, Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Hwalsuk Lee, What is wrong with scene text recognition model comparisons? dataset and model analysis, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4715\u20134723.","DOI":"10.1109\/ICCV.2019.00481"},{"issue":"6","key":"10.1016\/j.jvcir.2026.104907_b54","doi-asserted-by":"crossref","first-page":"7123","DOI":"10.1109\/TPAMI.2022.3223908","article-title":"Abinet++: Autonomous, bidirectional and iterative language modeling for scene text spotting","volume":"45","author":"Fang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104907_b55","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","article-title":"Moran: A multi-object rectified attention network for scene text recognition","volume":"90","author":"Luo","year":"2019","journal-title":"Pattern Recognit."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326002026?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326002026?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T14:54:29Z","timestamp":1788620069000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326002026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":55,"alternative-id":["S1047320326002026"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104907","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TibSTR-Former: Multi-scale feature integration and attention mechanisms for Tibetan scene text recognition","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104907","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":"104907"}}