{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:13:46Z","timestamp":1789074826925,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368454","type":"print"},{"value":"9783032368461","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-36846-1_3","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:04:07Z","timestamp":1789074247000},"page":"36-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UniRec-0.1B: Unified Text and\u00a0Formula Recognition with\u00a00.1B Parameters"],"prefix":"10.1007","author":[{"given":"Yongkun","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yazhen","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"3_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report (2023). arXiv:2303.08774 arXiv preprint"},{"key":"3_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: ECCV, pp. 178\u2013196. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"3_CR4","unstructured":"Blecher, L.: pix2tex: LaTeX-OCR \u2013 using a ViT to convert images of equations into LaTeX code. https:\/\/github.com\/lukas-blecher\/LaTeX-OCR (2021)"},{"key":"3_CR5","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: neural optical understanding for academic documents (2023). arXiv:2308.13418 arXiv preprint"},{"key":"3_CR6","unstructured":"breezedeus: Pix2text. https:\/\/github.com\/breezedeus\/Pix2Text (2022). Accessed 23 June 2025"},{"key":"3_CR7","unstructured":"Chen, J., et al.: Benchmarking Chinese text recognition: datasets, baselines, and an empirical study. CoRR abs\/2112.15093 (2021)"},{"key":"3_CR8","unstructured":"Chen, S., et\u00a0al.: Ocean-OCR: towards general OCR application via a vision-language model. arXiv preprint arXiv:2501.15558 (2025)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"3_CR10","unstructured":"chatdoc com: Ocrflux. https:\/\/github.com\/chatdoc-com\/OCRFlux (2025). Accessed 25 Oct 2025"},{"key":"3_CR11","unstructured":"Cui, C., et\u00a0al.: PaddleOCR-VL: boosting multilingual document parsing via a 0.9 B ultra-compact vision-language model. arXiv preprint arXiv:2510.14528 (2025)"},{"key":"3_CR12","unstructured":"Cui, C., et\u00a0al.: PaddleOCR 3.0 technical report. arXiv preprint arXiv:2507.05595 (2025)"},{"key":"3_CR13","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: ICML, pp. 980\u2013989 (2017)"},{"key":"3_CR14","unstructured":"Du, Y., Chen, P., Ying, X., Chen, Z.: DocPTBench: benchmarking end-to-end photographed document parsing and translation. arXiv preprint arXiv:2511.18434 (2025)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Jia, C., Gao, X., Jiang, Y.G.: Out of length text recognition with sub-string matching. In: AAAI, pp. 2798\u20132806 (2025)","DOI":"10.1609\/aaai.v39i3.32285"},{"issue":"6","key":"3_CR16","doi-asserted-by":"publisher","first-page":"4668","DOI":"10.1109\/TPAMI.2025.3545453","volume":"47","author":"Y Du","year":"2025","unstructured":"Du, Y., et al.: Context perception parallel decoder for scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 47(6), 4668\u20134683 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3545453","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Du, Y., et al.: SVTR: scene text recognition with a single visual model. In: IJCAI, pp. 884\u2013890 (2022)","DOI":"10.24963\/ijcai.2022\/124"},{"issue":"4","key":"3_CR18","doi-asserted-by":"publisher","first-page":"2723","DOI":"10.1109\/TPAMI.2025.3525526","volume":"47","author":"Y Du","year":"2025","unstructured":"Du, Y., Chen, Z., Su, Y., Jia, C., Jiang, Y.G.: Instruction-guided scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 47(4), 2723\u20132738 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3525526","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Du, Y., Chen, Z., Xie, H., Jia, C., Jiang, Y.G.: SVTRv2: CTC beats encoder-decoder models in scene text recognition. In: ICCV, pp. 20147\u201320156 (2025)","DOI":"10.1109\/ICCV51701.2025.01874"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Duan, C., Tan, Z., Bartsch, S.: LaTeX rainbow: universal LaTeX to PDF document semantic & layout annotation framework. In: Proceedings of the Second Workshop on Information Extraction from Scientific Publications, pp. 56\u201367 (2023)","DOI":"10.18653\/v1\/2023.wiesp-1.8"},{"issue":"6","key":"3_CR21","doi-asserted-by":"publisher","first-page":"7123","DOI":"10.1109\/TPAMI.2022.3223908","volume":"45","author":"S Fang","year":"2023","unstructured":"Fang, S., Mao, Z., Xie, H., Wang, Y., Yan, C., Zhang, Y.: ABINet++: autonomous, bidirectional and iterative language modeling for scene text spotting. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7123\u20137141 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: CVPR, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"3_CR23","unstructured":"Feng, H., et al.: Dolphin-V2: universal document parsing via scalable anchor prompting (2026). arXiv:2602.05384 arXiv preprint"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Feng, H., et al.: Dolphin: document image parsing via heterogeneous anchor prompting (2025). arXiv:2505.14059 arXiv preprint","DOI":"10.18653\/v1\/2025.findings-acl.1130"},{"key":"3_CR25","unstructured":"Filimoa: open-parse. https:\/\/github.com\/Filimoa\/open-parse (2024). Accessed 23 June 2025"},{"key":"3_CR26","unstructured":"Google DeepMind: Gemini 2.5. https:\/\/blog.google\/technology\/google-deepmind\/gemini-model-thinking-updates-march-2025\/ (2025)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Feng, Q., Jiang, Z., Yang, X.: Self-supervised character-to-character distillation for text recognition. In: ICCV, pp. 19473\u201319484 (2023)","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"3_CR29","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-VL technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images, pp. 2315\u20132324. CVPR (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"He, M., et al.: ICPR2018 contest on robust reading for multi-type web images. In: ICPR, pp. 7\u201312 (2018)","DOI":"10.1109\/ICPR.2018.8546143"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., Lin, Z.: GTC: guided training of CTC towards efficient and accurate scene text recognition. AAAI 34, 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"3_CR33","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. CoRR abs\/1406.2227 (2014)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Wang, J., Peng, D., Liu, C., Jin, L.: Revisiting scene text recognition: a data perspective. In: ICCV, pp. 20486\u201320497 (2023)","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: ECCV, pp. 498\u2013517 Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"3_CR36","unstructured":"Li, G., et al.: Towards real-world document parsing via realistic scene synthesis and document-aware training (2026). arXiv:2603.23885 arXiv preprint"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition, pp. 8610\u20138617. AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"3_CR38","unstructured":"Li, Y., Yang, G., Liu, H., Wang, B., Zhang, C.: dots.OCR: multilingual document layout parsing in a single vision-language model (2025)"},{"key":"3_CR39","unstructured":"Li, Z., et al.: MonkeyOCR: document parsing with a structure-recognition-relation triplet paradigm. arXiv preprint arXiv:2506.05218 (2025)"},{"key":"3_CR40","unstructured":"Liu, A., et\u00a0al.: DeepSeek-V2: a strong, economical, and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: Casia online and offline Chinese handwriting databases. In: ICDAR, pp. 37\u201341 (2011)","DOI":"10.1109\/ICDAR.2011.17"},{"key":"3_CR42","unstructured":"Liu, Y., et al.: TextMonkey: an OCR-free large multimodal model for understanding document. arXiv preprint arXiv:2403.04473 (2024)"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M.: Towards end-to-end unified scene text detection and layout analysis. In: CVPR, pp. 1049\u20131059 (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"3_CR44","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"key":"3_CR45","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. ICLR (2019)"},{"key":"3_CR46","unstructured":"Lukas Blecher: pix2tex - latex OCR. https:\/\/github.com\/lukas-blecher\/LaTeX-OCR (2022). Accessed 23 June 2025"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. Pattern Recognit. 90, 109\u2013118 (2019)","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"3_CR48","unstructured":"Mandal, S., Talewar, A., Ahuja, P., Juvatkar, P.: Nanonets-OCR-S: a model for transforming documents into structured markdown with intelligent content recognition and semantic tagging (2025)"},{"key":"3_CR49","unstructured":"Mathpix: Mathpix snip: Convert images and PDFs to latex, docx, and more. https:\/\/mathpix.com\/ (2025)"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Nassar, A., et\u00a0al.: SmolDocling: an ultra-compact vision-language model for end-to-end multi-modal document conversion. arXiv preprint arXiv:2503.11576 (2025)","DOI":"10.1109\/ICCV51701.2025.02040"},{"key":"3_CR51","unstructured":"Niu, J., et al.: MinerU2. 5: a decoupled vision-language model for efficient high-resolution document parsing (2025). arXiv:2509.22186 arXiv preprint"},{"key":"3_CR52","unstructured":"opendatalab: MinerU2.0-2505-0.9B. https:\/\/huggingface.co\/opendatalab\/MinerU2.0-2505-0.9B (2025)"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et\u00a0al.: OmniDocBench: benchmarking diverse PDF document parsing with comprehensive annotations. In: CVPR, pp. 24838\u201324848 (2025)","DOI":"10.1109\/CVPR52734.2025.02313"},{"key":"3_CR54","unstructured":"Paruchuri, V.: Marker. https:\/\/github.com\/datalab-to\/marker (2025). Accessed 25 Oct 2025"},{"key":"3_CR55","unstructured":"Poznanski, J., et al.: OLMOCR: unlocking trillions of tokens in PDFs with vision language models (2025). arXiv:2502.18443 arXiv preprint"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., Xu, B.: NRTR: a no-recurrence sequence-to-sequence model for scene text recognition. In: ICDAR, pp. 781\u2013786 (2019)","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"3_CR57","doi-asserted-by":"publisher","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2646371","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2019)","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: ICDAR 2019 competition on large-scale street view text with partial labeling-RRC-LSVT. In: ICDAR, pp. 1557\u20131562 (2019)","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"3_CR60","unstructured":"TAL: Tal open dataset. https:\/\/ai.100tal.com\/dataset (2023)"},{"key":"3_CR61","unstructured":"Team, D.: Docling. https:\/\/github.com\/docling-project\/docling (2024). Accessed 23 June 2025"},{"key":"3_CR62","unstructured":"Team, H.V., et al.: HunyuanOCR technical report (2025)"},{"key":"3_CR63","unstructured":"Team, K., et\u00a0al.: Kimi-VL technical report. arXiv preprint arXiv:2504.07491 (2025)"},{"key":"3_CR64","unstructured":"Tencent: Hunyuan-0.5B. https:\/\/github.com\/Tencent-Hunyuan\/Hunyuan-0.5B (2025)"},{"key":"3_CR65","unstructured":"Unstructured-IO: unstructured. https:\/\/github.com\/Unstructured-IO\/unstructured (2022). Accessed 23 June 2025"},{"key":"3_CR66","doi-asserted-by":"crossref","unstructured":"Wang, B., et al.: Infinity Parser: layout aware reinforcement learning for scanned document parsing (2025)","DOI":"10.18653\/v1\/2026.findings-acl.82"},{"key":"3_CR67","unstructured":"Wang, B., et al.: UniMERNet: a universal network for real-world mathematical expression recognition (2024). arXiv:2404.15254 arXiv preprint"},{"key":"3_CR68","unstructured":"Wang, B., et\u00a0al.: MinerU: an open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839 (2024)"},{"key":"3_CR69","doi-asserted-by":"crossref","unstructured":"Wang, P., Da, C., Yao, C.: Multi-Granularity Prediction for scene text recognition, pp. 339\u2013355. ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"3_CR70","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: PETR: rethinking the capability of transformer-based language model in scene text recognition. IEEE Trans. Image Process. 31, 5585\u20135598 (2022)","DOI":"10.1109\/TIP.2022.3197981"},{"key":"3_CR71","unstructured":"Wei, H., et al.: General OCR theory: towards OCR-2.0 via a unified end-to-end model (2024). arXiv:2409.01704 arXiv preprint"},{"key":"3_CR72","unstructured":"Wei, H., Sun, Y., Li, Y.: DeepSeek-OCR: contexts optical compression (2025). arXiv:2510.18234 arXiv preprint"},{"key":"3_CR73","doi-asserted-by":"crossref","unstructured":"Wu, J.W., Yin, F., Zhang, Y.M., Zhang, X.Y., Liu, C.L.: Handwritten mathematical expression recognition via paired adversarial learning. IJCV 128, 2386\u20132401 (2020)","DOI":"10.1007\/s11263-020-01291-5"},{"key":"3_CR74","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"3_CR75","unstructured":"Yang, B., et al.: Kwai KEYE-VL 1.5 technical report (2025). arXiv:2509.01563 arXiv preprint"},{"key":"3_CR76","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, C., Dai, X., Gao, J.: Focal modulation networks. NeurIPS, pp. 4203\u20134217 (2022)","DOI":"10.52202\/068431-0304"},{"key":"3_CR77","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"3_CR78","doi-asserted-by":"crossref","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: ECCV, pp. 135\u2013151 (2020)","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"3_CR79","unstructured":"Zhang, J., Du, J., Yang, Y., Song, Y.Z., Wei, S., Dai, L.: A tree-structured decoder for image-to-markup generation. In: ICML, pp. 11076\u201311085. PMLR (2020)"},{"key":"3_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Watch, attend and parse: an end-to-end neural network based approach to handwritten mathematical expression recognition. PR 71, 196\u2013206 (2017)","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"3_CR81","unstructured":"Zhang, Q., et al.: Document parsing unveiled: techniques, challenges, and prospects for structured information extraction. arXiv preprint arXiv:2410.21169 (2024)"},{"key":"3_CR82","doi-asserted-by":"crossref","unstructured":"Zhao, S., Du, Y., Chen, Z., Jiang, Y.G.: Decoder pre-training with only text for scene text recognition. In: ACM MM, pp. 5191\u20135200 (2024)","DOI":"10.1145\/3664647.3681390"},{"key":"3_CR83","doi-asserted-by":"crossref","unstructured":"Zhao, S., Quan, R., Zhu, L., Yang, Y.: CLIP4STR: a simple baseline for scene text recognition with pre-trained vision-language model. IEEE Trans. Image Process. 33, 6893\u20136904 (2024)","DOI":"10.1109\/TIP.2024.3512354"},{"key":"3_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Multi-modal in-context learning makes an ego-evolving scene text recognizer, pp. 15567\u201315576. CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01474"},{"key":"3_CR85","doi-asserted-by":"crossref","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., Jiang, Y.G.: CDistNet: perceiving multi-domain character distance for robust text recognition. Int. J. Comput. Vis. 132(2), 300\u2013318 (2024)","DOI":"10.1007\/s11263-023-01880-0"},{"key":"3_CR86","doi-asserted-by":"crossref","unstructured":"Zhong, H., et al.: VL-Reader: vision and language reconstructor is an effective scene text recognizer. In: ACM MM, pp. 4207\u20134216 (2024)","DOI":"10.1145\/3664647.3681271"},{"key":"3_CR87","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models (2025). arXiv:2504.10479 arXiv preprint"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36846-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:04:32Z","timestamp":1789074272000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36846-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368454","9783032368461"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36846-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}