{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:07:01Z","timestamp":1789024021495,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372109","type":"print"},{"value":"9783032372116","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\/978-3-032-37211-6_37","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:38:16Z","timestamp":1789022296000},"page":"669-687","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LightSTAR: Efficient Visual Document Retrieval via\u00a0Lightweight Selection with\u00a0Vision-Adaptive Refinement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3346-8315","authenticated-orcid":false,"given":"Tongkun","family":"Guan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8449-1834","authenticated-orcid":false,"given":"Haocheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 23716\u201323736. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-1723"},{"key":"37_CR2","unstructured":"Bai, J., et al.: Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"37_CR3","unstructured":"Beyer, L., et al.: Paligemma: A versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"37_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems,. vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"37_CR5","doi-asserted-by":"publisher","first-page":"2318","DOI":"10.18653\/v1\/2024.findings-acl.137","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"J Chen","year":"2024","unstructured":"Chen, J., et al.: M3-embedding: multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics: ACL 2024, pp. 2318\u20132335. Association for Computational Linguistics, Bangkok, Thailand (Aug (2024)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Dao, T., et al.: Flashattention: fast and memory-efficient exact attention with io-awareness. In: Oh, A. (ed.) Advances in Neural Information Processing Systems, vol. 35, pp. 16344\u201316359. Curran Associates, Inc (2022)","DOI":"10.52202\/068431-1189"},{"key":"37_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"37_CR9","unstructured":"Faysse, M., et al.: Colpali: efficient document retrieval with vision language models. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations. vol.\u00a02025, pp. 61424\u201361449 (2025)"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Fu, P., et al.: Multimodal large language models for text-rich image understanding: A comprehensive review. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 19941\u201319958 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1023"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Gao, Z., et\u00a0al.: Mini-internvl: A flexible-transfer pocket multimodal model with 5% parameters and 90% performance. arXiv preprint arXiv:2410.16261 (2024)","DOI":"10.1007\/s44267-024-00067-6"},{"issue":"9","key":"37_CR12","doi-asserted-by":"publisher","first-page":"6073","DOI":"10.1109\/TCSVT.2022.3156390","volume":"32","author":"T Guan","year":"2022","unstructured":"Guan, T., et al.: Industrial scene text detection with refined feature-attentive network. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6073\u20136085 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Self-supervised implicit glyph attention for text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15285\u201315294 (2023)","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Guan, T., Lin, C., Shen, W., Yang, X.: Posformer: recognizing complex handwritten mathematical expression with position forest transformer. In: European Conference on Computer Vision, pp. 130\u2013147. Springer (2025)","DOI":"10.1007\/978-3-031-72670-5_8"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X.: CCDPlus: Towards accurate character to character distillation for text recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3533737"},{"key":"37_CR16","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19473\u201319484 (2023)","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Wang, X., Yang, X.: Bridging synthetic and real worlds for pre-training scene text detectors. In: European Conference on Computer Vision, pp. 428\u2013446. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_24"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: A token-level text image foundation model for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23210\u201323220 (2025)","DOI":"10.1109\/ICCV51701.2025.02155"},{"key":"37_CR19","unstructured":"Guan, T., et\u00a0al.: Codepercept: code-grounded visual stem perception for MLLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 33542\u201333552 (2026)"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"G\u00fcnther, M., et al.: jina-embeddings-v4: Universal embeddings for multimodal multilingual retrieval. In: Adelani, D.I., et al., (eds.) Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pp. 531\u2013550. Association for Computational Linguistics, Suzhou, China (Nov 2025)","DOI":"10.18653\/v1\/2025.mrl-main.36"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Guo, J., Xu, G., Cheng, X., Li, H.: Named entity recognition in query. In: Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 267\u2013274. SIGIR \u201909, Association for Computing Machinery, New York, NY, USA (2009)","DOI":"10.1145\/1571941.1571989"},{"key":"37_CR22","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"37_CR23","unstructured":"Jiang, T., et al.: E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Meng, R., Yang, X., Yavuz, S., Zhou, Y., Chen, W.: VLM2vec: Training vision-language models for massive multimodal embedding tasks. In: ICLR (2025)","DOI":"10.36227\/techrxiv.175624545.56457516\/v1"},{"key":"37_CR25","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: Colbert: Efficient and effective passage search via contextualized late interaction over BERT. In: Huang, J.X., Chang, Y., Cheng, X., Kamps, J., Murdock, V., Wen, J., Liu, Y. (eds.) Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, Virtual Event, China, July 25-30, 2020, pp. 39\u201348. ACM (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Computer Vision \u2013 ECCV 2022: 17th European Conference. Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVIII, pp. 498\u2013517. Springer-Verlag, Berlin, Heidelberg (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"37_CR28","unstructured":"Kirillov, A., et al.: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023). Segment anything"},{"key":"37_CR29","unstructured":"Lee, K., et al.: Pix2Struct: Screenshot parsing as pretraining for visual language understanding. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 18893\u201318912. PMLR (23\u201329 Jul 2023)"},{"key":"37_CR30","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 9459\u20139474. Curran Associates, Inc. (2020)"},{"key":"37_CR31","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (17\u201323 Jul 2022)"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Visual instruction tuning. In: Levine, S. (ed.) Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916. Curran Associates, Inc (2023)","DOI":"10.52202\/075280-1516"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Loper, E., Bird, S.: NLTK: The natural language toolkit. arXiv preprint arXiv:cs\/0205028 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: Massive text embedding benchmark. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2014\u20132037. Association for Computational Linguistics, Dubrovnik, Croatia (2023)","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"37_CR35","unstructured":"Nussbaum, Z., Duderstadt, B., Mulyar, A.: Nomic embed vision: Expanding the latent space. arXiv preprint arXiv:2406.18587 (2024)"},{"key":"37_CR36","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2019)"},{"key":"37_CR37","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (18\u201324 Jul 2021)"},{"issue":"4","key":"37_CR38","first-page":"333","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr. 3(4), 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"37_CR39","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M.: Okapi at trec (1994)","DOI":"10.6028\/NIST.SP.500-225.adhoc-city"},{"key":"37_CR40","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"SPARCK\u00a0JONES, K.: A statistical interpretation of term specificity and its application in retrieval. J. Document. 28(1), 11\u201321 (01 1972)","DOI":"10.1108\/eb026526"},{"key":"37_CR42","unstructured":"Team, N.: Nomic embed multimodal: Interleaved text, image, and screenshots for visual document retrieval (2025)"},{"key":"37_CR43","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"37_CR44","unstructured":"Tschannen, M., et al.: Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"37_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Marten: Visual question answering with mask generation for multi-modal document understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14460\u201314471 (2025)","DOI":"10.1109\/CVPR52734.2025.01348"},{"key":"37_CR46","doi-asserted-by":"crossref","unstructured":"Wen, C., Peng, Z., Huang, Y., Shen, W.: Efficient segmentation with multimodal large language model via token routing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 10593\u201310602 (2026)","DOI":"10.1609\/aaai.v40i13.38032"},{"key":"37_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2579\u20132591. Association for Computational Linguistics, Online (Aug 2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"37_CR48","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1192\u20131200. KDD \u201920, ACM (Aug 2020)","DOI":"10.1145\/3394486.3403172"},{"key":"37_CR49","unstructured":"Yu, S., et al.: VisRAG: Vision-based retrieval-augmented generation on multi-modality documents. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations, vol.\u00a02025, pp. 21074\u201321098 (2025)"},{"key":"37_CR50","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"37_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: OCR hinders rag: Evaluating the cascading impact of OCR on retrieval-augmented generation. arXiv preprint arXiv:2412.02592 (2025)","DOI":"10.1109\/ICCV51701.2025.01620"},{"key":"37_CR52","unstructured":"Zhu, J., et al.: Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-37211-6_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:38:36Z","timestamp":1789022316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37211-6_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372109","9783032372116"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37211-6_37","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"}}]}}