{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:39:00Z","timestamp":1769186340412,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556816","type":"print"},{"value":"9789819556823","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\/978-981-95-5682-3_30","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:55Z","timestamp":1769116435000},"page":"426-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Q-Doc: Benchmarking Document Image Quality Assessment Capabilities in\u00a0Multi-modal Large Language Models"],"prefix":"10.1007","author":[{"given":"Jiaxi","family":"Huang","sequence":"first","affiliation":[]},{"given":"Dongxu","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Hanwei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Lingyu","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Baoliang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"issue":"2","key":"30_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3606692","volume":"56","author":"A Alaei","year":"2023","unstructured":"Alaei, A., Bui, V., Doermann, D., Pal, U.: Document image quality assessment: a survey. ACM Comput. Surv. 56(2), 1\u201336 (2023)","journal-title":"ACM Comput. Surv."},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"30_CR3","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Visual chain-of-thought prompting for knowledge-based visual reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1254\u20131262 (2024)","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, H., Zeng, Y., Ma, K., Wang, Z.: Perceptual quality assessment of smartphone photography. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3677\u20133686 (2020)","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"30_CR6","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arxiv:2306.13394 (2024)"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: multimodal large language models can see but not perceive. In: European Conference on Computer Vision, pp. 148\u2013166. Springer (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"30_CR8","unstructured":"Ge, J., Luo, H., Qian, S., Gan, Y., Fu, J., Zhang, S.: Chain of thought prompt tuning in vision language models. arXiv preprint arXiv:2304.07919 (2023)"},{"key":"30_CR9","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"30_CR10","unstructured":"Hong, W., et\u00a0al.: Cogvlm2: visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024)"},{"key":"30_CR11","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1109\/TIP.2020.2967829","volume":"29","author":"V Hosu","year":"2020","unstructured":"Hosu, V., Lin, H., Sziranyi, T., Saupe, D.: Koniq-10k: an ecologically valid database for deep learning of blind image quality assessment. IEEE Trans. Image Process. 29, 4041\u20134056 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"30_CR12","unstructured":"Hurst, A., et\u00a0al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal LLMs with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Zhu, F., Qiu, J.: CG-DIQA: no-reference document image quality assessment based on character gradient. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3622\u20133626. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8545433"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Mmbench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"30_CR17","first-page":"46378","volume":"37","author":"Z Liu","year":"2024","unstructured":"Liu, Z., et al.: II-bench: an image implication understanding benchmark for multimodal large language models. Adv. Neural Inf. Process. Syst. 37, 46378\u201346480 (2024)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR18","unstructured":"Lu, J., et al.: Evaluation and mitigation of agnosia in multimodal large language models. arXiv preprint arXiv:2309.040413 (2023)"},{"key":"30_CR19","unstructured":"Meta: Llama-3.2-11b-vision-instruct. https:\/\/huggingface.co\/meta-llama\/Llama-3.2-11B-Vision-Instruct (2024)"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Nayef, N., Luqman, M.M., Prum, S., Eskenazi, S., Chazalon, J., Ogier, J.M.: SmartDOC-QA: A dataset for quality assessment of smartphone captured document images-single and multiple distortions. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1231\u20131235. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333960"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Van\u00a0Strien, D., Beelen, K., Ardanuy, M.C., Hosseini, K., McGillivray, B., Colavizza, G.: Assessing the impact of OCR quality on downstream NLP tasks (2020)","DOI":"10.5220\/0009169004840496"},{"key":"30_CR22","unstructured":"Wu, H., et al.: Q-bench: a benchmark for general-purpose foundation models on low-level vision. In: ICLR (2024)"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Wu, H., et\u00a0al.: Towards open-ended visual quality comparison. In: European Conference on Computer Vision, pp. 360\u2013377. Springer (2024)","DOI":"10.1007\/978-3-031-72646-0_21"},{"key":"30_CR24","unstructured":"Wu, Z., et\u00a0al.: Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"30_CR25","unstructured":"Ye, J., et al.: mPLUG-Owl3: Towards long image-sequence understanding in multi-modal large language models. arXiv preprint arXiv:2408.04840 (2024)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Ye, P., Doermann, D.: Document image quality assessment: a brief survey. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 723\u2013727. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.148"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yang, W., Lai, S., Xie, Z., Jin, L.: Dockylin: a large multimodal model for visual document understanding with efficient visual slimming. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 9923\u20139932 (2025)","DOI":"10.1609\/aaai.v39i9.33076"},{"key":"30_CR28","unstructured":"Zhang, R., et al.: Improve vision language model chain-of-thought reasoning. arXiv preprint arXiv:2410.16198 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5682-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:05Z","timestamp":1769116445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5682-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556816","9789819556823"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5682-3_30","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":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}