{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:04Z","timestamp":1788937624292,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375940","type":"print"},{"value":"9783032375957","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\/978-3-032-37595-7_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:34:33Z","timestamp":1788935673000},"page":"324-343","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of\u00a0Knowledge-Intensive VQA"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2639-7117","authenticated-orcid":false,"given":"Hanseok","family":"Oh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6117-8764","authenticated-orcid":false,"given":"Parishad","family":"BehnamGhader","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1649-428X","authenticated-orcid":false,"given":"Benno","family":"Krojer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0187-336X","authenticated-orcid":false,"given":"Hyunji","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7768-3610","authenticated-orcid":false,"given":"Paul","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3753-0323","authenticated-orcid":false,"given":"Siva","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5955-6896","authenticated-orcid":false,"given":"Verna","family":"Dankers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). ICCV \u201915, pp. 2425\u20132433. IEEE Computer Society, USA (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.279","DOI":"10.1109\/ICCV.2015.279"},{"key":"18_CR2","unstructured":"Bai, S., et al.: Qwen2.5-vl Technical report. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions? In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14948\u201314968. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.925, https:\/\/aclanthology.org\/2023.emnlp-main.925\/","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Molmo and PixMo: open weights and open data for state-of-the-art vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 91\u2013104 (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/papers\/Deitke_Molmo_and_PixMo_Open_Weights_and_Open_Data_for_State-of-the-Art_CVPR_2025_paper.pdf","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"18_CR5","doi-asserted-by":"publisher","unstructured":"Ding, Y., Ren, K., Huang, J., Luo, S., Han, S.C.: MMVQA: a comprehensive dataset for investigating multipage multimodal information retrieval in pdf-based visual question answering. In: Larson, K. (ed.) Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, pp. 6243\u20136251. International Joint Conferences on Artificial Intelligence Organization (2024). https:\/\/doi.org\/10.24963\/ijcai.2024\/690, main Track","DOI":"10.24963\/ijcai.2024\/690"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14375\u201314385 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024\/papers\/Guan_HallusionBench_An_Advanced_Diagnostic_Suite_for_Entangled_Language_Hallucination_and_CVPR_2024_paper.pdf","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Open-domain visual entity recognition: towards recognizing millions of Wikipedia entities. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12065\u201312075 (2023), https:\/\/openaccess.thecvf.com\/content\/ICCV2023\/papers\/Hu_Open-domain_Visual_Entity_Recognition_Towards_Recognizing_Millions_of_Wikipedia_Entities_ICCV_2023_paper.pdf","DOI":"10.1109\/ICCV51070.2023.01108"},{"key":"18_CR8","unstructured":"Hu, W., et al.: MRAG-bench: vision-centric evaluation for retrieval-augmented multimodal models. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations, vol.\u00a02025, pp. 95558\u201395581 (2025). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/ee46288ab2aaf5c6e53aebebe719712c-Paper-Conference.pdf"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Jian, P., Yu, D., Zhang, J.: Large language models know what is key visual entity: an LLM-assisted multimodal retrieval for VQA. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 10939\u201310956. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.613, https:\/\/aclanthology.org\/2024.emnlp-main.613\/","DOI":"10.18653\/v1\/2024.emnlp-main.613"},{"key":"18_CR10","unstructured":"Kabir, R., Haque, N., Islam, M.S., et\u00a0al.: A comprehensive survey on visual question answering datasets and algorithms. arXiv preprint (2024). https:\/\/api.semanticscholar.org\/CorpusID:274131862"},{"key":"18_CR11","unstructured":"Kim, J., et\u00a0al.: Pixel-grounded retrieval for knowledgeable large multimodal models. arXiv preprint (2026). https:\/\/arxiv.org\/abs\/2601.19060"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Lerner, P., et al.: ViQuAE, a dataset for knowledge-based visual question answering about named entities. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201922, pp. 3108\u20133120. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3477495.3531753","DOI":"10.1145\/3477495.3531753"},{"key":"18_CR13","unstructured":"Li, M., et\u00a0al.: Qwen3-VL-embedding and Qwen3-VL-reranker: a unified framework for state-of-the-art multimodal retrieval and ranking. arXiv preprint (2026). https:\/\/arxiv.org\/abs\/2601.04720"},{"key":"18_CR14","unstructured":"Li, Y., et al.: Benchmarking multimodal retrieval augmented generation with dynamic VQA dataset and self-adaptive planning agent. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=VvDEuyVXkG"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Lin, L., Xie, Y., Chen, D., Xu, Y., Zhu, C., Yuan, L.: REVIVE: regional visual representation matters in knowledge-based visual question answering. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=wwyiEyK-G5D","DOI":"10.52202\/068431-0767"},{"key":"18_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-031-72970-6_3","volume-title":"Computer Vision \u2013 ECCV 2024, Part XLVII","author":"S Liu","year":"2024","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024, Part XLVII. LNCS, vol. 15105, pp. 38\u201355. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Ma, T., et al.: When visual grounding meets gigapixel-level large-scale scenes: benchmark and approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22119\u201322128 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024\/papers\/Ma_When_Visual_Grounding_Meets_Gigapixel-level_Large-scale_Scenes_Benchmark_and_Approach_CVPR_2024_paper.pdf","DOI":"10.1109\/CVPR52733.2024.02088"},{"key":"18_CR18","unstructured":"Ma, X., et al.: DeepPerception: advancing r1-like cognitive visual perception in MLLMs for knowledge-intensive visual grounding. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2503.12797"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., Hajishirzi, H.: When not to trust language models: investigating effectiveness of parametric and non-parametric memories. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 9802\u20139822. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.546, https:\/\/aclanthology.org\/2023.acl-long.546\/","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019). https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/papers\/Marino_OK-VQA_A_Visual_Question_Answering_Benchmark_Requiring_External_Knowledge_CVPR_2019_paper.pdf","DOI":"10.1109\/CVPR.2019.00331"},{"key":"18_CR21","unstructured":"Meng, R., et al.: VLM2vec-v2: advancing multimodal embedding for videos, images, and visual documents. Trans. Mach. Learn. Res. (2026). https:\/\/openreview.net\/forum?id=TpU38jbKIJ"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Mensink, T., et al.: Encyclopedic VQA: visual questions about detailed properties of fine-grained categories. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3113\u20133124 (2023). https:\/\/openaccess.thecvf.com\/content\/ICCV2023\/papers\/Mensink_Encyclopedic_VQA_Visual_Questions_About_Detailed_Properties_of_Fine-Grained_Categories_ICCV_2023_paper.pdf","DOI":"10.1109\/ICCV51070.2023.00289"},{"key":"18_CR23","unstructured":"Meta, A.: Llama 3.2: revolutionizing edge AI and vision with open, customizable models (2024). https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"18_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"Computer Vision \u2013 ECCV 2022, Part X","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part X. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"18_CR25","unstructured":"Narayan, K., et al.: DeepMMSearch-R1: empowering multimodal LLMs in multimodal web search. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2510.12801"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Qiang, C., et al.: VER-bench: evaluating MLLMs on reasoning with fine-grained visual evidence. In: Proceedings of the 33rd ACM International Conference on Multimedia. MM \u201925, pp. 12698\u201312705. Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3746027.3758208","DOI":"10.1145\/3746027.3758208"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, Y., et al.: Prism: a framework for decoupling and assessing the capabilities of VLMs. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=qLnXPVvwLx","DOI":"10.52202\/079017-3552"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Qiu, J., et al.: SnapNTell: enhancing entity-centric visual question answering with retrieval augmented multimodal LLM. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 247\u2013266. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.14, https:\/\/aclanthology.org\/2024.findings-emnlp.14\/","DOI":"10.18653\/v1\/2024.findings-emnlp.14"},{"key":"18_CR29","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, ICML 2021. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Singh, P., Dhawan, S., Agarwal, S., Thakur, N.: Implementation of an efficient fuzzy logic based information retrieval system. arXiv preprint (2015). https:\/\/arxiv.org\/abs\/1503.03957","DOI":"10.4108\/sis.2.5.e5"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Tran, D.T., Tran, T.K., Hauswirth, M., Le\u00a0Phuoc, D.: ReasonVQA: a multi-hop reasoning benchmark with structural knowledge for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 18793\u201318803 (2025). https:\/\/openaccess.thecvf.com\/content\/ICCV2025\/papers\/Tran_ReasonVQA_A_Multi-hop_Reasoning_Benchmark_with_Structural_Knowledge_for_Visual_ICCV_2025_paper.pdf","DOI":"10.1109\/ICCV51701.2025.01746"},{"key":"18_CR32","unstructured":"Wang, J., et\u00a0al.: CRAG-MM: multi-modal multi-turn comprehensive rag benchmark. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2510.26160"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., Van Den\u00a0Henge, A.: Explicit knowledge-based reasoning for visual question answering. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence. IJCAI\u201917, pp. 1290\u20131296. AAAI Press (2017). https:\/\/dl.acm.org\/doi\/10.5555\/3171642.3171825","DOI":"10.24963\/ijcai.2017\/179"},{"key":"18_CR34","unstructured":"Wang, Y., et al.: VisualSimpleQA: a benchmark for decoupled evaluation of large vision-language models in fact-seeking question answering. arXiv preprint (2025). https:\/\/arxiv.org\/abs\/2503.06492"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V?: guided visual search as a core mechanism in multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13084\u201313094 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024\/papers\/Wu_V_Guided_Visual_Search_as_a_Core_Mechanism_in_Multimodal_CVPR_2024_paper.pdf","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Xiao, L., Yang, X., Lan, X., Wang, Y., Xu, C.: Toward visual grounding: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 48(03), 2749\u20132771 (2026). https:\/\/doi.org\/10.1109\/TPAMI.2025.3630635, https:\/\/doi.ieeecomputersociety.org\/10.1109\/TPAMI.2025.3630635","DOI":"10.1109\/TPAMI.2025.3630635"},{"key":"18_CR37","doi-asserted-by":"publisher","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., Nie, J.Y.: C-pack: packed resources for general Chinese embeddings. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201924, pp. 641\u2013649. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657878","DOI":"10.1145\/3626772.3657878"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, L., Yang, Y.: MC-Bench: a benchmark for multi-context visual grounding in the era of MLLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17675\u201317687 (2025). https:\/\/openaccess.thecvf.com\/content\/ICCV2025\/papers\/Xu_MC-Bench_A_Benchmark_for_Multi-Context_Visual_Grounding_in_the_Era_ICCV_2025_paper.pdf","DOI":"10.1109\/ICCV51701.2025.01642"},{"key":"18_CR39","unstructured":"Yu, W., et al.: MM-Vet: evaluating large multimodal models for integrated capabilities. In: Proceedings of the 41st International Conference on Machine Learning. ICML\u201924, JMLR.org (2024). https:\/\/dl.acm.org\/doi\/10.5555\/3692070.3694451"},{"key":"18_CR40","unstructured":"Zhang, Y., et al.: MME-realworld: could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans? In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=k5VHHgsRbi"}],"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\/978-3-032-37595-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:34:40Z","timestamp":1788935680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37595-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375940","9783032375957"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37595-7_18","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":"10 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"}}]}}