{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T08:50:03Z","timestamp":1768121403050,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557608","type":"print"},{"value":"9789819557615","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\/978-981-95-5761-5_29","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:43Z","timestamp":1768110763000},"page":"414-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VisualQuest: A Benchmark for\u00a0Abstract Visual Reasoning in\u00a0MLLMs"],"prefix":"10.1007","author":[{"given":"Kelaiti","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"PAERHATI","family":"Tulajiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Multimodal large language models: a survey. In: 2023 IEEE International Conference on Big Data (BigData), pp. 2247\u20132256. IEEE (2023)","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv abs\/2306.13549 (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.13549","DOI":"10.48550\/arXiv.2306.13549"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Andreas, J., et al.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"29_CR5","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: Yfcc100m: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","DOI":"10.1145\/2812802"},{"key":"29_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: FVQA: fact-based visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2017)","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: RAVEN: a dataset for relational and analogical visual REasoNing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00546"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Suhr, A., et al.: A corpus of natural language for visual reasoning. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 217\u2013223 (2017)","DOI":"10.18653\/v1\/P17-2034"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Knowledge-routed visual question reasoning: challenges for deep representation embedding. IEEE Trans. Neural Netw. Learn. Syst. 33(7), 2758\u20132767 (2021)","DOI":"10.1109\/TNNLS.2020.3045034"},{"key":"29_CR15","first-page":"29776","volume":"35","author":"A Zerroug","year":"2022","unstructured":"Zerroug, A., et al.: A benchmark for compositional visual reasoning. Adv. Neural. Inf. Process. Syst. 35, 29776\u201329788 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., S\u00f8gaard: A.: QLEVR: a diagnostic dataset for quantificational language and elementary visual reasoning. In: Findings of the Association for Computational Linguistics: NAACL 2022. pp. 980\u2013 996 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.73"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Biever, C.: ChatGPT broke the Turing test-the race is on for new ways to assess AI. Nature 619(7971), 686\u2013689 (2023)","DOI":"10.1038\/d41586-023-02361-7"},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Collier, N., Emerson, G.E.T., Liu, F.: Visual spatial reasoning. Trans. Assoc. Comput. Linguist. 11, 635\u2013651 (2022). https:\/\/doi.org\/10.1162\/tacl_a_00566.","DOI":"10.1162\/tacl_a_00566."},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Super-CLEVR: a virtual benchmark to diagnose domain robustness in visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14963\u201314973 (2023)","DOI":"10.1109\/CVPR52729.2023.01437"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Q., et al.: Learning part segmentation through unsupervised domain adaptation from synthetic vehicles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19140\u201319151 (2022)","DOI":"10.1109\/CVPR52688.2022.01855"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Zhong, S., et al.: Let\u2019s think outside the box: exploring leap-of- thought in large language models with creative humor generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13246\u201313257 (2024)","DOI":"10.1109\/CVPR52733.2024.01258"},{"key":"29_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-981-97-8620-6_2","volume-title":"Pattern Recognition and Computer Vision - PRCV 2024","author":"A Wu","year":"2025","unstructured":"Wu, A., et al.: Charting the uncharted: building and analyzing a multifaceted chart question answering dataset for complex logical reasoning process. In: Lin, Z., et al. (eds.) PRCV 2024. LNCS, vol. 15035, pp. 18\u201333. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-97-8620-6_2"},{"key":"29_CR23","first-page":"95095","volume":"37","author":"K Wang","year":"2024","unstructured":"Wang, K., et al.: Measuring multimodal mathematical reasoning with mathvision dataset. Adv. Neural. Inf. Process. Syst. 37, 95095\u201395169 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Akter, S.N., et al.: VISREAS: complex visual reasoning with unanswerable questions. In: Findings of the Association for Computational Linguistics. ACL 2024, pp. 6735\u20136752 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.402"},{"key":"29_CR25","unstructured":"Xu, W., et al.: Visulogic: a benchmark for evaluating visual reasoning in multi-modal large language models. arXiv preprint arXiv:2504.15279 (2025)"},{"key":"29_CR26","unstructured":"Ren, Y., et al.: VGRP-bench: visual grid reasoning puzzle benchmark for large vision-language models. arXiv preprint arXiv:2503.23064 (2025)"}],"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\/978-981-95-5761-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:47Z","timestamp":1768110767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5761-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557608","9789819557615"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5761-5_29","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":"12 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"}}]}}