{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:55:13Z","timestamp":1781585713375,"version":"3.54.5"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"33","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2022ZD0115100"],"award-info":[{"award-number":["2022ZD0115100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20427"],"award-info":[{"award-number":["U21A20427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Competitive Research Fund from the Westlake Center for Synthetic Biology and Integrated Bioengineering","award":["WU2022A009"],"award-info":[{"award-number":["WU2022A009"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["20220303"],"award-info":[{"award-number":["20220303"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00521-024-10310-2","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T03:16:43Z","timestamp":1723778203000},"page":"20849-20861","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Enhancing human-like multimodal reasoning: a new challenging dataset and comprehensive framework"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8520-6347","authenticated-orcid":false,"given":"Jingxuan","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangyang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linzhuang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bihui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"key":"10310_CR1","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, et\u00a0al (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10310_CR2","doi-asserted-by":"crossref","unstructured":"Antol S, Agrawal A, Lu J, et\u00a0al (2015) Vqa: Visual question answering. In: Proceedings of the IEEE international conference on computer vision, pp 2425\u20132433","DOI":"10.1109\/ICCV.2015.279"},{"key":"10310_CR3","unstructured":"Cao H, Tan C, Gao Z, et\u00a0al (2022) A survey on generative diffusion model. arXiv preprint arXiv:2209.02646"},{"key":"10310_CR4","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et\u00a0al (2020) End-to-end object detection with transformers. In: European conference on computer vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10310_CR5","doi-asserted-by":"crossref","unstructured":"Cha J, Kang W, Mun J, et\u00a0al (2023) Honeybee: locality-enhanced projector for multimodal llm. arXiv preprint arXiv:2312.06742","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"10310_CR6","unstructured":"Chen G, Gong H, Li G (2020) Hcp-mic at vqa-med 2020: effective visual representation for medical visual question answering. In: CLEF (Working Notes), pp 1\u20138"},{"key":"10310_CR7","unstructured":"Chen X, Fang H, Lin TY, et\u00a0al (2015) Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325"},{"key":"10310_CR8","unstructured":"Chowdhery A, Narang S, Devlin J, et\u00a0al (2022) Palm: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311"},{"key":"10310_CR9","unstructured":"Chung HW, Hou L, Longpre S, et\u00a0al (2022) Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416"},{"key":"10310_CR10","doi-asserted-by":"crossref","unstructured":"Gao P, Jiang Z, You H, et\u00a0al (2019) Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6639\u20136648","DOI":"10.1109\/CVPR.2019.00680"},{"key":"10310_CR11","unstructured":"Gao P, Han J, Zhang R, et\u00a0al (2023) Llama-adapter v2: parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010"},{"key":"10310_CR12","doi-asserted-by":"crossref","unstructured":"Gao Z, Tan C, Wu L, et\u00a0al (2022) Simvp: simpler yet better video prediction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3170\u20133180","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"10310_CR13","doi-asserted-by":"crossref","unstructured":"Goyal Y, Khot T, Summers-Stay D, et\u00a0al (2017) Making the v in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6904\u20136913","DOI":"10.1109\/CVPR.2017.670"},{"key":"10310_CR14","doi-asserted-by":"crossref","unstructured":"Huang LC, Kulkarni K, Jha A, et\u00a0al (2018) Cs-vqa: visual question answering with compressively sensed images. In: 2018 25th IEEE international conference on image processing (ICIP), IEEE, pp 1283\u20131287","DOI":"10.1109\/ICIP.2018.8451445"},{"key":"10310_CR15","doi-asserted-by":"crossref","unstructured":"Khashabi D, Min S, Khot T, et\u00a0al (2020) Unifiedqa: crossing format boundaries with a single qa system. arXiv preprint arXiv:2005.00700","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"10310_CR16","unstructured":"Kim W, Son B, Kim I (2021) Vilt: vision-and-language transformer without convolution or region supervision. In: International conference on machine learning, pp 5583\u20135594"},{"key":"10310_CR17","unstructured":"Koyejo S, Mohamed S, Agarwal A, et\u00a0al (eds) (2022) Advances in neural information processing systems 35: Annual conference on neural information processing systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9"},{"key":"10310_CR18","unstructured":"Li LH, Yatskar M, Yin D, et\u00a0al (2019) Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557"},{"key":"10310_CR19","unstructured":"Li S, Wang Z, Liu Z, et\u00a0al (2022) Efficient multi-order gated aggregation network. arXiv preprint arXiv:2211.03295"},{"key":"10310_CR20","doi-asserted-by":"crossref","unstructured":"Lin T, Wang Y, Liu X, et\u00a0al (2022) A survey of transformers. AI Open","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"10310_CR21","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie SJ, et\u00a0al (2014) Microsoft coco: common objects in context. In: European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10310_CR22","unstructured":"Liu H, Li C, Wu Q, et\u00a0al (2023) Visual instruction tuning. arXiv preprint arXiv:2304.08485"},{"key":"10310_CR23","unstructured":"Liu Z, Li S, Wang G, et\u00a0al (2022) Decoupled mixup for data-efficient learning. arXiv preprint arXiv:2203.10761"},{"key":"10310_CR24","unstructured":"Lu P, Qiu L, Chen J, et\u00a0al (2021) Iconqa: a new benchmark for abstract diagram understanding and visual language reasoning. In: The 35th conference on neural information processing systems (NeurIPS 2021) Track on Datasets and Benchmarks, pp 1\u201314"},{"key":"10310_CR25","first-page":"2507","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu P, Mishra S, Xia T et al (2022) Learn to explain: multimodal reasoning via thought chains for science question answering. Adv Neural Inf Process Syst 35:2507\u20132521","journal-title":"Adv Neural Inf Process Syst"},{"key":"10310_CR26","doi-asserted-by":"crossref","unstructured":"Lyu Q, Havaldar S, Stein A, et\u00a0al (2023) Faithful chain-of-thought reasoning. arXiv preprint arXiv:2301.13379","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"10310_CR27","doi-asserted-by":"crossref","unstructured":"Mondal D, Modi S, Panda S, et\u00a0al (2024) Kam-cot: knowledge augmented multimodal chain-of-thoughts reasoning. arXiv preprint arXiv:2401.12863","DOI":"10.1609\/aaai.v38i17.29844"},{"issue":"1","key":"10310_CR28","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(1):5485\u20135551","journal-title":"J Mach Learn Res"},{"key":"10310_CR29","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1613\/jair.1.13200","volume":"73","author":"G Ras","year":"2022","unstructured":"Ras G, Xie N, Van Gerven M et al (2022) Explainable deep learning: A field guide for the uninitiated. Journal of Artificial Intelligence Research 73:329\u2013396","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10310_CR30","doi-asserted-by":"crossref","unstructured":"Sood E, K\u00f6gel F, Strohm F, et\u00a0al (2021) Vqa-mhug: a gaze dataset to study multimodal neural attention in visual question answering. arXiv preprint arXiv:2109.13116","DOI":"10.18653\/v1\/2021.conll-1.3"},{"key":"10310_CR31","doi-asserted-by":"crossref","unstructured":"Srivastava Y, Murali V, Dubey SR, et\u00a0al (2021) Visual question answering using deep learning: a survey and performance analysis. In: Computer vision and image processing: 5th international conference, CVIP 2020, Prayagraj, India, December 4-6, 2020, Revised Selected Papers, Part II 5, Springer, pp 75\u201386","DOI":"10.1007\/978-981-16-1092-9_7"},{"key":"10310_CR32","doi-asserted-by":"crossref","unstructured":"Tan C, Xia J, Wu L, et\u00a0al (2021) Co-learning: learning from noisy labels with self-supervision. In: Proceedings of the 29th ACM international conference on multimedia, pp 1405\u20131413","DOI":"10.1145\/3474085.3475622"},{"key":"10310_CR33","unstructured":"Tan C, Gao Z, Li S, et\u00a0al (2022a) Simvp: towards simple yet powerful spatiotemporal predictive learning. arXiv preprint arXiv:2211.12509"},{"key":"10310_CR34","doi-asserted-by":"crossref","unstructured":"Tan C, Gao Z, Li S, et\u00a0al (2022b) Temporal attention unit: towards efficient spatiotemporal predictive learning. arXiv preprint arXiv:2206.12126","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"10310_CR35","unstructured":"Tan C, Gao Z, Li SZ (2022c) Target-aware molecular graph generation. arXiv preprint arXiv:2202.04829"},{"key":"10310_CR36","doi-asserted-by":"crossref","unstructured":"Tan C, Gao Z, Wu L, et\u00a0al (2022d) Hyperspherical consistency regularization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7244\u20137255","DOI":"10.1109\/CVPR52688.2022.00710"},{"key":"10310_CR37","unstructured":"Tan C, Wei J, Gao Z, et\u00a0al (2023) Boosting the power of small multimodal reasoning models to match larger models with self-consistency training. arXiv preprint arXiv:2311.14109"},{"key":"10310_CR38","unstructured":"Thoppilan R, De\u00a0Freitas D, Hall J, et\u00a0al (2022) Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239"},{"key":"10310_CR39","unstructured":"Touvron H, Lavril T, Izacard G, et\u00a0al (2023) Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"10310_CR40","unstructured":"Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"10310_CR41","doi-asserted-by":"crossref","unstructured":"Wang L, Hu Y, He J, et\u00a0al (2023) T-sciq: teaching multimodal chain-of-thought reasoning via large language model signals for science question answering. arXiv preprint arXiv:2305.03453","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"10310_CR42","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.550030","volume":"4","author":"L Wells","year":"2021","unstructured":"Wells L, Bednarz T (2021) Explainable AI and reinforcement learning-a systematic review of current approaches and trends. Front Artif Intell 4:550030","journal-title":"Front Artif Intell"},{"key":"10310_CR43","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cviu.2017.05.001","volume":"163","author":"Q Wu","year":"2017","unstructured":"Wu Q, Teney D, Wang P et al (2017) Visual question answering: A survey of methods and datasets. Comput Vis Image Underst 163:21\u201340","journal-title":"Comput Vis Image Underst"},{"key":"10310_CR44","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"42","author":"P Xu","year":"2023","unstructured":"Xu P, Zhu X, Clifton DA (2023) Multimodal learning with transformers: a survey. IEEE Trans Pattern Anal Mach Intell 42:12113\u201312132","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"10310_CR45","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1109\/JBHI.2022.3229465","volume":"27","author":"R Yu","year":"2023","unstructured":"Yu R, Pan C, Fei X et al (2023) Multi-graph attention networks with bilinear convolution for diagnosis of schizophrenia. IEEE J Biomed Health Inform 27(3):1443\u20131454","journal-title":"IEEE J Biomed Health Inform"},{"key":"10310_CR46","doi-asserted-by":"crossref","unstructured":"Yu Z, Yu J, Cui Y, et\u00a0al (2019) Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6281\u20136290","DOI":"10.1109\/CVPR.2019.00644"},{"key":"10310_CR47","unstructured":"Zhang S, Roller S, Goyal N, et\u00a0al (2022) Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068"},{"key":"10310_CR48","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.inffus.2021.02.006","volume":"72","author":"W Zhang","year":"2021","unstructured":"Zhang W, Yu J, Zhao W et al (2021) Dmrfnet: deep multimodal reasoning and fusion for visual question answering and explanation generation. Inf Fusion 72:70\u201379","journal-title":"Inf Fusion"},{"key":"10310_CR49","unstructured":"Zhang Z, Zhang A, Li M, et\u00a0al (2023) Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923"},{"key":"10310_CR50","doi-asserted-by":"crossref","unstructured":"Zheng J, Wang Y, Tan C, et\u00a0al (2023) Cvt-slr: contrastive visual-textual transformation for sign language recognition with variational alignment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 23141\u201323150","DOI":"10.1109\/CVPR52729.2023.02216"},{"key":"10310_CR51","unstructured":"Zhu D, Chen J, Shen X, et\u00a0al (2023) Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592"},{"key":"10310_CR52","doi-asserted-by":"crossref","unstructured":"Zou Y, Xie Q (2020) A survey on vqa: datasets and approaches. In: 2020 2nd international conference on information technology and computer application (ITCA), IEEE, pp 289\u2013297","DOI":"10.1109\/ITCA52113.2020.00069"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10310-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10310-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10310-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T16:03:36Z","timestamp":1727539416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10310-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":52,"journal-issue":{"issue":"33","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10310"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10310-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"assertion":[{"value":"28 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}