{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:35:12Z","timestamp":1767321312732,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819541577","type":"print"},{"value":"9789819541584","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\/978-981-95-4158-4_3","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:33:19Z","timestamp":1767321199000},"page":"37-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Yan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kui","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoju","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1400","volume":"9","author":"S Lu","year":"2023","unstructured":"Lu, S., Liu, M., Yin, L., Yin, Z., Liu, X., Zheng, W.: The multi-modal fusion in visual question answering: a review of attention mechanisms. PeerJ Comput. Sci. 9, e1400 (2023)","journal-title":"PeerJ Comput. Sci."},{"key":"3_CR2","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., Shen, C., Dick, A.R., van den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21\u201340 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Sood, E., K\u00f6gel, F., M\u00fcller, P., Thomas, D., B\u0103ce, M., Bulling, A.: Multimodal integration of human-like attention in visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2648\u20132658 (2023)","DOI":"10.1109\/CVPRW59228.2023.00265"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Cad\u00e8ne, R., Ben-Younes, H., Cord, M., Thome, N.: MUREL: multimodal relational reasoning for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1989\u20131998 (2019)","DOI":"10.1109\/CVPR.2019.00209"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for Few-shot knowledge-based VQA. In: Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, pp. 3081\u20133089 (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Heo, Y.-J., Kim, E.-S., Choi, W.S., Zhang, B.-T.: Hypergraph transformer: weakly-supervised multi-hop reasoning for knowledge-based visual question answering. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 373\u2013390 (2022)","DOI":"10.18653\/v1\/2022.acl-long.29"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Shao, Z., Yu, Z., Wang, M., Yu, J.: Prompting large language models with answer heuristics for knowledge-based visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14974\u201314983 (2023)","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"3_CR8","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the International Conference on Machine Learning, vol. 162, pp. 12888\u201312900 (2022)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Kukliansky, D., Szpektor, I., Chen, X., Ding, N., Soricut, R.: All you may need for VQA are image captions. In: Proceedings of the 2022 Conference of the Association for Computational Linguistics, pp. 1947\u20131963. (2022)","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: From images to textual prompts: zero-shot visual question answering with frozen large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10867\u201310877 (2023)","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"3_CR11","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 Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E.G., Chen, X.: In defense of grid features for visual question answering. In: Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10264\u201310273 (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"3_CR13","unstructured":"Shen, S., et al.: How much Can CLIP benefit vision-and-language tasks? In: Proceedings of the Tenth International Conference on Learning Representations (2022)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Gan, C., Li, Y., Li, H., Sun, C., Gong, B.: VQS: linking segmentations to questions and answers for supervised attention in VQA and question-focused semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1829\u20131838 (2017)","DOI":"10.1109\/ICCV.2017.201"},{"key":"3_CR17","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems, pp. 1039\u20131050 (2018)"},{"key":"3_CR18","unstructured":"Barbiero, P., et al.: Interpretable neural-symbolic concept reasoning. In: Proceedings of the International Conference on Machine Learning, pp. 1801\u20131825 (2023)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Wu, J., Mooney, R.J.: Entity-focused dense passage retrieval for outside-knowledge visual question answering. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 8061\u20138072 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.551"},{"issue":"10","key":"3_CR20","doi-asserted-by":"publisher","first-page":"4362","DOI":"10.1109\/TNNLS.2020.3017530","volume":"32","author":"L Zhang","year":"2021","unstructured":"Zhang, L., et al.: Rich visual knowledge-based augmentation network for visual question answering. IEEE Trans. Neural Networks Learn. Syst. 32(10), 4362\u20134373 (2021)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"3_CR21","unstructured":"Lin, Y., Xie, Y., Chen, D., Xu, Y., Zhu, C., Yuan, L.: REVIVE: regional visual representation matters in knowledge-based visual question answering. In: Advances in Neural Information Processing Systems (2022)"},{"key":"3_CR22","unstructured":"Narasimhan, M., Lazebnik, S., Schwing, A.G.: Out of the box: reasoning with graph convolution nets for factual visual question answering. In: Advances in Neural Information Processing Systems, pp. 2659\u20132670 (2018)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: Proceedings of The Thirty-Third AAAI Conference on Artificial Intelligence, pp. 8876\u20138884 (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Gui, L., Wang, B., Huang, Q., Hauptmann, A., Bisk, Y., Gao, J.: KAT: a knowledge augmented transformer for vision-and-language. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 956\u2013968 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Kan, B., Wang, T., Lu, W., Zhen, X., Guan, W., Zheng, F.: Knowledge-aware prompt tuning for generalizable vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15624\u201315634 (2023)","DOI":"10.1109\/ICCV51070.2023.01436"},{"issue":"2","key":"3_CR26","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336\u2013359 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze-questions for few-shot text classification and natural language inference. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pp. 255\u2013269 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"3_CR28","unstructured":"Alayrac, J.-B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems (2022)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: Proceedings of the 17th European Conference on Computer Vision, pp. 146\u2013162 (2022)","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR31","unstructured":"Zhang, S., et al.: OPT: open pre-trained transformer language models. CoRR abs\/2205.01068 (2022)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Tiong, A.M.H., Li, J., Li, B., Savarese, S., Hoi, S.C.H.: Plug-and-Play VQA: zero-shot VQA by conjoining large pretrained models with zero training. In: Proceedings of the Association for Computational Linguistics, pp. 951\u2013967 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"key":"3_CR33","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 1931\u20131942 (2021)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Jin, W., Cheng, Y., Shen, Y., Chen, W., Ren, X.: A good prompt is worth millions of parameters: low-resource prompt-based learning for vision-language models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 2763\u20132775 (2022)","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Dai, W., Hou, L., Shang, L., Jiang, X., Liu, Q., Fung, P.: Enabling multimodal generation on CLIP via vision-language knowledge distillation. In: Proceedings of the Association for Computational Linguistics, pp. 2383\u20132395 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"3_CR36","unstructured":"Tsimpoukelli, M., Menick, J., Cabi, S., Eslami, S.M.A., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. In: Advances in Neural Information Processing Systems, pp. 200\u2013212 (2021)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Banerjee, P., Gokhale, T., Yang, Y., Baral, C.: WeaQA: weak supervision via captions for visual question answering. In: Proceedings of the Association for Computational Linguistics, pp. 3420\u20133435 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.302"},{"key":"3_CR38","unstructured":"Mokady, R., Hertz, A., Berman, A.H.: ClipCap: CLIP Prefix for Image Captioning. CoRR abs\/2111.09734 (2021)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4158-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:33:22Z","timestamp":1767321202000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4158-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819541577","9789819541584"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4158-4_3","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","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":"26 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2025.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}