{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:17:05Z","timestamp":1777655825203,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731945","type":"print"},{"value":"9783031731952","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73195-2_15","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T09:37:24Z","timestamp":1732613844000},"page":"252-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Fully Authentic Visual Question Answering Dataset from Online Communities"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3188-6652","authenticated-orcid":false,"given":"Chongyan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noel","family":"Codella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danna","family":"Gurari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"15_CR1","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":"15_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Litman, R., Xie, Y., Appalaraju, S., Manmatha, R.: LATR: layout-aware transformer for scene-text VQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16548\u201316558 (2022)","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bitton-Guetta, N., et al.: Breaking common sense: whoops! a vision-and-language benchmark of synthetic and compositional images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2616\u20132627 (2023)","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions? arXiv preprint arXiv:2302.11713 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"15_CR5","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Elliott, D., Keller, F.: Image description using visual dependency representations. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1292\u20131302 (2013)","DOI":"10.18653\/v1\/D13-1128"},{"key":"15_CR7","unstructured":"GPT-4V pricing (2023). https:\/\/platform.openai.com\/docs\/guides\/vision. Accessed 16 Nov 2023"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Fu, H., Fan, Y.: Music information seeking via social Q &A: an analysis of questions in music stackexchange community. In: Proceedings of the 16th ACM\/IEEE-CS on Joint Conference on Digital Libraries, pp. 139\u2013142 (2016)","DOI":"10.1145\/2910896.2910914"},{"key":"15_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2023.117071","volume":"120","author":"O Gonz\u00e1lez-Ch\u00e1vez","year":"2024","unstructured":"Gonz\u00e1lez-Ch\u00e1vez, O., Ruiz, G., Moctezuma, D., Ramirez-delReal, T.: Are metrics measuring what they should? An evaluation of image captioning task metrics. Signal Process. Image Commun. 120, 117071 (2024)","journal-title":"Signal Process. Image Commun."},{"key":"15_CR10","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gurari, D., Grauman, K.: Crowdverge: predicting if people will agree on the answer to a visual question. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 3511\u20133522 (2017)","DOI":"10.1145\/3025453.3025781"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Gurari, D., Zhao, Y., Zhang, M., Bhattacharya, N.: Captioning images taken by people who are blind. arXiv preprint arXiv:2002.08565 (2020)","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Harper, F.M., Weinberg, J., Logie, J., Konstan, J.A.: Question types in social Q &A sites. First Monday (2010)","DOI":"10.5210\/fm.v15i7.2913"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"He, B., Xia, M., Yu, X., Jian, P., Meng, H., Chen, Z.: An educational robot system of visual question answering for preschoolers. In: 2017 2nd International Conference on Robotics and Automation Engineering (ICRAE), pp. 441\u2013445. IEEE (2017)","DOI":"10.1109\/ICRAE.2017.8291426"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"15_CR17","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 Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Jing, L., Li, R., Chen, Y., Jia, M., Du, X.: Faithscore: evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477 (2023)","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van\u00a0der Maaten, L., Fei-Fei, L., Lawrence\u00a0Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.: TVQA: localized, compositional video question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1369\u20131379 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"15_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"15_CR22","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"15_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"15_CR24","unstructured":"Lu, P., et al.: Mathvista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: Infographicvqa. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., Chakraborty, A.: OCR-VQA: visual question answering by reading text in images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 947\u2013952. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Naik, N., Potts, C., Kreiss, E.: Context-VQA: towards context-aware and purposeful visual question answering. arXiv preprint arXiv:2307.15745 (2023)","DOI":"10.1109\/ICCVW60793.2023.00301"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Nie, L., Wang, M., Zha, Z., Li, G., Chua, T.S.: Multimedia answering: enriching text QA with media information. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 695\u2013704 (2011)","DOI":"10.1145\/2009916.2010010"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Novikova, J., Du\u0161ek, O., Curry, A.C., Rieser, V.: Why we need new evaluation metrics for NLG. arXiv preprint arXiv:1707.06875 (2017)","DOI":"10.18653\/v1\/D17-1238"},{"key":"15_CR32","unstructured":"OpenAI: GPT-4 technical report. arXiv abs\/2303.08774 (2023)"},{"issue":"3","key":"15_CR33","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s00799-022-00329-y","volume":"23","author":"T Saikh","year":"2022","unstructured":"Saikh, T., Ghosal, T., Mittal, A., Ekbal, A., Bhattacharyya, P.: Scienceqa: a novel resource for question answering on scholarly articles. Int. J. Digit. Libr. 23(3), 289\u2013301 (2022)","journal-title":"Int. J. Digit. Libr."},{"key":"15_CR34","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"issue":"3","key":"15_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2934687","volume":"10","author":"I Srba","year":"2016","unstructured":"Srba, I., Bielikova, M.: A comprehensive survey and classification of approaches for community question answering. ACM Trans. Web (TWEB) 10(3), 1\u201363 (2016)","journal-title":"ACM Trans. Web (TWEB)"},{"key":"15_CR37","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"15_CR38","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., 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":"15_CR39","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: LVLM-eHub: a comprehensive evaluation benchmark for large vision-language models. arXiv preprint arXiv:2306.09265 (2023)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"15_CR40","unstructured":"Yang, Z., et al.: The dawn of LMMs: preliminary explorations with GPT-4V (ision). arXiv preprint arXiv:2309.17421, vol. 9 (2023)"},{"key":"15_CR41","unstructured":"Ye, Q., et al.: mPLUG-Owl: modularization empowers large language models with multimodality (2023)"},{"issue":"CSCW2","key":"15_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3415220","volume":"4","author":"X Zeng","year":"2020","unstructured":"Zeng, X., Wang, Y., Chiu, T.Y., Bhattacharya, N., Gurari, D.: Vision skills needed to answer visual questions. Proc. ACM Hum.-Comput. Interact. 4(CSCW2), 1\u201331 (2020)","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"15_CR43","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"15_CR44","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73195-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:54:09Z","timestamp":1733100849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}