{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:26:20Z","timestamp":1742991980680,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9437-9_28","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:30:31Z","timestamp":1730392231000},"page":"356-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the\u00a0Fidelity of\u00a0Image Captioning via\u00a0Weighted Boolean Question Answering"],"prefix":"10.1007","author":[{"given":"Kaixuan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jintao","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Kehan","family":"Long","sequence":"additional","affiliation":[]},{"given":"Yongzhu","family":"Miao","sequence":"additional","affiliation":[]},{"given":"Fangda","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.cviu.2017.12.004","volume":"173","author":"S Aditya","year":"2018","unstructured":"Aditya, S., Yang, Y., Baral, C., Aloimonos, Y., Ferm\u00fcller, C.: Image understanding using vision and reasoning through scene description graph. Comput. Vis. Image Underst. 173, 33\u201345 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"28_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"28_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"28_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"28_CR5","doi-asserted-by":"publisher","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: A reference-free evaluation metric for image captioning. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 7\u201311 November 2021, pp. 7514\u20137528. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/V1\/2021.EMNLP-MAIN.595","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.595"},{"key":"28_CR6","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Hu, A., Chen, S., Jin, Q.: Question-controlled text-aware image captioning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3097\u20133105 (2021)","DOI":"10.1145\/3474085.3475452"},{"key":"28_CR8","doi-asserted-by":"publisher","unstructured":"Hu, A., Chen, S., Zhang, L., Jin, Q.: InfoMetIC: an informative metric for reference-free image caption evaluation. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 3171\u20133185. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.178","DOI":"10.18653\/v1\/2023.acl-long.178"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Tifa: accurate and interpretable text-to-image faithfulness evaluation with question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20406\u201320417 (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"28_CR10","doi-asserted-by":"publisher","unstructured":"Kasai, J., et al.: Transparent human evaluation for image captioning. In: Carpuat, M., de\u00a0Marneffe, M., Ru\u00edz, I.V.M. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, 10\u201315 July 2022, pp. 3464\u20133478. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/V1\/2022.NAACL-MAIN.254","DOI":"10.18653\/V1\/2022.NAACL-MAIN.254"},{"key":"28_CR11","unstructured":"Khashabi, D., Kordi, Y., Hajishirzi, H.: Unifiedqa-v2: stronger generalization via broader cross-format training. arXiv preprint arXiv:2202.12359 (2022)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Lee, H., Scialom, T., Yoon, S., Dernoncourt, F., Jung, K.: Qace: asking questions to evaluate an image caption. ArXiv arxiv:2108.12560 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.395"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Lee, H., Yoon, S., Dernoncourt, F., Bui, T., Jung, K.: Umic: an unreferenced metric for image captioning via contrastive learning. arXiv preprint arXiv:2106.14019 (2021)","DOI":"10.18653\/v1\/2021.acl-short.29"},{"key":"28_CR14","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: mPLUG: effective and efficient vision-language learning by cross-modal skip-connections. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7241\u20137259. Association for Computational Linguistics, Abu Dhabi (2022). DOI: https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.488","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"28_CR15","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"MacLeod, H., Bennett, C.L., Morris, M.R., Cutrell, E.: Understanding blind people\u2019s experiences with computer-generated captions of social media images. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 5988\u20135999 (2017)","DOI":"10.1145\/3025453.3025814"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Novikova, J., Du\u0161ek, O., Cercas\u00a0Curry, A., Rieser, V.: Why we need new evaluation metrics for NLG. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2241\u20132252. Association for Computational Linguistics, Copenhagen (2017). DOI: July10.18653\/v1\/D17-1238","DOI":"10.18653\/v1\/D17-1238"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"28_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"140","key":"28_CR20","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Bensa\u00efd, D., Brody, S., Ganz, R., Kimmel, R.: Fusecap: leveraging large language models for enriched fused image captions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5689\u20135700 (2024)","DOI":"10.1109\/WACV57701.2024.00559"},{"issue":"2","key":"28_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3485766","volume":"55","author":"AB Sai","year":"2022","unstructured":"Sai, A.B., Mohankumar, A.K., Khapra, M.M.: A survey of evaluation metrics used for NLG systems. ACM Comput. Surv. (CSUR) 55(2), 1\u201339 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"28_CR24","unstructured":"Sun, Y.: Mining the correlation between human and automatic evaluation at sentence level. In: LREC (2010)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"28_CR26","doi-asserted-by":"publisher","unstructured":"Wang, A., Cho, K., Lewis, M.: Asking and answering questions to evaluate the factual consistency of summaries. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5008\u20135020. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.450","DOI":"10.18653\/v1\/2020.acl-main.450"},{"key":"28_CR27","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9437-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:32:51Z","timestamp":1730392371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}