{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:11:54Z","timestamp":1742987514077,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819736225"},{"type":"electronic","value":"9789819736232"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-3623-2_11","type":"book-chapter","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T10:07:45Z","timestamp":1718878065000},"page":"138-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unbiased Image Caption Generation Based on\u00a0Dynamic Counterfactual Inference"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5534-8686","authenticated-orcid":false,"given":"Jinfei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-6411","authenticated-orcid":false,"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9287-3639","authenticated-orcid":false,"given":"Yana","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"11_CR1","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":"11_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"11_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). https:\/\/dblp.org\/db\/conf\/iclr\/iclr2015"},{"key":"11_CR4","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.3115\/1626355.1626389","DOI":"10.3115\/1626355.1626389"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10575\u201310584. IEEE Computer Society, Los Alamitos (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01059","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"11_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR, pp. 1\u201315 (2015)"},{"key":"11_CR7","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Proceedings of the 42nd Association for Computational Linguistics, pp. 74\u201381 (2004)"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Liu, B., et al.: Show, deconfound and tell: image captioning with causal inference. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), vol.\u00a044, pp. 18020\u201318029 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01751","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Lopez-Paz, D., Nishihara, R., Chintala, S., Scholkopf, B., Bottou, L.: Discovering causal signals in images. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 58\u201366. IEEE Computer Society, Los Alamitos (2017)","DOI":"10.1109\/CVPR.2017.14"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"11_CR12","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":"11_CR13","volume-title":"Causal Inference in Statistics: A Primer","author":"J Pearl","year":"2016","unstructured":"Pearl, J., Glymour, M., Jewell, N.P.: Causal Inference in Statistics: A Primer. John Wiley & Sons, Hoboken (2016)"},{"key":"11_CR14","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation, vol.\u00a014, pp. 1532\u20131543 (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Qi, J., Niu, Y., Huang, J., Zhang, H.: Two causal principles for improving visual dialog. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10857\u201310866 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01087","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Conference on Empirical Methods in Natural Language Processing (2018). https:\/\/api.semanticscholar.org\/CorpusID:52176506","DOI":"10.18653\/v1\/D18-1437"},{"key":"11_CR17","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a027. Curran Associates, Inc. (2014)"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 6000\u20136010 (2017).https:\/\/doi.org\/10.5555\/3295222.3295349","DOI":"10.5555\/3295222.3295349"},{"key":"11_CR19","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":"11_CR20","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Wang, T., Huang, J., Zhang, H., Sun, Q.: Visual commonsense r-cnn. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10757\u201310767 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01077","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"11_CR22","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, vol.\u00a037, pp. 2048\u20132057. PMLR (2015)"},{"issue":"11","key":"11_CR23","first-page":"12996","volume":"45","author":"X Yang","year":"2023","unstructured":"Yang, X., Zhang, H., Cai, J.: Deconfounded image captioning: a causal retrospect. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 12996\u201313010 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, H., Qi, G., Cai, J.: Causal attention for vision-language tasks. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9842\u20139852 (2021)","DOI":"10.1109\/CVPR46437.2021.00972"}],"container-title":["Communications in Computer and Information Science","Digital Multimedia Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-3623-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T10:10:20Z","timestamp":1718878220000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-3623-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819736225","9789819736232"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-3623-2_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 June 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IFTC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Forum on Digital TV and Wireless Multimedia Communications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iftc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.siga.org.cn\/xshd\/iftc2023.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}