{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:25:26Z","timestamp":1771953926204,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_7","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"113-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Explicit Image Caption Editing"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangxing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulei","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"7_CR1","unstructured":"Alva-Manchego, F., Bingel, J., Paetzold, G., Scarton, C., Specia, L.: Learning how to simplify from explicit labeling of complex-simplified text pairs. In: IJCNLP, pp. 295\u2013305 (2017)"},{"key":"7_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":"7_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Awasthi, A., Sarawagi, S., Goyal, R., Ghosh, S., Piratla, V.: Parallel iterative edit models for local sequence transduction. arXiv (2019)","DOI":"10.18653\/v1\/D19-1435"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Jiang, Z., Xiao, J., Liu, W.: Human-like controllable image captioning with verb-specific semantic roles. In: CVPR, pp. 16846\u201316856 (2021)","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR, pp. 326\u2013335 (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"7_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv (2018)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Y., Li, Z., Rezagholizadeh, M., Cheung, J.C.K.: Editnts: an neural programmer-interpreter model for sentence simplification through explicit editing. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1331"},{"key":"7_CR10","unstructured":"Fei, Z.C.: Fast image caption generation with position alignment. arXiv (2019)"},{"key":"7_CR11","unstructured":"Gao, J., et al.: Masked non-autoregressive image captioning. arXiv (2019)"},{"key":"7_CR12","unstructured":"Gu, J., Wang, C., Zhao, J.: Levenshtein transformer. In: NeurIPS 32 (2019)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., He, X., Jiang, J., Lu, H.: Non-autoregressive image captioning with counterfactuals-critical multi-agent learning. arXiv (2020)","DOI":"10.24963\/ijcai.2020\/107"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also snowboard: overcoming bias in captioning models. In: ECCV, pp. 771\u2013787 (2018)","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: ICCV, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR. pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Kayser, M., et al.: e-vil: a dataset and benchmark for natural language explanations in vision-language tasks. arXiv (2021)","DOI":"10.1109\/ICCV48922.2021.00128"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"7_CR19","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"7_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Liu, A.A., Zhai, Y., Xu, N., Nie, W., Li, W., Zhang, Y.: Region-aware image captioning via interaction learning. In: IEEE Transactions on Circuits and Systems for Video Technology (2021)","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"7_CR22","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"7_CR23","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: CVPR, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"7_CR24","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":"7_CR25","doi-asserted-by":"crossref","unstructured":"Mallinson, J., Severyn, A., Malmi, E., Garrido, G.: Felix: flexible text editing through tagging and insertion. arXiv (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.111"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Malmi, E., Krause, S., Rothe, S., Mirylenka, D., Severyn, A.: Encode, tag, realize: High-precision text editing. arXiv (2019)","DOI":"10.18653\/v1\/D19-1510"},{"key":"7_CR27","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv (2014)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Mao, Y., Chen, L., Jiang, Z., Zhang, D., Zhang, Z., Shao, J., Xiao, J.: Rethinking the reference-based distinctive image captioning. In: ACMMM (2022)","DOI":"10.1145\/3503161.3548358"},{"issue":"1","key":"7_CR29","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11263-015-0840-y","volume":"119","author":"V Ordonez","year":"2015","unstructured":"Ordonez, V., Han, X., Kuznetsova, P., Kulkarni, G., Mitchell, M., Yamaguchi, K., Stratos, K., Goyal, A., Dodge, J., Mensch, A., Daum\u00e9, H., Berg, A.C., Choi, Y., Berg, T.L.: Large scale retrieval and generation of image descriptions. Int. J. Comput. Vis. 119(1), 46\u201359 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0840-y","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward. In: CVPR, pp. 290\u2013298 (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"7_CR34","unstructured":"Sammani, F., Elsayed, M.: Look and modify: modification networks for image captioning. arXiv (2019)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Sammani, F., Melas-Kyriazi, L.: Show, edit and tell: a framework for editing image captions. In: CVPR, pp. 4808\u20134816 (2020)","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"7_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS 30 (2017)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, N., Liu, A.A., Li, W., Zhang, Y.: High-order interaction learning for image captioning. In: IEEE Transactions on Circuits and Systems for Video Technology (2021)","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"7_CR40","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv (2016)"},{"key":"7_CR41","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"issue":"5","key":"7_CR42","first-page":"1372","volume":"22","author":"N Xu","year":"2019","unstructured":"Xu, N., et al.: Multi-level policy and reward-based deep reinforcement learning framework for image captioning. TMM 22(5), 1372\u20131383 (2019)","journal-title":"TMM"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"7_CR44","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. TACL 2, 67\u201378 (2014)","journal-title":"TACL"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and vqa. In: AAAI, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:06:34Z","timestamp":1666973194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}