{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:29:18Z","timestamp":1777656558730,"version":"3.51.4"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585679","type":"print"},{"value":"9783030585686","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58568-6_34","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T14:03:09Z","timestamp":1605189789000},"page":"574-590","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning"],"prefix":"10.1007","author":[{"given":"Xiangxi","family":"Shi","sequence":"first","affiliation":[]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jiuxiang","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Shafiq","family":"Joty","sequence":"additional","affiliation":[]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"issue":"7","key":"34_CR1","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s10514-018-9734-5","volume":"42","author":"PF Alcantarilla","year":"2018","unstructured":"Alcantarilla, P.F., Stent, S., Ros, G., Arroyo, R., Gherardi, R.: Street-view change detection with deconvolutional networks. Auton. Robots 42(7), 1301\u20131322 (2018)","journal-title":"Auton. Robots"},{"key":"34_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, Part V. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"34_CR3","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":"34_CR4","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1171\u20131179 (2015)"},{"issue":"3","key":"34_CR5","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1109\/36.843009","volume":"38","author":"L Bruzzone","year":"2000","unstructured":"Bruzzone, L., Prieto, D.F.: Automatic analysis of the difference image for unsupervised change detection. IEEE Trans. Geosci. Remote Sensi. 38(3), 1171\u20131182 (2000)","journal-title":"IEEE Trans. Geosci. Remote Sensi."},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., Mu, S., Xiao, W., Ye, Z., Wu, L., Ju, Q.: Improving image captioning with conditional generative adversarial nets. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, vol. 33, pp. 8142\u20138150 (2019)","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Daudt, R.C., Le Saux, B., Boulch, A.: Fully convolutional siamese networks for change detection. In: Proceedings of the 2018 25th IEEE International Conference on Image Processing, pp. 4063\u20134067. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"34_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Wang, G., Chen, T.: Stack-captioning: Coarse-to-fine learning for image captioning. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"34_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-030-01246-5_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Gu","year":"2018","unstructured":"Gu, J., Joty, S., Cai, J., Wang, G.: Unpaired image captioning by language pivoting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part I. LNCS, vol. 11205, pp. 519\u2013535. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_31"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., Wang, G.: Unpaired image captioning via scene graph alignments. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Jhamtani, H., Berg-Kirkpatrick, T.: Learning to describe differences between pairs of similar images. In: arXiv preprint arXiv:1808.10584 (2018)","DOI":"10.18653\/v1\/D18-1436"},{"key":"34_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"34_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"34_CR17","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp. 74\u201381 (2004)"},{"key":"34_CR18","unstructured":"Oh, S., et al.: A large-scale benchmark dataset for event recognition in surveillance video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3153\u20133160. IEEE (2011)"},{"key":"34_CR19","doi-asserted-by":"publisher","first-page":"106773","DOI":"10.1109\/ACCESS.2019.2931223","volume":"7","author":"A Oluwasanmi","year":"2019","unstructured":"Oluwasanmi, A., Aftab, M.U., Alabdulkreem, E., Kumeda, B., Baagyere, E.Y., Qin, Z.: Captionnet: automatic end-to-end siamese difference captioning model with attention. IEEE Access 7, 106773\u2013106783 (2019)","journal-title":"IEEE Access"},{"key":"34_CR20","doi-asserted-by":"publisher","first-page":"175929","DOI":"10.1109\/ACCESS.2019.2957513","volume":"7","author":"A Oluwasanmi","year":"2019","unstructured":"Oluwasanmi, A., Frimpong, E., Aftab, M.U., Baagyere, E.Y., Qin, Z., Ullah, K.: Fully convolutional captionnet: siamese difference captioning attention model. IEEE Access 7, 175929\u2013175939 (2019)","journal-title":"IEEE Access"},{"key":"34_CR21","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 on Association for Computational Linguistics, pp. 311\u2013318. Proceedings of Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4624\u20134633 (2019)","DOI":"10.1109\/ICCV.2019.00472"},{"key":"34_CR23","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"34_CR26","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"},{"issue":"1","key":"34_CR27","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TGRS.2018.2849692","volume":"57","author":"Q Wang","year":"2018","unstructured":"Wang, Q., Yuan, Z., Du, Q., Li, X.: Getnet: A general end-to-end 2-D CNN framework for hyperspectral image change detection. IEEE Trans. Geosci. Remote Sens. 57(1), 3\u201313 (2018)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"34_CR28","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 2019","DOI":"10.1109\/CVPR.2019.01094"},{"key":"34_CR30","unstructured":"Yang, X., Zhang, H., Cai, J.: Deconfounded image captioning: A causal retrospect. arXiv preprint arXiv:2003.03923 (2020)"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Yu, L., Zhang, W., Wang, J., Yu, Y.: Seqgan: sequence generative adversarial nets with policy gradient. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10804"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58568-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:25:05Z","timestamp":1731371105000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58568-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585679","9783030585686"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58568-6_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}