{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:34:09Z","timestamp":1793151249907,"version":"4.5.0"},"publisher-location":"Cham","reference-count":44,"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"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_13","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T12:02:50Z","timestamp":1666958570000},"page":"219-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Object-Centric Unsupervised Image Captioning"],"prefix":"10.1007","author":[{"given":"Zihang","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"13_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":"13_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":"13_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"13_CR4","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":"13_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Pang, B., Sharma, P., Soricut, R.: Decoupled box proposal and featurization with ultrafine-grained semantic labels improve image captioning and visual question answering. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1468\u20131474 (2019)","DOI":"10.18653\/v1\/D19-1155"},{"key":"13_CR6","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8307\u20138316 (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Aneja, J., Wang, L., Schwing, A.G., Forsyth, D.: Fast, diverse and accurate image captioning guided by part-of-speech. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10695\u201310704 (2019)","DOI":"10.1109\/CVPR.2019.01095"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Elliott, D., Frank, S., Sima\u2019an, K., Specia, L.: Multi30k: multilingual English-German image descriptions. arXiv preprint arXiv:1605.00459 (2016)","DOI":"10.18653\/v1\/W16-3210"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Luo, J.: Unsupervised image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4125\u20134134 (2019)","DOI":"10.1109\/CVPR.2019.00425"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Wang, G.: Unpaired image captioning by language pivoting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 503\u2013519 (2018)","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"13_CR13","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\/CVF International Conference on Computer Vision, pp. 10323\u201310332 (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, Y., Song, P., Wang, M.: Recurrent relational memory network for unsupervised image captioning. arXiv preprint arXiv:2006.13611 (2020)","DOI":"10.24963\/ijcai.2020\/128"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R., Saenko, K., Darrell, T.: Deep compositional captioning: describing novel object categories without paired training data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u201310 (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Honda, U., Ushiku, Y., Hashimoto, A., Watanabe, T., Matsumoto, Y.: Removing word-level spurious alignment between images and pseudo-captions in unsupervised image captioning. arXiv preprint arXiv:2104.13872 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.323"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"13_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"13_CR20","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR21","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: International Conference on Machine Learning, pp. 957\u2013966. PMLR (2015)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Navab, N.: Towards unsupervised image captioning with shared multimodal embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7414\u20137424 (2019)","DOI":"10.1109\/ICCV.2019.00751"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Lan, W., Li, X., Dong, J.: Fluency-guided cross-lingual image captioning. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1549\u20131557 (2017)","DOI":"10.1145\/3123266.3123366"},{"issue":"9","key":"13_CR24","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1109\/TMM.2019.2896494","volume":"21","author":"X Li","year":"2019","unstructured":"Li, X., et al.: COCO-CN for cross-lingual image tagging, captioning, and retrieval. IEEE Trans. Multimedia 21(9), 2347\u20132360 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR25","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"13_CR26","unstructured":"Liu, F., Gao, M., Zhang, T., Zou, Y.: Exploring semantic relationships for unpaired image captioning. arXiv preprint arXiv:2106.10658 (2021)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Meng, Z., et al.: Connecting what to say with where to look by modeling human attention traces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12679\u201312688 (2021)","DOI":"10.1109\/CVPR46437.2021.01249"},{"key":"13_CR28","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":"13_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/978-3-030-58558-7_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Pont-Tuset","year":"2020","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., Ferrari, V.: Connecting vision and language with localized narratives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 647\u2013664. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_38"},{"key":"13_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Rajendran, J., Khapra, M.M., Chandar, S., Ravindran, B.: Bridge correlational neural networks for multilingual multimodal representation learning. arXiv preprint arXiv:1510.03519 (2015)","DOI":"10.18653\/v1\/N16-1021"},{"key":"13_CR32","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., Manning, C.D.: Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In: Proceedings of the Fourth Workshop on Vision and Language, pp. 70\u201380 (2015)","DOI":"10.18653\/v1\/W15-2812"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Song, Y., Chen, S., Zhao, Y., Jin, Q.: Unpaired cross-lingual image caption generation with self-supervised rewards. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 784\u2013792 (2019)","DOI":"10.1145\/3343031.3350996"},{"key":"13_CR36","unstructured":"Stefanini, M., Cornia, M., Baraldi, L., Cascianelli, S., Fiameni, G., Cucchiara, R.: From show to tell: a survey on image captioning. arXiv preprint arXiv:2107.06912 (2021)"},{"key":"13_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, 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":"13_CR39","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Anne Hendricks, L., Rohrbach, M., Mooney, R., Darrell, T., Saenko, K.: Captioning images with diverse objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5753\u20135761 (2017)","DOI":"10.1109\/CVPR.2017.130"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhao, S., Chen, J., Zhang, Y., Yuan, X., Su, Z.: Improving captioning for low-resource languages by cycle consistency. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 362\u2013367. IEEE (2019)","DOI":"10.1109\/ICME.2019.00070"},{"key":"13_CR41","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ying, Y., Lu, P., Zha, H.: Learning long-and short-term user literal-preference with multimodal hierarchical transformer network for personalized image caption. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 9571\u20139578 (2020)","DOI":"10.1609\/aaai.v34i05.6503"},{"key":"13_CR44","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: Proceedings of the AAAI Conference on Artificial Intelligence, 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_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:14:06Z","timestamp":1793150046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-20059-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_13","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}