{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T20:38:21Z","timestamp":1770496701877,"version":"3.49.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031446924","type":"print"},{"value":"9783031446931","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44693-1_37","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"469-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Bounding and\u00a0Filling: A Fast and\u00a0Flexible Framework for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Ma","sequence":"first","affiliation":[]},{"given":"Changxin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zixuan","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jianbing","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: Spice: semantic propositional image caption evaluation. In: Proceedings of ECCV (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"37_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 CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"37_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of ACL workshop (2005)"},{"key":"37_CR4","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"37_CR6","unstructured":"Fei, Z.: Fast image caption generation with position alignment. arXiv preprint arXiv:1912.06365 (2019)"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Iterative back modification for faster image captioning. In: Proceedings of ACM MM (2020)","DOI":"10.1145\/3394171.3413901"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Partially non-autoregressive image captioning. In: Proceedings of AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"37_CR9","unstructured":"Gao, J., Meng, X., Wang, S., Li, X., Wang, S., Ma, S., Gao, W.: Masked non-autoregressive image captioning. arXiv preprint arXiv:1906.00717 (2019)"},{"key":"37_CR10","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 preprint arXiv:2005.04690 (2020)","DOI":"10.24963\/ijcai.2020\/107"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR12","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. CoRR (2015)"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"37_CR15","unstructured":"Kaiser, L., et al.: Fast decoding in sequence models using discrete latent variables. In: Proceedings of ICML (2018)"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"37_CR17","volume-title":"Visual genome: connecting language and vision using crowdsourced dense image annotations","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput, Vis (2017)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Pan, Y., Yao, T., Mei, T.: Comprehending and ordering semantics for image captioning. In: Proceedings of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"37_CR19","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out (2004)"},{"key":"37_CR20","unstructured":"Luo, R.: A better variant of self-critical sequence training. CoRR (2020)"},{"key":"37_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 ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"37_CR22","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of NeurIPS (2015)"},{"key":"37_CR23","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 CVPR (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Song, Z., Zhou, X., Dong, L., Tan, J., Guo, L.: Direction relation transformer for image captioning. In: Proceedings of ACM MM (2021)","DOI":"10.1145\/3474085.3475607"},{"key":"37_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS (2017)"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Yan, X., Fei, Z., Li, Z., Wang, S., Huang, Q., Tian, Q.: Semi-autoregressive image captioning. In: Proceedings of ACM MM (2021)","DOI":"10.1145\/3474085.3475179"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Y., Qi, P., Manning, C.D., Langlotz, C.P.: Biomedical and clinical English model packages in the stanza python NLP library. CoRR (2020)","DOI":"10.1093\/jamia\/ocab090"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, Y., Hu, Z., Wang, M.: Semi-autoregressive transformer for image captioning. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00350"}],"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\/978-3-031-44693-1_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:23:39Z","timestamp":1696839819000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44693-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446924","9783031446931"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44693-1_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","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":"Foshan","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":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","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":"143","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":"30% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}