{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:10:23Z","timestamp":1743091823891,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784552"},{"type":"electronic","value":"9783031784569"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78456-9_21","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:25:12Z","timestamp":1733138712000},"page":"325-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Branch Non-Autoregressive Image Captioning"],"prefix":"10.1007","author":[{"given":"Yuanqiu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R.K., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J.C., et\u00a0al.: From captions to visual concepts and back. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"21_CR4","unstructured":"Fei, Z.: Fast image caption generation with position alignment. CoRR abs\/1912.06365 (2019)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Iterative back modification for faster image captioning. In: ACM International Conference on Multimedia (ACM MM). p. 3182-3190 (2020)","DOI":"10.1145\/3394171.3413901"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Memory-augmented image captioning. In: AAAI Conference on Artificial Intelligence (AAAI). pp. 1317\u20131324 (2021)","DOI":"10.1609\/aaai.v35i2.16220"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Partially non-autoregressive image captioning. In: AAAI Conference on Artificial Intelligence (AAAI). pp. 1309\u20131316 (2021)","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"21_CR8","unstructured":"Gao, J., Meng, X., Wang, S., Li, X., Wang, S., Ma, S., Gao, W.: Masked non-autoregressive image captioning. CoRR abs\/1906.00717 (2019)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, G., Cai, J., Chen, T.: An empirical study of language cnn for image captioning. In: IEEE international conference on computer vision (ICCV). pp. 1222\u20131231 (2017)","DOI":"10.1109\/ICCV.2017.138"},{"key":"21_CR11","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. In: International Joint Conference on Artificial Intelligence (IJCAI). pp. 767\u2013773 (2020)","DOI":"10.24963\/ijcai.2020\/107"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Ji, J., Luo, Y., Sun, X., Chen, F., Luo, G., Wu, Y., Gao, Y., Ji, R.: Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. In: AAAI Conference on Artificial Intelligence (AAAI). pp. 1655\u20131663 (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 1317\u20131327 (2016)","DOI":"10.18653\/v1\/D16-1139"},{"key":"21_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Lavie, A., Agarwal, A.: Meteor: An automatic metric for mt evaluation with high levels of correlation with human judgments. In: Workshop on Statistical Machine Translation. pp. 228\u2013231 (2007)","DOI":"10.3115\/1626355.1626389"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Pan, Y., Yao, T., Mei, T.: Comprehending and ordering semantics for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 17990\u201317999 (2022)","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"21_CR19","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out. pp. 74\u201381 (2004)"},{"key":"21_CR20","doi-asserted-by":"crossref","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: European Conference on Computer Vision (ECCV). pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR22","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, V.Q., Suganuma, M., Okatani, T.: Grit: Faster and better image captioning transformer using dual visual features. In: European Conference on Computer Vision (ECCV). pp. 167\u2013184 (2022)","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: Annual Meeting of the Association for Computational Linguistics (ACL). pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"21_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: NIPS. pp. 5998\u20136008 (2017)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, J., Sun, Y.: End-to-end transformer based model for image captioning. In: AAAI Conference on Artificial Intelligence (AAAI). pp. 2585\u20132594 (2022)","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Xian, T., Li, Z., Zhang, C., Ma, H.: Dual global enhanced transformer for image captioning. In: Neural Networks. vol.\u00a0148, pp. 129\u2013141 (2022)","DOI":"10.1016\/j.neunet.2022.01.011"},{"key":"21_CR30","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML). pp. 2048\u20132057 (2015)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Yan, X., Fei, Z., Li, Z., Wang, S., Huang, Q., Tian, Q.: Semi-autoregressive image captioning. In: ACM International Conference on Multimedia (ACM MM). pp. 2708\u20132716 (2021)","DOI":"10.1145\/3474085.3475179"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, Y., Hu, Z., Wang, M.: Semi-autoregressive transformer for image captioning. In: IEEE International Conference on Computer Vision Workshops (ICCVW). pp. 3132\u20133136 (2021)","DOI":"10.1109\/ICCVW54120.2021.00350"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:12:43Z","timestamp":1733141563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}