{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:44:54Z","timestamp":1743021894036,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819754946"},{"type":"electronic","value":"9789819754953"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5495-3_27","type":"book-chapter","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T10:02:27Z","timestamp":1721901747000},"page":"358-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Image Captioning with\u00a0Image Concepts of\u00a0Words"],"prefix":"10.1007","author":[{"given":"Yiyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunzhi","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingfei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,26]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: noCaps: novel object captioning at scale. In: ICCV, pp. 8947\u20138956 (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"27_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":"27_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":"27_CR4","unstructured":"Aoki, T., Kitada, S., Iyatomi, H.: Text classification through glyph-aware disentangled character embedding and semantic sub-character augmentation. In: AACL\/IJCNLP, Student Research Workshop, pp.\u00a01\u20137 (2020)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: CVPR, pp. 10575\u201310584 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Fang, Z., et al.: Injecting semantic concepts into end-to-end image captioning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"27_CR8","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. In: NeurIPS, pp. 11135\u201311145 (2019)"},{"issue":"8","key":"27_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.: Attention on attention for image captioning. In: ICCV, pp. 4633\u20134642 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Ji, J., et al.: Improving image captioning by leveraging intra- and inter-layer global representation in transformer network. In: AAAI, pp. 1655\u20131663 (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"issue":"4","key":"27_CR12","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664\u2013676 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR13","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: ACL, pp. 228\u2013231 (2007)","DOI":"10.3115\/1626355.1626389"},{"key":"27_CR14","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: ACL Workshop on Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"27_CR15","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., et al.: 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":"27_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: AAAI, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: CVPR, pp. 10968\u201310977 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: BleU: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"27_CR20","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, pp. 91\u201399 (2015)"},{"key":"27_CR21","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. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Shimada, D., Kotani, R., Iyatomi, H.: Document classification through image-based character embedding and wildcard training. In: BigData, pp. 3922\u20133927 (2016)","DOI":"10.1109\/BigData.2016.7841067"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Sun, B., Yang, L., Dong, P., Zhang, W., Dong, J., Young, C.: Super characters: a conversion from sentiment classification to image classification. In: EMNLP Workshop WASSA, pp. 309\u2013315 (2018)","DOI":"10.18653\/v1\/W18-6245"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: ChineseBERT: Chinese pretraining enhanced by glyph and pinyin information. In: ACL\/IJCNLP, pp. 2065\u20132075 (2021)","DOI":"10.18653\/v1\/2021.acl-long.161"},{"key":"27_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"27_CR27","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":"27_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, J., Sun, Y.: End-to-end transformer based model for image captioning. In: AAAI, pp. 2585\u20132594 (2022)","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"27_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. arXiv abs\/1502.03044 (2015)"},{"issue":"6","key":"27_CR30","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.55730\/1300-0632.4035","volume":"31","author":"S Yildiz","year":"2023","unstructured":"Yildiz, S., Memis, A., Varli, S.: Trcaptionnet: a novel and accurate deep Turkish image captioning model with vision transformer based image encoders and deep linguistic text decoders. Turkish J. Electr. Eng. Comput. Sci. 31(6), 1079\u20131098 (2023)","journal-title":"Turkish J. Electr. Eng. Comput. Sci."},{"key":"27_CR31","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. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5495-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T10:09:08Z","timestamp":1721902148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5495-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819754946","9789819754953"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5495-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Birmingham","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2024","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":"ksem2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ai-edge.net\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}