{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:35:11Z","timestamp":1744220111463,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208691"},{"type":"electronic","value":"9783030208707"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20870-7_2","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"21-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Gated Hierarchical Attention for Image Captioning"],"prefix":"10.1007","author":[{"given":"Qingzhong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"key":"2_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":"2_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. arXiv preprint arXiv:1707.07998 (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Aneja, J., Deshpande, A., Schwing, A.: Convolutional image captioning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00583"},{"key":"2_CR4","unstructured":"Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Conneau, A., Schwenk, H., Barrault, L., Lecun, Y.: Very deep convolutional networks for text classification. In: EACL (2017)","DOI":"10.18653\/v1\/E17-1104"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yang, G., Veit, A., Huang, X., Belongie, S.: Learning to evaluate image captioning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00608"},{"key":"2_CR7","unstructured":"Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: ICML (2017)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: METEOR universal: language specific translation evaluation for any target language. In: EACL Workshop on Statistical Machine Translation (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Gan, Z., et al.: Semantic compositional networks for visual captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"2_CR12","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: ICML (2017)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, G., Cai, J., Chen, T.: An empirical study of language CNN for image captioning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.138"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR15","unstructured":"Jetley, S., Lord, N., Lee, N., Torr, P.: Learn to pay attention. In: ICLR (2018)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"2_CR18","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.356"},{"key":"2_CR20","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: ACL Workshop (2004)"},{"key":"2_CR21","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":"TY 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":"2_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhu, Z., Ye, N., Guadarrama, S., Murphy, K.: Improved image captioning via policy gradient optimization of spider. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.100"},{"key":"2_CR23","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Shang, L., Li, H.: Multimodal convolutional neural networks for matching image and sentence. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.301"},{"key":"2_CR25","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632 (2014)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Hierarchical multimodal LSTM for dense visual-semantic embedding. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.208"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Osman, A., Samek, W.: Dual recurrent attention units for visual question answering. arXiv preprint arXiv:1802.00209 (2018)","DOI":"10.1016\/j.cviu.2019.05.001"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Pedersoli, M., Lucas, T., Schmid, C., Verbeek, J.: Areas of attention for image captioning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.140"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Pu, Y., Min, M.R., Gan, Z., Carin, L.: Adaptive feature abstraction for translating video to text. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12245"},{"key":"2_CR32","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 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"2_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"1","key":"2_CR34","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"2_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-319-54193-8_7","volume-title":"Computer Vision \u2013 ACCV 2016","author":"YH Tan","year":"2017","unstructured":"Tan, Y.H., Chan, C.S.: phi-LSTM: a phrase-based hierarchical LSTM model for image captioning. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10115, pp. 101\u2013117. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54193-8_7"},{"key":"2_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2_CR40","unstructured":"Wang, L., Schwing, A., Lazebnik, S.: Diverse and accurate image description using a variational auto-encoder with an additive Gaussian encoding space. In: NIPS (2017)"},{"key":"2_CR41","unstructured":"Wang, Q., Chan, A.B.: CNN+CNN: convolutional decoders for image captioning. arXiv preprint arXiv:1805.09019 (2018)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., van den Hengel, A.: What value do explicit high level concepts have in vision to language problems? In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.29"},{"key":"2_CR43","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"2_CR44","unstructured":"Yang, Z., Yuan, Y., Wu, Y., Cohen, W.W., Salakhutdinov, R.R.: Review networks for caption generation. In: NIPS (2016)"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T16:18:32Z","timestamp":1663517912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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","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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}