{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T04:10:31Z","timestamp":1746159031132,"version":"3.37.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208752"},{"type":"electronic","value":"9783030208769"}],"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\/978-3-030-20876-9_37","type":"book-chapter","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T10:03:53Z","timestamp":1558778633000},"page":"587-602","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multivariate Attention Network for Image Captioning"],"prefix":"10.1007","author":[{"given":"Weixuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,26]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M.: Bottom-up and top-down attention for image captioning and visual question answering. In: Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Benyounes, H., Cadene, R., Cord, M., Thome, N.: Mutan: multimodal tucker fusion for visual question answering. In: International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"37_CR4","unstructured":"Denkowski, M., Lavie, A.: Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 85\u201391. Association for Computational Linguistics (2011)"},{"key":"37_CR5","unstructured":"Flick, C.: ROUGE: a package for automatic evaluation of summaries. In: The Workshop on Text Summarization Branches Out, p. 10 (2004)"},{"issue":"12","key":"37_CR6","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2017","unstructured":"Fu, K., Jin, J., Cui, R., Sha, F., Zhang, C.: Aligning where to see and what to tell: image captioning with region-based attention and scene-specific contexts. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2321\u20132334 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Gan, Z., et al.: Semantic compositional networks for visual captioning. In: Computer Vision and Pattern Recognition, pp. 5630\u20135639 (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"37_CR8","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","volume-title":"Supervised Sequence Labelling with Recurrent Neural Networks","author":"A Graves","year":"2012","unstructured":"Graves, A.: Long short-term memory. In: Graves, A. (ed.) Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence, vol. 385, pp. 37\u201345. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-24797-2_4"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"37_CR11","unstructured":"Kim, J.H., et al.: Multimodal residual learning for visual QA. In: Advances in Neural Information Processing Systems, pp. 361\u2013369 (2016)"},{"key":"37_CR12","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. arXiv preprint \n                      arXiv:1610.04325\n                      \n                     (2016)"},{"key":"37_CR13","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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"37_CR14","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: International Conference on Computer Vision, pp. 873\u2013881 (2017)","DOI":"10.1109\/ICCV.2017.100"},{"key":"37_CR15","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: Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: Computer Vision and Pattern Recognition, pp. 7219\u20137228 (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"issue":"2","key":"37_CR17","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.neuron.2018.03.009","volume":"98","author":"Y Lu","year":"2018","unstructured":"Lu, Y., et al.: Revealing detail along the visual hierarchy: neural clustering preserves acuity from v1 to v4. Neuron 98(2), 417\u2013428 (2018)","journal-title":"Neuron"},{"key":"37_CR18","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint \n                      arXiv:1412.6632\n                      \n                     (2014)"},{"key":"37_CR19","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 on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"37_CR20","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint \n                      arXiv:1511.06732\n                      \n                     (2015)"},{"key":"37_CR21","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2","key":"37_CR23","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/0959-4388(94)90066-3","volume":"4","author":"LG Ungerleider","year":"1994","unstructured":"Ungerleider, L.G., Haxby, J.V.: \u2018what\u2019 and \u2018where\u2019 in the human brain. Curr. Opin. Neurobiol. 4(2), 157\u2013165 (1994)","journal-title":"Curr. Opin. Neurobiol."},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"1","key":"37_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Li, F.F., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lin, Z., Shen, X., Cohen, S., Cottrell, G.W.: Skeleton key: image captioning by skeleton-attribute decomposition. In: Computer Vision and Pattern Recognition, pp. 7272\u20137281 (2017)","DOI":"10.1109\/CVPR.2017.780"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., Hengel, A.V.D.: What value do explicit high level concepts have in vision to language problems? In: Computer Vision and Pattern Recognition, pp. 203\u2013212 (2016)","DOI":"10.1109\/CVPR.2016.29"},{"key":"37_CR29","unstructured":"Xu, K., Ba, J.L., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"37_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."},{"key":"37_CR32","unstructured":"Zhang, L., et al.: Actor-critic sequence training for image captioning. arXiv preprint \n                      arXiv:1706.09601\n                      \n                     (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20876-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T10:09:56Z","timestamp":1558778996000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20876-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208752","9783030208769"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20876-9_37","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":"26 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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"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"}},{"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"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}