{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:18:07Z","timestamp":1742959087499,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811072987"},{"type":"electronic","value":"9789811072994"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-981-10-7299-4_53","type":"book-chapter","created":{"date-parts":[[2017,11,29]],"date-time":"2017-11-29T16:27:13Z","timestamp":1511972833000},"page":"638-649","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["FFGS: Feature Fusion with Gating Structure for Image Caption Generation"],"prefix":"10.1007","author":[{"given":"Aihong","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,11,30]]},"reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., Lawrence Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2422\u20132431 (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"53_CR2","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"issue":"4","key":"53_CR3","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., Hendricks, L.A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"issue":"12","key":"53_CR5","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1109\/TNNLS.2013.2271778","volume":"24","author":"M Fairbank","year":"2013","unstructured":"Fairbank, M., Alonso, E., Prokhorov, D.: An equivalence between adaptive dynamic programming with a critic and backpropagation through time. IEEE Trans. Neural Netw. Learn. Syst. (TNNLS) 24(12), 2088\u20132100 (2013)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst. (TNNLS)"},{"key":"53_CR6","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"issue":"4","key":"53_CR7","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":"53_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"12","key":"53_CR9","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., Berg, A.C., Berg, T.L.: BabyTalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53_CR10","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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"},{"issue":"99","key":"53_CR11","first-page":"1","volume":"PP","author":"X Lu","year":"2017","unstructured":"Lu, X., Zheng, X., Yuan, Y.: Remote sensing scene classification by unsupervised representation learning. IEEE Trans. Geosci. Remote Sens. PP(99), 1\u201310 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"53_CR12","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"53_CR13","doi-asserted-by":"crossref","unstructured":"Qu, B., Li, X., Tao, D., Lu, X.: Deep semantic understanding of high resolution remote sensing image. In: 2016 International Conference on Computer, Information and Telecommunication Systems (CITS), pp. 1\u20135, July 2016","DOI":"10.1109\/CITS.2016.7546397"},{"key":"53_CR14","unstructured":"Rashtchian, C., Young, P., Hodosh, M., Hockenmaier, J.: Collecting image annotations using Amazon\u2019s mechanical turk. In: Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk, pp. 139\u2013147. Association for Computational Linguistics (2010)"},{"key":"53_CR15","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"53_CR16","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. (TACL) 2, 207\u2013218 (2014)","journal-title":"Trans. Assoc. Comput. Linguist. (TACL)"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"53_CR18","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"4","key":"53_CR19","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53_CR20","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: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6\u201311 July 2015, pp. 2048\u20132057 (2015)"},{"key":"53_CR21","doi-asserted-by":"crossref","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. (TACL) 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist. (TACL)"},{"issue":"99","key":"53_CR22","first-page":"1","volume":"PP","author":"X Zheng","year":"2017","unstructured":"Zheng, X., Yuan, Y., Lu, X.: Dimensionality reduction by spatial-spectral preservation in selected bands. IEEE Trans. Geosci. Remote Sens. PP(99), 1\u201313 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Communications in Computer and Information Science","Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-7299-4_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:18:02Z","timestamp":1709821082000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-10-7299-4_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9789811072987","9789811072994"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-7299-4_53","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"30 November 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Chinese Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cccv2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ccf-cccv.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}