{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:04:39Z","timestamp":1742911479125,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007751"},{"type":"electronic","value":"9783030007768"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00776-8_56","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T08:14:58Z","timestamp":1537258498000},"page":"611-621","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Dialog with Multi-turn Attentional Memory Network"],"prefix":"10.1007","author":[{"given":"Dejiang","family":"Kong","sequence":"first","affiliation":[]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"56_CR1","unstructured":"Bordes, A., Boureau, Y.L., Weston, J.: Learning end-to-end goal-oriented dialog. In: International Conference on Learning Representations (2017)"},{"key":"56_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Zhao, S., Han, J.: Temporal-difference learning with sampling baseline for image captioning. In: AAAI-18 AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12263"},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Ding, G., Zhao, S., Chen, H., Liu, Q., Han, J.: Reference based LSTM for image captioning. In: AAAI, pp. 3981\u20133987 (2017)","DOI":"10.1609\/aaai.v31i1.11198"},{"key":"56_CR4","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"56_CR5","doi-asserted-by":"crossref","unstructured":"De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: Guesswhat?! visual object discovery through multi-modal dialogue. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"56_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"56_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"issue":"8","key":"56_CR8","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":"56_CR9","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"56_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., Monroe, W., Ritter, A., Jurafsky, D., Galley, M., Gao, J.: Deep reinforcement learning for dialogue generation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1192\u20131202 (2016)","DOI":"10.18653\/v1\/D16-1127"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., Jurafsky, D.: Adversarial learning for neural dialogue generation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2157\u20132169 (2017)","DOI":"10.18653\/v1\/D17-1230"},{"key":"56_CR12","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":"56_CR13","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"56_CR14","unstructured":"Mansimov, E., Parisotto, E., Ba, J.L., Salakhutdinov, R.: Generating images from captions with attention. In: International Conference on Learning Representations (2016)"},{"key":"56_CR15","doi-asserted-by":"crossref","unstructured":"Noh, H., Seo, P.H., Han, B.: Image question answering using convolutional neural network with dynamic parameter prediction. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 30\u201338 (2016)","DOI":"10.1109\/CVPR.2016.11"},{"key":"56_CR16","unstructured":"Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069 (2016)"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Serban, I.V., Sordoni, A., Bengio, Y., Courville, A.C., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: AAAI, vol. 16, pp. 3776\u20133784 (2016)","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"56_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"56_CR19","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"56_CR20","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference onComputer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"56_CR21","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"56_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"56_CR23","unstructured":"Zhou, L., Small, K., Rokhlenko, O., Elkan, C.: End-to-end offline goal-oriented dialog policy learning via policy gradient (2017)"},{"key":"56_CR24","unstructured":"Zhu, L., Xu, Z., Yang, Y., Hauptmann, A.G.: Uncovering temporal context for video question and answering. arXiv preprint arXiv:1511.04670 (2015)"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00776-8_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:30:34Z","timestamp":1710333034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00776-8_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007751","9783030007768"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00776-8_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}