{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:20:11Z","timestamp":1782404411410,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464770","type":"print"},{"value":"9783319464787","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46478-7_28","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:48:37Z","timestamp":1473932917000},"page":"451-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":318,"title":["Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Huijuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"issue":"2","key":"28_CR1","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/MMUL.2014.29","volume":"21","author":"K Tu","year":"2014","unstructured":"Tu, K., Meng, M., Lee, M.W., Choe, T.E., Zhu, S.C.: Joint video and text parsing for understanding events and answering queries. IEEE MultiMedia 21(2), 42\u201370 (2014)","journal-title":"IEEE MultiMedia"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Lasecki, W.S., Zhong, Y., Bigham, J.P.: Increasing the bandwidth of crowdsourced visual question answering to better support blind users. In: Proceedings of the 16th International ACM SIGACCESS Conference on Computers and Accessibility, pp. 263\u2013264. ACM (2014)","DOI":"10.1145\/2661334.2661407"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. arXiv preprint \n                      arXiv:1411.4389\n                      \n                     (2014)","DOI":"10.21236\/ADA623249"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. arXiv preprint \n                      arXiv:1411.4555\n                      \n                     (2014)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"28_CR5","unstructured":"Karpathy, A., Joulin, A., Li, F.F.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in Neural Information Processing Systems, pp. 1889\u20131897 (2014)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J., et al.: From captions to visual concepts and back. arXiv preprint \n                      arXiv:1411.4952\n                      \n                     (2014)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: VQA: visual question answering. CoRR abs\/1505.00468 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"28_CR8","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. CoRR abs\/1410.0210 (2014)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. arXiv preprint \n                      arXiv:1505.01121\n                      \n                     (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"28_CR10","unstructured":"Ren, M., Kiros, R., Zemel, R.S.: Exploring models and data for image question answering. CoRR abs\/1505.02074 (2015)"},{"key":"28_CR11","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv preprint \n                      arXiv:1512.02167\n                      \n                     (2015)"},{"key":"28_CR12","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. CoRR abs\/1410.3916 (2014)"},{"key":"28_CR13","unstructured":"Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: End-to-end memory networks. arXiv preprint \n                      arXiv:1503.08895\n                      \n                     (2015)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint \n                      arXiv:1408.5093\n                      \n                     (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"28_CR15","unstructured":"Yahya, M., Berberich, K., Elbassuoni, S., Ramanath, M., Tresp, V., Weikum, G.: Natural language questions for the web of data. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Association for Computational Linguistics, pp. 379\u2013390 (2012)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Proceedings of ACL, vol. 7, p. 92 (2014)","DOI":"10.3115\/v1\/P14-1133"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Bordes, A., Chopra, S., Weston, J.: Question answering with subgraph embeddings. arXiv preprint \n                      arXiv:1406.3676\n                      \n                     (2014)","DOI":"10.3115\/v1\/D14-1067"},{"key":"28_CR18","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint \n                      arXiv:1410.5401\n                      \n                     (2014)"},{"key":"28_CR19","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. CoRR abs\/1603.01417 (2016)"},{"key":"28_CR20","unstructured":"Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. arXiv preprint \n                      arXiv:1502.03044\n                      \n                     (2015)"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"28_CR22","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint \n                      arXiv:1409.0473\n                      \n                     (2014)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint \n                      arXiv:1508.04025\n                      \n                     (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"28_CR24","unstructured":"Hermann, K.M., Kocisky, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., Blunsom, P.: Teaching machines to read and comprehend. In: Advances in Neural Information Processing Systems, pp. 1684\u20131692 (2015)"},{"issue":"11","key":"28_CR25","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"Kyunghyun Cho","year":"2015","unstructured":"Cho, K., Courville, A., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks (2015)","journal-title":"IEEE Transactions on Multimedia"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7W: grounded question answering in images. arXiv preprint \n                      arXiv:1511.03416\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.540"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., van den Hengel, A., Dick, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. arXiv preprint \n                      arXiv:1511.06973\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.500"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Noh, H., Seo, P.H., Han, B.: Image question answering using convolutional neural network with dynamic parameter prediction. arXiv preprint \n                      arXiv:1511.05756\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.11"},{"key":"28_CR29","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: CVPR 2015 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. arXiv preprint \n                      arXiv:1511.07394\n                      \n                     (2015)","DOI":"10.1109\/CVPR.2016.499"},{"key":"28_CR31","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, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10602-1_48"},{"key":"28_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33715-4_54"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. arXiv preprint \n                      arXiv:1412.4729\n                      \n                     (2014)","DOI":"10.3115\/v1\/N15-1173"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46478-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:15:53Z","timestamp":1602292553000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46478-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464770","9783319464787"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"16 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","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":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","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"}]}}