{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:22:04Z","timestamp":1760955724266},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319588377"},{"type":"electronic","value":"9783319588384"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-58838-4_41","type":"book-chapter","created":{"date-parts":[[2017,5,11]],"date-time":"2017-05-11T15:54:08Z","timestamp":1494518048000},"page":"372-380","source":"Crossref","is-referenced-by-count":2,"title":["VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Marc","family":"Bola\u00f1os","sequence":"first","affiliation":[]},{"given":"\u00c1lvaro","family":"Peris","sequence":"additional","affiliation":[]},{"given":"Francisco","family":"Casacuberta","sequence":"additional","affiliation":[]},{"given":"Petia","family":"Radeva","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,5,12]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh., D.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"41_CR2","unstructured":"Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO captions: data collection and evaluation server. arXiv:1504.00325 (2015)"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, G., Zhou, P., Han, J.: RIFD-CNN: rotation-invariant and fisher discriminative convolutional neural networks for object detection. In: CVPR, pp. 2884\u20132893 (2016)","DOI":"10.1109\/CVPR.2016.315"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"issue":"10","key":"41_CR5","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451\u20132471 (2000)","journal-title":"Neural Comput."},{"issue":"8","key":"41_CR6","doi-asserted-by":"crossref","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":"41_CR7","unstructured":"Kim, J.-H., Lee, S.-W., Kwak, D.-H., Heo, M.-O., Kim, J., Ha, J.-W., Zhang, B.-T.: Multimodal residual learning for visual QA. arXiv:1606.01455 (2016)"},{"key":"41_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"41_CR9","unstructured":"Liu, Z.: Kernelized deep convolutional neural network for describing complex images. arXiv:1509.04581 (2015)"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.-W., Kim, J.: Dual attention networks for multimodal reasoning and matching. arXiv:1611.00471 (2016)","DOI":"10.1109\/CVPR.2017.232"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"41_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-44781-0_1","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2016","author":"\u00c1 Peris","year":"2016","unstructured":"Peris, \u00c1., Bola\u00f1os, M., Radeva, P., Casacuberta, F.: Video description using bidirectional recurrent neural networks. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 3\u201311. Springer, Cham (2016). doi: 10.1007\/978-3-319-44781-0_1"},{"key":"41_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15561-1_11"},{"issue":"4","key":"41_CR14","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TPAMI.2008.111","volume":"31","author":"J Sivic","year":"2009","unstructured":"Sivic, J., Zisserman, A.: Efficient visual search of videos cast as text retrieval. PAMI 31(4), 591\u2013606 (2009)","journal-title":"PAMI"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Specia, L., Frank, S., Sima\u2019an, K., Elliott, D.: A shared task on multimodal machine translation and crosslingual image description. In: Proceedings of the First Conference on Machine Translation, pp. 543\u2013553. ACL (2016)","DOI":"10.18653\/v1\/W16-2346"},{"key":"41_CR16","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, vol. 27, pp. 3104\u20133112 (2014)"},{"key":"41_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: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"41_CR18","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:1502.03044 (2015)"},{"key":"41_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). doi: 10.1007\/978-3-319-10602-1_26"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Image Analysis"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-58838-4_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T09:50:20Z","timestamp":1569318620000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-58838-4_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319588377","9783319588384"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-58838-4_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}