{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:49:57Z","timestamp":1742964597661,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811557873"},{"type":"electronic","value":"9789811557880"}],"license":[{"start":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T00:00:00Z","timestamp":1599609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T00:00:00Z","timestamp":1599609600000},"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":[[2021]]},"DOI":"10.1007\/978-981-15-5788-0_10","type":"book-chapter","created":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T08:02:45Z","timestamp":1599552165000},"page":"103-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimal Image Feature Ranking and Fusion for Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6465-6883","authenticated-orcid":false,"given":"Sruthy","family":"Manmadhan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1566-4454","authenticated-orcid":false,"given":"Binsu C.","family":"Kovoor","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,9]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Lawrence Zitnick, C., Parikh, D.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and Yang: balancing and answering binary visual questions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5014\u20135022 (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7w: grounded question answering in images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Yu, L., Park, E., Berg, A.C., Berg, T.L.: Visual madlibs: fill in the blank description generation and question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2461\u20132469 (2015)","DOI":"10.1109\/ICCV.2015.283"},{"key":"10_CR5","unstructured":"Fader, A., Zettlemoyer, L., Etzioni, O.: Paraphrase-driven learning for open question answering. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1608\u20131618 (2013)"},{"key":"10_CR6","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: International Conference on Machine Learning, pp. 2397\u20132406 (2016)"},{"key":"10_CR7","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint \narXiv:1409.1556"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A.: Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting visual question answering baselines. In: European Conference on Computer Vision, pp. 727\u2013739. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Ask me anything: Free-form visual question answering based on knowledge from external sources. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4622\u20134630 (2016)","DOI":"10.1109\/CVPR.2016.500"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Noh, H., Hongsuck Seo, P., Han, B.: Image question answering using convolutional neural network with dynamic parameter prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 30\u201338 (2016)","DOI":"10.1109\/CVPR.2016.11"},{"key":"10_CR15","unstructured":"Kim, J.H., Lee, S.W., Kwak, D., Heo, M.O., Kim, J., Ha, J.W., Zhang, B.T.: Multimodal residual learning for visual QA. In: Advances in Neural Information Processing Systems, pp. 361\u2013369 (2016)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Bai, Y., Fu, J., Zhao, T., Mei, T.: Deep attention neural tensor network for visual question answering. In: Computer Vision\u2013ECCV 2018: 15th European Conference, Munich, Germany, September 8\u201314, 2018, Proceedings, vol. 11216, p. 20. Springer, Berlin (2018)","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Peng, L., Yang, Y., Bin, Y., Xie, N., Shen, F., Ji, Y., Xu, X.: Word-to-region attention network for visual question answering. Multimedia Tools Appl. 1\u201316 (2018)","DOI":"10.1007\/s11042-018-6389-3"},{"key":"10_CR18","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Doersch, C., Santoro, A., Battaglia, P.:. Learning visual question answering by bootstrapping hard attention. In: Computer Vision\u2014ECCV 2018 Lecture Notes in Computer Science, pp. 3\u201320 (2018)","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818\u2013833. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Tommasi, T., Mallya, A., Plummer, B., Lazebnik, S., Berg, A.C., Berg, T.L.: Combining multiple cues for visual madlibs question answering. Int. J. Comput. Vis. 1\u201323 (2018)","DOI":"10.1007\/s11263-018-1096-0"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Campello, R.J., Moulavi, D., Sander, J.: Density-based clustering based on hierarchical density estimates. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 160\u2013172. Springer, Berlin (2013)","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"10_CR24","unstructured":"Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley (2012)"},{"issue":"9","key":"10_CR25","doi-asserted-by":"publisher","first-page":"1984","DOI":"10.1109\/TIFS.2016.2569061","volume":"11","author":"M Haghighat","year":"2016","unstructured":"Haghighat, M., Abdel-Mottaleb, M., Alhalabi, W.: Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans. Inf. Forensics Secur. 11(9), 1984\u20131996 (2016)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10_CR26","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: Advances in Neural Information Processing Systems, pp. 1682\u20131690 (2014)"},{"key":"10_CR27","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018). arXiv preprint \narXiv:1804.02767"}],"container-title":["Advances in Intelligent Systems and Computing","Evolution in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-5788-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T08:05:01Z","timestamp":1599552301000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-5788-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,9]]},"ISBN":["9789811557873","9789811557880"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-5788-0_10","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2020,9,9]]},"assertion":[{"value":"9 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}