{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:19:17Z","timestamp":1742919557901,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110178"},{"type":"electronic","value":"9783030110185"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11018-5_9","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"106-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MoQA \u2013 A Multi-modal Question Answering Architecture"],"prefix":"10.1007","author":[{"given":"Monica","family":"Haurilet","sequence":"first","affiliation":[]},{"given":"Ziad","family":"Al-Halah","sequence":"additional","affiliation":[]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: 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":"9_CR2","doi-asserted-by":"crossref","unstructured":"Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2017)","DOI":"10.18653\/v1\/D17-1070"},{"key":"9_CR3","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":"9_CR4","doi-asserted-by":"crossref","unstructured":"Jauhar, S.K., Turney, P., Hovy, E.: Tables as semi-structured knowledge for question answering. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 474\u2013483 (2016)","DOI":"10.18653\/v1\/P16-1045"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"9_CR6","unstructured":"Kahou, S.E., Atkinson, A., Michalski, V., K\u00e1d\u00e1r, \u00c1., Trischler, A., Bengio, Y.: Figureqa: an annotated figure dataset for visual reasoning. arXiv preprint arXiv:1710.07300 (2017)"},{"key":"9_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? textbook question answering for multimodal machine comprehension. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"9_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (2014)"},{"key":"9_CR10","unstructured":"Kiros, R., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, pp. 3294\u20133302 (2015)"},{"issue":"1","key":"9_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"9_CR12","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":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Su, H., Zhu, J., Wang, S., Zhang, B.: Textbook question answering under instructor guidance with memory networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3655\u20133663 (2018)","DOI":"10.1109\/CVPR.2018.00385"},{"key":"9_CR14","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":"9_CR15","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1\u20139. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"9_CR16","unstructured":"Reddy, R., Ramesh, R., Deshpande, A., Khapra, M.M.: A question-answering framework for plots using deep learning. arXiv preprint arXiv:1806.04655 (2018)"},{"key":"9_CR17","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: Advances in Neural Information Processing Systems, pp. 2953\u20132961 (2015)"},{"key":"9_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VII. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"9_CR19","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":"9_CR20","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"9_CR21","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11018-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:17:22Z","timestamp":1674350242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}