{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:24Z","timestamp":1783439844802,"version":"3.54.6"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464831","type":"print"},{"value":"9783319464848","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\/978-3-319-46484-8_44","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T08:35:32Z","timestamp":1474014932000},"page":"727-739","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":94,"title":["Revisiting Visual Question Answering Baselines"],"prefix":"10.1007","author":[{"given":"Allan","family":"Jabri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armand","family":"Joulin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurens","family":"van der Maaten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"44_CR1","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"44_CR2","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalanditis, Y., Li, L.J., Shamma, D., Bernstein, M., Fei-Fei, L.: Visual genome: connecting language and vision using crowdsourced dense image annotations. arXiv:1602.07332 (2016)","DOI":"10.1007\/s11263-016-0981-7"},{"issue":"12","key":"44_CR4","doi-asserted-by":"crossref","first-page":"3618","DOI":"10.1073\/pnas.1422953112","volume":"112","author":"D Geman","year":"2015","unstructured":"Geman, D., Geman, S., Hallonquist, N., Younes, L.: Visual turing test for computer vision systems. Proc. Natl. Acad. Sci. 112(12), 3618\u20133623 (2015)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C., Parikh, D.: VQA: visual question answering. In: Proceedings of the International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"44_CR6","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: Advances in Neural Information Processing Systems (2015)"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Yu, L., Park, E., Berg, A., Berg, T.: Visual madlibs: fill in the blank image generation and question answering. arXiv:1506.00278 (2015)","DOI":"10.1109\/ICCV.2015.283"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7W: grounded question answering in images. arXiv:1511.03416 (2015)","DOI":"10.1109\/CVPR.2016.540"},{"key":"44_CR9","unstructured":"Zhou, B., Tian, Y., Sukhbataar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv:1512.02167 (2015)"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Das, A., Agrawal, H., Zitnick, C.L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? arXiv:1606.03556 (2016)","DOI":"10.18653\/v1\/D16-1092"},{"key":"44_CR11","unstructured":"Koehn, P.: Statistical significance tests for machine translation evaluation. In: EMNLP, pp. 388\u2013395 (2004)"},{"key":"44_CR12","unstructured":"Callison-Burch, C., Osborne, M., Koehn, P.: Re-evaluation the role of BLEU in machine translation research. In: EACL, vol. 6, pp. 249\u2013256 (2006)"},{"key":"44_CR13","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":"44_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., Zitnick, C.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"44_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 Internation Conference on Computer Vision(2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"44_CR16","unstructured":"Wu, Q., Shen, C., van den Hengel, A., Wang, P., Dick, A.: Image captioning and visual question answering based on attributes and their related external knowledge. arXiv:1603.02814 (2016)"},{"key":"44_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","volume-title":"The Semantic Web","author":"S Auer","year":"2007","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., Choi, K.-S., Noy, N., Allemang, D., Lee, K.-I., Nixon, L., Golbeck, J., Mika, P., Maynard, D., Mizoguchi, R., Schreiber, G., Cudr\u00e9-Mauroux, P. (eds.) ASWC\/ISWC -2007. LNCS, vol. 4825, pp. 722\u2013735. Springer, Heidelberg (2007). doi: 10.1007\/978-3-540-76298-0_52"},{"key":"44_CR18","unstructured":"Gao, H., Mao, J., Zhou, J., Huang, Z., Wang, L., Xu, W.: Are you talking to a machine? Dataset and methods for multilingual image question answering. In: Advances in Neural Information Processing Systems (2015)"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Li, H.: Learning to answer questions from image using convolutional neural network. arXiv:1506.00333 (2015)","DOI":"10.1609\/aaai.v30i1.10442"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Deep compositional question answering with neural module networks. arXiv:1511.02799 (2015)","DOI":"10.1109\/CVPR.2016.12"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Fukui, A., Huk Park, D., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: Focus regions for visual question answering. arXiv:1511.07394 (2016)","DOI":"10.1109\/CVPR.2016.499"},{"issue":"1","key":"44_CR24","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"44_CR25","unstructured":"Gross, S., Wilber, M.: Training and investigating residual nets (2016)"},{"key":"44_CR26","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv:1301.3781 (2013)"},{"key":"44_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"issue":"8","key":"44_CR28","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":"44_CR29","doi-asserted-by":"crossref","unstructured":"Joulin, A., van der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. arXiv:1511.0225 (2015)","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. arXiv:1403.6382 (2014)","DOI":"10.1109\/CVPRW.2014.131"}],"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\/978-3-319-46484-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T16:36:32Z","timestamp":1657298192000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46484-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464831","9783319464848"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46484-8_44","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":"17 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"}]}}