{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:45:07Z","timestamp":1783421107639,"version":"3.54.6"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,9,11]],"date-time":"2018-09-11T00:00:00Z","timestamp":1536624000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s11263-018-1116-0","type":"journal-article","created":{"date-parts":[[2018,9,11]],"date-time":"2018-09-11T09:41:43Z","timestamp":1536658903000},"page":"398-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":119,"title":["Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering"],"prefix":"10.1007","volume":"127","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2496-7422","authenticated-orcid":false,"given":"Yash","family":"Goyal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tejas","family":"Khot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aishwarya","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Douglas","family":"Summers-Stay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,9,11]]},"reference":[{"key":"1116_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., & Parikh, D. (2016). Analyzing the behavior of visual question answering models. In EMNLP.","DOI":"10.18653\/v1\/D16-1203"},{"key":"1116_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., & Kembhavi, A. (2018). Don\u2019t just assume; look and answer: Overcoming priors for visual question answering. In CVPR.","DOI":"10.1109\/CVPR.2018.00522"},{"key":"1116_CR3","unstructured":"Agrawal, A., Kembhavi, A., Batra, D., & Parikh, D. (2017). C-vqa: A compositional split of the visual question answering (vqa) v1. 0 dataset. arXiv preprint \n                    arXiv:1704.08243\n                    \n                  ."},{"key":"1116_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., et al. (2018). Bottom-up and top-down attention for image captioning and visual question answering. In CVPR.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1116_CR5","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., & Klein, D. (2016). Neural module networks. In CVPR.","DOI":"10.1109\/CVPR.2016.12"},{"key":"1116_CR6","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., et al. (2015). VQA: Visual question answering. In ICCV.","DOI":"10.1109\/ICCV.2015.279"},{"key":"1116_CR7","doi-asserted-by":"crossref","unstructured":"Berg, T., & Belhumeur, P. N. (2013). How do you tell a blackbird from a crow? In ICCV.","DOI":"10.1109\/ICCV.2013.9"},{"key":"1116_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., & Zitnick, C. L. (2015). Mind\u2019s eye: A recurrent visual representation for image caption generation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"1116_CR9","unstructured":"Devlin, J., Gupta, S., Girshick, R. B., Mitchell, M., & Zitnick, C. L. (2015). Exploring nearest neighbor approaches for image captioning. arXiv preprint \n                    arXiv:1505.04467\n                    \n                  ."},{"issue":"4","key":"1116_CR10","doi-asserted-by":"publisher","first-page":"101:1","DOI":"10.1145\/2185520.2185597","volume":"31","author":"C Doersch","year":"2012","unstructured":"Doersch, C., Singh, S., Gupta, A., Sivic, J., & Efros, A. A. (2012). What makes Paris look like Paris? ACM Transactions on Graphics (SIGGRAPH), 31(4), 101:1\u2013101:9.","journal-title":"ACM Transactions on Graphics (SIGGRAPH)"},{"key":"1116_CR11","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., et al. (2015). Long-term recurrent convolutional networks for visual recognition and description. In CVPR.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1116_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F. N., Srivastava, R., Deng, L., Doll\u00e1r, P., et al. (2015). From captions to visual concepts and back. In CVPR.","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"1116_CR13","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D. H., Yang, D., Rohrbach, A., Darrell, T., & Rohrbach, M. (2016). Multimodal compact bilinear pooling for visual question answering and visual grounding. In EMNLP.","DOI":"10.18653\/v1\/D16-1044"},{"key":"1116_CR14","unstructured":"Gao, H., Mao, J., Zhou, J., Huang, Z., & Yuille, A. (2015). Are you talking to a machine? dataset and methods for multilingual image question answering. In NIPS."},{"key":"1116_CR15","unstructured":"Goyal, Y., Mohapatra, A., Parikh, D., & Batra, D. (2016). Towards transparent AI systems: Interpreting visual question answering models. In ICML workshop on visualization for deep learning."},{"key":"1116_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1116_CR17","doi-asserted-by":"crossref","unstructured":"Hendricks, L. A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., & Darrell, T. (2016). Generating visual explanations. In ECCV.","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"1116_CR18","doi-asserted-by":"crossref","unstructured":"Hodosh, M., & Hockenmaier, J. (2016). Focused evaluation for image description with binary forced-choice tasks. In Workshop on vision and language, annual meeting of the association for computational linguistics.","DOI":"10.18653\/v1\/W16-3203"},{"key":"1116_CR19","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., & Saenko, K. (2017). Learning to reason: End-to-end module networks for visual question answering. In ICCV.","DOI":"10.1109\/ICCV.2017.93"},{"key":"1116_CR20","unstructured":"Ilievski, I., Yan, S., & Feng, J. (2016). A focused dynamic attention model for visual question answering. arXiv preprint \n                    arXiv:1604.01485\n                    \n                  ."},{"key":"1116_CR21","doi-asserted-by":"crossref","unstructured":"Jabri, A., Joulin, A., & van\u00a0der Maaten, L. (2016). Revisiting visual question answering baselines. In ECCV.","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"1116_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van\u00a0der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2017). Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR.","DOI":"10.1109\/CVPR.2017.215"},{"key":"1116_CR23","doi-asserted-by":"crossref","unstructured":"Kafle, K., & Kanan, C. (2016a). Answer-type prediction for visual question answering. In CVPR.","DOI":"10.1109\/CVPR.2016.538"},{"key":"1116_CR24","doi-asserted-by":"crossref","unstructured":"Kafle, K., & Kanan, C. (2016b). Visual question answering: Datasets, algorithms, and future challenges. arXiv preprint \n                    arXiv:1610.01465\n                    \n                  .","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"1116_CR25","doi-asserted-by":"crossref","unstructured":"Kafle, K., & Kanan, C. (2017). An analysis of visual question answering algorithms. In ICCV.","DOI":"10.1109\/ICCV.2017.217"},{"key":"1116_CR26","doi-asserted-by":"crossref","unstructured":"Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1116_CR27","unstructured":"Kim, J. H., Lee, S. W., Kwak, D. H., Heo, M. O., Kim, J., Ha, J. W., et al. (2016). Multimodal residual learning for visual QA. In NIPS."},{"key":"1116_CR28","unstructured":"Kim, J. H., On, K. W., Lim, W., Kim, J., Ha, J. W., & Zhang, B. T. (2017). Hadamard product for low-rank bilinear pooling. In ICLR."},{"key":"1116_CR29","unstructured":"Kiros, R., Salakhutdinov, R., & Zemel, R. S. (2015). Unifying visual-semantic embeddings with multimodal neural language models. In TACL."},{"key":"1116_CR30","unstructured":"Koh, P. W., & Liang, P. (2017). Understanding black-box predictions via influence functions. In ICML."},{"key":"1116_CR31","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., et\u00a0al. (2016). Visual genome: Connecting language and vision using crowdsourced dense image annotations. arXiv preprint \n                    arXiv:1602.07332\n                    \n                  ."},{"key":"1116_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft COCO: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1116_CR33","unstructured":"Lu, J., Lin, X., Batra, D., & Parikh, D. (2015). Deeper LSTM and normalized CNN visual question answering model. \n                    https:\/\/github.com\/VT-vision-lab\/VQA_LSTM_CNN\n                    \n                  . Accessed 1 Sep 2017."},{"key":"1116_CR34","unstructured":"Lu, J., Yang, J., Batra, D., & Parikh, D. (2016). Hierarchical question-image co-attention for visual question answering. In NIPS."},{"key":"1116_CR35","unstructured":"Malinowski, M., & Fritz, M. (2014). A multi-world approach to question answering about real-world scenes based on uncertain input. In NIPS."},{"key":"1116_CR36","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., & Fritz, M. (2015). Ask your neurons: A neural-based approach to answering questions about images. In ICCV.","DOI":"10.1109\/ICCV.2015.9"},{"key":"1116_CR37","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., & Yuille, A. L. (2014). Explain images with multimodal recurrent neural networks. In NIPS."},{"key":"1116_CR38","unstructured":"Noh, H., & Han, B. (2016). Training recurrent answering units with joint loss minimization for vqa. arXiv preprint \n                    arXiv:1606.03647\n                    \n                  ."},{"key":"1116_CR39","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. In EMNLP.","DOI":"10.3115\/v1\/D14-1162"},{"key":"1116_CR40","doi-asserted-by":"crossref","unstructured":"Ray, A., Christie, G., Bansal, M., Batra, D., & Parikh, D. (2016). Question relevance in VQA: Identifying non-visual and false-premise questions. In EMNLP.","DOI":"10.18653\/v1\/D16-1090"},{"key":"1116_CR41","unstructured":"Ren, M., Kiros, R., & Zemel, R. (2015). Exploring models and data for image question answering. In NIPS."},{"key":"1116_CR42","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). \u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier. In Knowledge discovery and data mining (KDD).","DOI":"10.1145\/2939672.2939778"},{"key":"1116_CR43","unstructured":"Saito, K., Shin, A., Ushiku, Y., & Harada, T. (2016). Dualnet: Domain-invariant network for visual question answering. arXiv preprint \n                    arXiv:1606.06108\n                    \n                  ."},{"key":"1116_CR44","unstructured":"Selvaraju, R. R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., & Batra, D. (2016). Grad-CAM: Why did you say that? Visual explanations from deep networks via gradient-based localization. arXiv preprint \n                    arXiv:1610.02391\n                    \n                  ."},{"key":"1116_CR45","doi-asserted-by":"crossref","unstructured":"Shih, K. J., Singh, S., & Hoiem, D. (2016). Where to look: Focus regions for visual question answering. In CVPR.","DOI":"10.1109\/CVPR.2016.499"},{"key":"1116_CR46","unstructured":"Shin, A., Ushiku, Y., & Harada, T. (2016). The color of the cat is gray: 1 Million full-sentences visual question answering (FSVQA). arXiv preprint \n                    arXiv:1609.06657\n                    \n                  ."},{"key":"1116_CR47","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In ICLR."},{"key":"1116_CR48","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., & Fidler, S. (2016). MovieQA: Understanding stories in movies through question-answering. In CVPR.","DOI":"10.1109\/CVPR.2016.501"},{"key":"1116_CR49","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., & van\u00a0den Hengel, A. (2018). Tips and tricks for visual question answering: Learnings from the 2017 challenge. In CVPR.","DOI":"10.1109\/CVPR.2018.00444"},{"key":"1116_CR50","doi-asserted-by":"crossref","unstructured":"Torralba, A., & Efros, A. (2011). Unbiased look at dataset bias. In CVPR.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"1116_CR51","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015). Show and tell: A neural image caption generator. In CVPR.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1116_CR52","unstructured":"Wang, P., Wu, Q., Shen, C., van\u00a0den Hengel, A., & Dick, A. R. (2015). Explicit knowledge-based reasoning for visual question answering. arXiv preprint \n                    arXiv:1511.02570\n                    \n                  ."},{"key":"1116_CR53","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., van\u00a0den Hengel, A., & Dick, A. R. (2016). Ask me anything: Free-form visual question answering based on knowledge from external sources. In CVPR.","DOI":"10.1109\/CVPR.2016.500"},{"key":"1116_CR54","unstructured":"Xiong, C., Merity, S., & Socher, R. (2016). Dynamic memory networks for visual and textual question answering. In ICML."},{"key":"1116_CR55","doi-asserted-by":"crossref","unstructured":"Xu, H., & Saenko, K. (2016). Ask, attend and answer: Exploring question-guided spatial attention for visual question answering. In ECCV.","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"1116_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., & Smola, A. (2016). Stacked attention networks for image question answering. In CVPR.","DOI":"10.1109\/CVPR.2016.10"},{"key":"1116_CR57","doi-asserted-by":"crossref","unstructured":"Yu, L., Park, E., Berg, A. C., & Berg, T. L. (2015). Visual madlibs: Fill-in-the-blank description generation and question answering. In ICCV.","DOI":"10.1109\/ICCV.2015.283"},{"key":"1116_CR58","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., & Tao, D. (2017). Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In ICCV.","DOI":"10.1109\/ICCV.2017.202"},{"key":"1116_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., & Parikh, D. (2016). Yin and Yang: Balancing and answering binary visual questions. In CVPR.","DOI":"10.1109\/CVPR.2016.542"},{"key":"1116_CR60","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2015). Learning deep features for discriminative localization. In CVPR."},{"key":"1116_CR61","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., & Fergus, R. (2015). Simple baseline for visual question answering. arXiv preprint \n                    arXiv:1512.02167\n                    \n                  ."},{"key":"1116_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., & Fei-Fei, L. (2016). Visual7w: Grounded question answering in images. In CVPR.","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1116-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-018-1116-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1116-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T19:11:22Z","timestamp":1568142682000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-018-1116-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,11]]},"references-count":62,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["1116"],"URL":"https:\/\/doi.org\/10.1007\/s11263-018-1116-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,11]]},"assertion":[{"value":"14 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}