{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T19:05:47Z","timestamp":1746299147610,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012243"},{"type":"electronic","value":"9783030012250"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01225-0_10","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:39:54Z","timestamp":1538987994000},"page":"158-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Question Type Guided Attention in Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Yang","family":"Shi","sequence":"first","affiliation":[]},{"given":"Tommaso","family":"Furlanello","sequence":"additional","affiliation":[]},{"given":"Sheng","family":"Zha","sequence":"additional","affiliation":[]},{"given":"Animashree","family":"Anandkumar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"10_CR3","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. http:\/\/arxiv.org\/abs\/1707.07998"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Charikar, M., Chen, K., Farach-Colton, M.: Finding frequent items in data streams. In: Proceedings of ICALP (2002)","DOI":"10.1007\/3-540-45465-9_59"},{"key":"10_CR6","unstructured":"Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. In: Neural Information Processing Systems, Workshop on Machine Learning Systems (2015)"},{"key":"10_CR7","unstructured":"Donahue, J., et al.: DECAF: a deep convolutional activation feature for generic visual recognition. http:\/\/arxiv.org\/abs\/1310.1531"},{"key":"10_CR8","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. In: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.41"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in Visual Question Answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"10_CR11","unstructured":"Gurari, D., et al.: VizWiz grand challenge: answering visual questions from blind people. https:\/\/arxiv.org\/abs\/1802.08218"},{"key":"10_CR12","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 (CVPR)"},{"issue":"8","key":"10_CR13","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":"10_CR14","unstructured":"Johnson, J., et al.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. http:\/\/arxiv.org\/abs\/1612.06890"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"10_CR16","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. https:\/\/arxiv.org\/abs\/1602.07332"},{"key":"10_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012)"},{"key":"10_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR19","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: NIPS (2016)"},{"key":"10_CR20","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp. 3111\u20133119"},{"key":"10_CR21","unstructured":"Noh, H., Han, B.: Training recurrent answering units with joint loss minimization for VQA. https:\/\/arxiv.org\/abs\/1606.03647"},{"key":"10_CR22","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. http:\/\/arxiv.org\/abs\/1506.01497"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Simon, M., Gao, Y., Darrell, T., Denzler, J., Rodner, E.: Generalized orderless pooling performs implicit salient matching. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.531"},{"key":"10_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Strub, F., de Vries, H., Mary, J., Piot, B., Courville, A.C., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. In: International Joint Conference on Artificial Intelligence (IJCAI) (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"10_CR26","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, pp. 3104\u20133112. MIT Press, Cambridge (2014). http:\/\/dl.acm.org\/citation.cfm?id=2969033.2969173"},{"key":"10_CR27","unstructured":"Teney, D., Anderson, P., He, X., van den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge. http:\/\/arxiv.org\/abs\/1708.02711"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Structured triplet learning with POS-tag guided attention for visual question answering. In: IEEE Winter Conference on Applications of Computer Vision (2018)","DOI":"10.1109\/WACV.2018.00209"},{"key":"10_CR29","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. http:\/\/arxiv.org\/abs\/1609.08144"},{"key":"10_CR30","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. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"10_CR31","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning (2015)"},{"key":"10_CR32","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. https:\/\/arxiv.org\/abs\/1511.02274"},{"key":"10_CR33","unstructured":"Zhang, P.: Towards interpretable vision systems. Ph.D. thesis. Virginia Polytechnic Institute and State University (2017)"},{"key":"10_CR34","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.542"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01225-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:07:14Z","timestamp":1665187634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01225-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012243","9783030012250"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01225-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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"}]}}