{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:48:30Z","timestamp":1726030110029},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208868"},{"type":"electronic","value":"9783030208875"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20887-5_5","type":"book-chapter","created":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T08:03:59Z","timestamp":1558944239000},"page":"72-87","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Answer Distillation for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Zhiwei","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,28]]},"reference":[{"key":"5_CR1","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering (2017). http:\/\/arxiv.org\/abs\/1707.07998"},{"key":"5_CR2","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Deep compositional question answering with neural module networks. CoRR abs\/1511.02799 (2015). http:\/\/arxiv.org\/abs\/1511.02799"},{"key":"5_CR3","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":"5_CR4","doi-asserted-by":"publisher","unstructured":"Ben-younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering, pp. 2612\u20132620 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.285 , http:\/\/arxiv.org\/abs\/1705.06676","DOI":"10.1109\/ICCV.2017.285"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"5_CR6","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. arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"5_CR7","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":"5_CR8","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"issue":"8","key":"5_CR9","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":"5_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-319-46484-8_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Jabri","year":"2016","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting visual question answering baselines. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 727\u2013739. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_44"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Jordan, M.I.: Serial order: a parallel distributed processing approach. In: Advances in Psychology, vol. 121, pp. 471\u2013495. Elsevier (1997)","DOI":"10.1016\/S0166-4115(97)80111-2"},{"key":"5_CR12","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. In: The 5th International Conference on Learning Representations (2017)"},{"key":"5_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"5_CR14","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. CoRR abs\/1602.07332 (2016). http:\/\/arxiv.org\/abs\/1602.07332"},{"key":"5_CR15","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":"5_CR16","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs\/1405.0312 (2014). http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"5_CR17","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":"5_CR18","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). http:\/\/arxiv.org\/abs\/1410.0210"},{"key":"5_CR19","unstructured":"Nam, H., Ha, J., Kim, J.: Dual attention networks for multimodal reasoning and matching. CoRR abs\/1611.00471 (2016). http:\/\/arxiv.org\/abs\/1611.00471"},{"key":"5_CR20","unstructured":"Noh, H., Han, B.: Training recurrent answering units with joint loss minimization for VQA. CoRR abs\/1606.03647 (2016). http:\/\/arxiv.org\/abs\/1606.03647"},{"key":"5_CR21","unstructured":"Ren, M., Kiros, R., Zemel, R.S.: Image question answering: a visual semantic embedding model and a new dataset. CoRR abs\/1505.02074 (2015). http:\/\/arxiv.org\/abs\/1505.02074"},{"key":"5_CR22","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR abs\/1506.01497 (2015). http:\/\/arxiv.org\/abs\/1506.01497"},{"key":"5_CR23","unstructured":"Schwartz, I., Schwing, A.G., Hazan, T.: High-order attention models for visual question answering (Nips) (2017). http:\/\/arxiv.org\/abs\/1711.04323"},{"key":"5_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5_CR26","unstructured":"Teney, D., Anderson, P., He, X., van den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge (2017). http:\/\/arxiv.org\/abs\/1708.02711"},{"key":"5_CR27","unstructured":"Wu, Q., Shen, C., van den Hengel, A., Wang, P., Dick, A.R.: Image captioning and visual question answering based on attributes and their related external knowledge. CoRR abs\/1603.02814 (2016). http:\/\/arxiv.org\/abs\/1603.02814"},{"key":"5_CR28","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. CoRR abs\/1511.02274 (2015). http:\/\/arxiv.org\/abs\/1511.02274"},{"key":"5_CR29","doi-asserted-by":"publisher","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.202 , http:\/\/arxiv.org\/abs\/1708.01471","DOI":"10.1109\/ICCV.2017.202"},{"key":"5_CR30","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. CoRR abs\/1512.02167 (2015). http:\/\/arxiv.org\/abs\/1512.02167"},{"key":"5_CR31","unstructured":"Zhu, Y., Groth, O., Bernstein, M.S., Fei-Fei, L.: Visual7W: grounded question answering in images. CoRR abs\/1511.03416 (2015). http:\/\/arxiv.org\/abs\/1511.03416"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20887-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T14:02:52Z","timestamp":1663509772000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20887-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208868","9783030208875"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20887-5_5","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":"28 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","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":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}