{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:16:31Z","timestamp":1743146191778,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863821"},{"type":"electronic","value":"9783030863838"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86383-8_21","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T08:02:49Z","timestamp":1631260969000},"page":"259-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual-Textual Semantic Alignment Network for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Weidong","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqiu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"21_CR3","unstructured":"Ashish, V., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Cadene, R., Ben-younes, H., Cord, M., Thome, N.: Murel: multimodal relational reasoning for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00209"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra- and inter-modality attention flow for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"21_CR6","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"21_CR7","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"21_CR8","unstructured":"Jeffrey, P., Richard, S., Christopher D.M.: Glove: global vectors for word representation. In: EMNLP (2014)"},{"key":"21_CR9","unstructured":"Kim, J., Jun, J., Zhang, B.: Bilinear attention networks. In: NIPS (2018)"},{"key":"21_CR10","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. arXiv preprint arXiv:1602.07332 (2016)"},{"key":"21_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-030-58536-5_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Li","year":"2020","unstructured":"Li, Q., Huang, S., Hong, Y., Zhu, S.-C.: A competence-aware curriculum for\u00a0visual concepts learning via question answering. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 141\u2013157. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_9"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Li, Q., Tao, Q., Joty, S., Cai, J., Luo, J.: VQA-E: explaining, elaborating, and enhancing your answers for visual questions. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"21_CR13","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"21_CR14","unstructured":"Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: ICLR (2019)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Okatani, T.: Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00637"},{"key":"21_CR16","unstructured":"Norcliffe-Brown, W., Vafeais, E., Parisot, S.: Learning conditioned graph structures for interpretable visual question answering. In: NIPS (2018)"},{"key":"21_CR17","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: NIPS (2018)"},{"key":"21_CR18","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., Hengel, A.V.D.: Tips and tricks for visual question answering. arXiv preprint arXiv:1708.02711 (2017)","DOI":"10.1109\/MSP.2017.2739826"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., Hengel, A.V.D.: What value do explicit high level concepts have in vision to language problems?. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.29"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: CVPR (2020)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86383-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:43:24Z","timestamp":1709822604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86383-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863821","9783030863838"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86383-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"265","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"53% - 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 (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"2.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}