{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:05:24Z","timestamp":1743113124578,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819722747"},{"type":"electronic","value":"9789819722754"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-2275-4_6","type":"book-chapter","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T19:02:10Z","timestamp":1713207730000},"page":"74-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Bilinear-MAC Network for Visual Reasoning"],"prefix":"10.1007","author":[{"given":"Jiaxing","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangli","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"6_CR2","unstructured":"Lu, J., Batra, D., Parikh, D., et al.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"6_CR3","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"6_CR5","unstructured":"Lu, J., Yang, J., Batra, D., et al.: Hierarchical question-image co-attention for visual question answering. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., et al.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"6_CR7","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: International Conference on Learning Representations (2018)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., et al.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"6_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Miao, Y., Cheng, W., He, S., et al.: Research on visual question answering based on GAT relational reasoning. Neural Process. Lett. 1\u201314 (2022)","DOI":"10.1007\/s11063-021-10689-2"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., et al.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Rahman, T., Chou, S.H., Sigal, L., et al.: An improved attention for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131662 (2021)","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.inffus.2021.02.006","volume":"72","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Yu, J., Zhao, W., et al.: DMRFNet: deep multimodal reasoning and fusion for visual question answering and explanation generation. Inf. Fusion 72, 70\u201379 (2021)","journal-title":"Inf. Fusion"},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1109\/TMM.2022.3173131","volume":"25","author":"B Qin","year":"2023","unstructured":"Qin, B., Hu, H., Zhuang, Y.: Deep residual weight-sharing attention network with low-rank attention for visual question answering. IEEE Trans. Multimed. 25, 4282\u20134295 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"6_CR16","unstructured":"Li, J., Li, D., Savarese, S., et al.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"}],"container-title":["Communications in Computer and Information Science","Bio-Inspired Computing: Theories and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2275-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T19:13:51Z","timestamp":1713208431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2275-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722747","9789819722754"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2275-4_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIC-TA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Bio-Inspired Computing: Theories and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bicta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2023.bicta.org\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"168","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":"64","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":"0","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":"38% - 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":"4","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)"}}]}}