{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:33:21Z","timestamp":1743082401389,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916412"},{"type":"electronic","value":"9789819916429"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-1642-9_40","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"467-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level Visual Feature Enhancement Method for\u00a0Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Xingang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honglu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., et al.: Adversarial cross-modal retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yang, G., Veit, A., et al.: Learning to evaluate image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5804\u20135812 (2018)","DOI":"10.1109\/CVPR.2018.00608"},{"issue":"2","key":"40_CR3","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1007\/s11063-021-10689-2","volume":"54","author":"Y Miao","year":"2022","unstructured":"Miao, Y., Cheng, W., He, S., et al.: Research on visual question answering based on gat relational reasoning. Neural Process. Lett. 54(2), 1435\u20131448 (2022)","journal-title":"Neural Process. Lett."},{"issue":"3","key":"40_CR4","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.3390\/s22031045","volume":"22","author":"F Yan","year":"2022","unstructured":"Yan, F., Silamu, W., Li, Y.: Deep modular bilinear attention network for visual question answering. Sensors 22(3), 1045 (2022)","journal-title":"Sensors"},{"key":"40_CR5","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neucom.2021.10.016","volume":"467","author":"H Zhan","year":"2022","unstructured":"Zhan, H., Xiong, P., Wang, X., et al.: Visual question answering by pattern matching and reasoning. Neurocomputing 467, 323\u2013336 (2022)","journal-title":"Neurocomputing"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., et al.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., et al.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"40_CR8","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":"40_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"40_CR12","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"40_CR13","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"40_CR14","unstructured":"Kim, J.H., Lee, S.W., Kwak, D., et al.: Multimodal residual learning for visual QA. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"40_CR15","unstructured":"Kim, J.H., On, K.W., Lim, W., et al.: Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)"},{"key":"40_CR16","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"40_CR17","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":"40_CR18","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":"40_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"40_CR20","unstructured":"Veli\u010dkovi\u0107, P.A., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"40_CR22","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"40_CR23","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"40_CR24","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., et al.: Tips and tricks for visual question answering: learnings from the 2017 challenge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4223\u20134232 (2018)","DOI":"10.1109\/CVPR.2018.00444"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"40_CR27","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":"TY 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":"40_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107956","volume":"117","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Zhang, X., Zhang, Q., et al.: Dual self-attention with co-attention networks for visual question answering. Pattern Recogn. 117, 107956 (2021)","journal-title":"Pattern Recogn."},{"key":"40_CR29","doi-asserted-by":"publisher","first-page":"35662","DOI":"10.1109\/ACCESS.2020.2975093","volume":"8","author":"C Chen","year":"2020","unstructured":"Chen, C., Han, D., Wang, J.: Multimodal encoder-decoder attention networks for visual question answering. IEEE Access 8, 35662\u201335671 (2020)","journal-title":"IEEE Access"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1642-9_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:31:31Z","timestamp":1681389091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_40","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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":"3","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":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}