{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:16:28Z","timestamp":1742912188911,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030821524"},{"type":"electronic","value":"9783030821531"}],"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\/978-3-030-82153-1_8","type":"book-chapter","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T23:26:36Z","timestamp":1628292396000},"page":"85-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Unbalanced Interaction Network for Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5761-7832","authenticated-orcid":false,"given":"Xinxin","family":"Liao","sequence":"first","affiliation":[]},{"given":"Mingyan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Heyan","family":"Chai","sequence":"additional","affiliation":[]},{"given":"Shuhan","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5301","authenticated-orcid":false,"given":"Qing","family":"Liao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,7]]},"reference":[{"issue":"4","key":"8_CR1","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MNET.2018.1700407","volume":"32","author":"K Gai","year":"2018","unstructured":"Gai, K., Qiu, M.: Reinforcement learning-based content-centric services in mobile sensing. IEEE Netw. 32(4), 34\u201339 (2018)","journal-title":"IEEE Netw."},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Tao, L., Golikov, S., Gai, K., Qiu, M.: A reusable software component for integrated syntax and semantic validation for services computing. In: 2015 IEEE Symposium on Service-Oriented System Engineering, pp. 127\u2013132. IEEE (2015)","DOI":"10.1109\/SOSE.2015.10"},{"issue":"3","key":"8_CR3","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/MCOM.2018.1700274","volume":"56","author":"M Chen","year":"2018","unstructured":"Chen, M., Zhang, Y., Qiu, M., Guizani, N., Hao, Y.: SPHA: smart personal health advisor based on deep analytics. IEEE Commun. Mag. 56(3), 164\u2013169 (2018)","journal-title":"IEEE Commun. Mag."},{"key":"8_CR4","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. arXiv preprint arXiv:1606.00061 (2016)"},{"issue":"12","key":"8_CR5","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 5947\u20135959 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"8_CR6","unstructured":"Yu, Z., Cui, Y., Yu, J., Tao, D., Tian, Q.: Multimodal unified attention networks for vision-and-language interactions. arXiv preprint arXiv:1908.04107 (2019)"},{"issue":"17","key":"8_CR7","doi-asserted-by":"publisher","first-page":"4897","DOI":"10.3390\/s20174897","volume":"20","author":"S He","year":"2020","unstructured":"He, S., Han, D.: An effective dense co-attention networks for visual question answering. Sensors 20(17), 4897 (2020)","journal-title":"Sensors"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Wang, X., Cao, W.: Non-iterative approaches in training feed-forward neural networks and their applications (2018)","DOI":"10.1007\/s00500-018-3203-0"},{"issue":"11","key":"8_CR9","doi-asserted-by":"publisher","first-page":"3487","DOI":"10.1007\/s00500-018-3021-4","volume":"22","author":"W Cao","year":"2018","unstructured":"Cao, W., Gao, J., Ming, Z., Cai, S., Shan, Z.: Fuzziness-based online sequential extreme learning machine for classification problems. Soft. Comput. 22(11), 3487\u20133494 (2018)","journal-title":"Soft. Comput."},{"key":"8_CR10","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 preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"8_CR11","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: 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":"8_CR13","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Cao, W., Hu, L., Gao, J., Wang, X., Ming, Z.: A study on the relationship between the rank of input data and the performance of random weight neural network. Neural Comput. Appl. 32(16), 12685\u201312696 (2020)","DOI":"10.1007\/s00521-020-04719-8"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6639\u20136648 (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"8_CR16","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"},{"key":"8_CR17","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":"8_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"8_CR19","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"8_CR20","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Anderson, P., 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":"8_CR22","unstructured":"Gao, P., You, H., Zhang, Z., Wang, X., Li, H.: Multi-modality latent interaction network for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5825\u20135835 (2019)"},{"key":"8_CR23","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.neucom.2020.03.098","volume":"402","author":"J Hong","year":"2020","unstructured":"Hong, J., Park, S., Byun, H.: Selective residual learning for visual question answering. Neurocomputing 402, 366\u2013374 (2020)","journal-title":"Neurocomputing"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Guo, W., Zhang, Y., Wu, X., Yang, J., Cai, X., Yuan, X.: Re-attention for visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 91\u201398 (2020)","DOI":"10.1609\/aaai.v34i01.5338"},{"issue":"23","key":"8_CR25","doi-asserted-by":"publisher","first-page":"6758","DOI":"10.3390\/s20236758","volume":"20","author":"Z Guo","year":"2020","unstructured":"Guo, Z., Han, D.: Multi-modal explicit sparse attention networks for visual question answering. Sensors 20(23), 6758 (2020)","journal-title":"Sensors"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82153-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T23:45:11Z","timestamp":1628293511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82153-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030821524","9783030821531"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82153-1_8","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 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2021","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":"ksem2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cloud-conf.net\/ksem21\/index.html","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":"492","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":"164","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":"33% - 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":"10","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)"}}]}}