{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:42:27Z","timestamp":1742949747013,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755875"},{"type":"electronic","value":"9789819755882"}],"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\/978-981-97-5588-2_9","type":"book-chapter","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T18:02:48Z","timestamp":1723485768000},"page":"96-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Branch Collaborative Learning for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Weidong","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzheng","family":"Xu","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":[[2024,8,13]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L.: Vqa: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, A., Darrell, T., Saenko, K.: Language conditioned graph networks for relational reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10294\u201310303 (2019)","DOI":"10.1109\/ICCV.2019.01039"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Jing, C., Jia, Y., Wu, Y., Li, C., Wu, Q.: Learning the dynamics of visual relational reasoning via reinforced path routing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1122\u20131130,2022","DOI":"10.1609\/aaai.v36i1.19997"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Jing, C., Jia, Y., Wu, Y., Liu, X., Wu, Q.: Maintaining reasoning consistency in compositional visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5099\u20135108 (2022)","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"9_CR5","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":"9_CR6","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: 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":"9_CR7","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular coattention 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":"9_CR8","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4613\u20134621 (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"9_CR10","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":"9_CR11","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":"9_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. arXiv preprint arXiv:1610.04325 (2016)"},{"issue":"1","key":"9_CR13","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61\u201380 (2008)","journal-title":"IEEE Trans. Neural Netw."},{"key":"9_CR14","unstructured":"Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)"},{"key":"9_CR15","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"9_CR16","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van Den Hengel, A.: Graph-structured representations for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"9_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"9_CR19","unstructured":"Song, G., Chai, W.: Collaborative learning for deep neural networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: 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":"9_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., Chen, X.: In defense of grid features for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10267\u201310276 (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"issue":"1","key":"9_CR22","first-page":"411","volume":"7","author":"M Honnibal","year":"2017","unstructured":"Honnibal, M., Montani, I.: Spacy 2: natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To Appear 7(1), 411\u2013420 (2017)","journal-title":"To Appear"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshedmemory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Zeng, P., Zhang, H., Song, J., Gao, L.: S2 transformer for image captioning. In: Proceedings of the International Joint Conferences on Artificial Intelligence, vol. 5 (2022)","DOI":"10.24963\/ijcai.2022\/224"},{"key":"9_CR25","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":"9_CR26","doi-asserted-by":"crossref","unstructured":"Kervadec, C., Antipov, G., Baccouche, M., Wolf, C.: Roses are red, violets are blue... but should vqa expect them to? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2776\u20132785 (2021)","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Chen, W., Gan, Z., Li, L., Cheng, Y., Wang, W., Liu, J.: Meta module network for compositional visual reasoning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 655\u2013664 (2021)","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"9_CR28","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)"},{"key":"9_CR29","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"9_CR30","unstructured":"Guo, D., Xu, C., Tao, D.: Bilinear graph networks for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. (2021)"},{"key":"9_CR31","unstructured":"Cao, J., Qin, X., Zhao, S., Shen, J.: Bilateral crossmodality graph matching attention for feature fusion in visual question answering. IEEE Trans. Neural Netw. Learn. Syst. (2022)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5588-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T18:04:18Z","timestamp":1723485858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5588-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755875","9789819755882"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5588-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"13 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}