{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:29Z","timestamp":1750309589812,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,17]]},"DOI":"10.1145\/3723178.3723213","type":"proceedings-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T07:16:47Z","timestamp":1749194207000},"page":"264-270","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Self-Attention and Co-Attention within the Modified Graph Matching Attention Network for Visual Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2919-7804","authenticated-orcid":false,"given":"Md. Fakhrul","family":"Islam","sequence":"first","affiliation":[{"name":"Computer Science & Engineering, Rajshahi University of Engineering and Technology, Rajshahi, Rajshahi, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7014-3205","authenticated-orcid":false,"given":"Md. Faysal","family":"Ahamed","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1989-4385","authenticated-orcid":false,"given":"Md. Rabiul","family":"Islam","sequence":"additional","affiliation":[{"name":"Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"}]}],"member":"320","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Jianjian Cao Xiameng Qin Sanyuan Zhao and Jianbing Shen. 2022. Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering. IEEE Transactions on Neural Networks and Learning Systems (2022) 1\u201312. 10.1109\/TNNLS.2021.3135655","DOI":"10.1109\/TNNLS.2021.3135655"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Shirong He and Dezhi Han. 2020. An Effective Dense Co-Attention Networks for Visual Question Answering. Sensors 20 17 (2020). 10.3390\/s20174897","DOI":"10.3390\/s20174897"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Kushal Kafle and Christopher Kanan. 2017. Visual question answering: Datasets algorithms and future challenges. Computer Vision and Image Understanding 163 (2017) 3\u201320. 10.1016\/j.cviu.2017.06.005 Language in Vision.","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"e_1_3_3_1_6_2","volume-title":"Advances in Neural Information Processing Systems","author":"Kim Jin-Hwa","year":"2018","unstructured":"Jin-Hwa Kim, Jaehyun Jun, and Byoung-Tak Zhang. 2018. Bilinear Attention Networks. In Advances in Neural Information Processing Systems , S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.), Vol.\u00a031. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/96ea64f3a1aa2fd00c72faacf0cb8ac9-Paper.pdf"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Yalin Miao Shuyun He WenFang Cheng Guodong Li and Meng Tong. 2022. Research on visual question answering based on dynamic memory network model of multiple attention mechanisms. Scientific Reports 12 1 (06 Oct 2022) 16758. 10.1038\/s41598-022-21149-9","DOI":"10.1038\/s41598-022-21149-9"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Ahmed Osman and Wojciech Samek. 2019. DRAU: Dual Recurrent Attention Units for Visual Question Answering. Computer Vision and Image Understanding 185 (2019) 24\u201330. 10.1016\/j.cviu.2019.05.001","DOI":"10.1016\/j.cviu.2019.05.001"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Xiang Shen Dezhi Han Zihan Guo Chongqing Chen Jie Hua and Gaofeng Luo. 2023. Local self-attention in transformer for visual question answering. Applied Intelligence 53 13 (01 Jul 2023) 16706\u201316723. 10.1007\/s10489-022-04355-w","DOI":"10.1007\/s10489-022-04355-w"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_26"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207058"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Yirui Wu Yuntao Ma and Shaohua Wan. 2021. Multi-scale relation reasoning for multi-modal Visual Question Answering. Signal Processing: Image Communication 96 (2021) 116319. 10.1016\/j.image.2021.116319","DOI":"10.1016\/j.image.2021.116319"},{"key":"e_1_3_3_1_14_2","unstructured":"Zhuoqian Yang Zengchang Qin Jing Yu and Yue Hu. 2018. Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering. arXiv:arXiv:1812.09681"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Sheng Zhang Min Chen Jincai Chen Fuhao Zou Yuan-Fang Li and Ping Lu. 2021. Multimodal feature-wise co-attention method for visual question answering. Information Fusion 73 (2021) 1\u201310. 10.1016\/j.inffus.2021.02.022","DOI":"10.1016\/j.inffus.2021.02.022"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Weifeng Zhang Jing Yu Wenhong Zhao and Chuan Ran. 2021. DMRFNet: Deep Multimodal Reasoning and Fusion for Visual Question Answering and explanation generation. Information Fusion 72 (2021) 70\u201379. 10.1016\/j.inffus.2021.02.006","DOI":"10.1016\/j.inffus.2021.02.006"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Xi Zhu Zhendong Mao Zhineng Chen Yangyang Li Zhaohui Wang and Bin Wang. 2021. Object-difference drived graph convolutional networks for visual question answering. Multimedia Tools and Applications 80 11 (May 2021) 16247\u201316265.","DOI":"10.1007\/s11042-020-08790-0"}],"event":{"name":"ICCA 2024: 3rd International Conference on Computing Advancements","acronym":"ICCA 2024","location":"Dhaka Bangladesh"},"container-title":["Proceedings of the 3rd International Conference on Computing Advancements"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723178.3723213","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723178.3723213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:47Z","timestamp":1750298207000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723178.3723213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":16,"alternative-id":["10.1145\/3723178.3723213","10.1145\/3723178"],"URL":"https:\/\/doi.org\/10.1145\/3723178.3723213","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"2025-06-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}