{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:01:22Z","timestamp":1750309282438,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T00:00:00Z","timestamp":1695340800000},"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":[[2023,9,22]]},"DOI":"10.1145\/3641584.3641770","type":"proceedings-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T22:44:43Z","timestamp":1718405083000},"page":"1237-1242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Question Answering Model Based on Relationship graphs and Co-Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5832-2027","authenticated-orcid":false,"given":"Wei","family":"Guan","sequence":"first","affiliation":[{"name":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1062-9193","authenticated-orcid":false,"given":"Xueli","family":"Yang","sequence":"additional","affiliation":[{"name":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7473-5761","authenticated-orcid":false,"given":"Li","family":"Ma","sequence":"additional","affiliation":[{"name":"Shaanxi provincial key laboratory of network data analysis and intelligent processing, Xi'an University of Posts and Telecommunications, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Show and rell: Lessons learned from the 2015 mscoco image captioning challenge[J]","author":"Vinyals O","year":"2016","unstructured":"Vinyals O, Toshev A, Bengio S, Show and rell: Lessons learned from the 2015 mscoco image captioning challenge[J].IEEE transactions on patten analysis and machine intelligence, 2016, 39(4): 652-663."},{"key":"e_1_3_2_1_2_1","first-page":"77","article-title":"Reduced frame set on wireless distorted video for quality assessment[J].","volume":"2016","author":"Shao Hua","unstructured":"Shao Hua,Wen Xiangming,Lu Zhaoming, Reduced frame set on wireless distorted video for quality assessment[J].The Journal of China Universities of Posts and Telecommunications,2016,23(04):77-82.","journal-title":"The Journal of China Universities of Posts and Telecommunications"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc.of the Int'l Conf. on Learning Representations.","author":"Mao J","year":"2015","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A. Deep captioning with multimodal recurrent neural networks (m-RNN). In: Proc.of the Int'l Conf. on Learning Representations. 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"Long-term recurrent convolutional networks for visual recognition and description[C]\/\/Proc of the 2015 IEEE Conf on Computer Vision and Pattern Recognition","author":"Donahue J","year":"2015","unstructured":"Donahue J, Hendricks L, Guadarrama S, Long-term recurrent convolutional networks for visual recognition and description[C]\/\/Proc of the 2015 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015:2625-2634."},{"key":"e_1_3_2_1_5_1","unstructured":"Gan Z Chen Y C Li L J et al. Playing lottery tickets with vision and language.[ EB\/OL]. (2021-04 -23)[ 2021 -05-07 ]. http:\/\/arxiv.org\/abs\/2104.1 1832."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yang Z C He X D Gao J F Deng L and Smola A. Stackedattention networks for image question answering\/\/Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas USA: IEEE: 21-29[DOI: 10. 1109\/CVPR.2016. 10]","DOI":"10.1109\/CVPR.2016.10"},{"volume-title":"Batra D and Parikh D. Hierarchical question-image co-attention for visual question answering\/\/Proceedings of the 30th Conference on Neural Information Processing Systems. Barcelona","author":"Lu JS","key":"e_1_3_2_1_7_1","unstructured":"Lu JS, Yang J W, Batra D and Parikh D. Hierarchical question-image co-attention for visual question answering\/\/Proceedings of the 30th Conference on Neural Information Processing Systems. Barcelona, Spain: NIPS: 289 -297."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Anderson P He x Buehler C Bottom-up and top-down attention for image captioning and visual question answering[C]\/\/Proceedings of the lEEE conference on computer vision and pattern recognition.2018:6077-6086","DOI":"10.1109\/CVPR.2018.00636"},{"volume-title":"Jun J and ZhangB T. Bilinear attention networks\/\/Proceedings of the 32nd Conference on Neural Information Processing Systems. Montr\u00e9al","author":"Kim J H","key":"e_1_3_2_1_9_1","unstructured":"Kim J H, Jun J and ZhangB T. Bilinear attention networks\/\/Proceedings of the 32nd Conference on Neural Information Processing Systems. Montr\u00e9al, Canada: Curran Associates Ine : 1564-1574."},{"key":"e_1_3_2_1_10_1","first-page":"91","article-title":"Re-Attention for visual question answering[J].","volume":"2020","author":"Guo W","unstructured":"Guo W, Zhang Z, Wu X, Re-Attention for visual question answering[J].AAA,2020,34(1):91-98.","journal-title":"AAA"},{"key":"e_1_3_2_1_11_1","volume-title":"Review of Language Processing Methods for Visual Question Answering[J].Computer Engineering and Applications","author":"Wang R","year":"2022","unstructured":"Wang R, Wu S, Zhang M, Review of Language Processing Methods for Visual Question Answering[J].Computer Engineering and Applications, 2022, 58(17): 50-60."},{"key":"e_1_3_2_1_12_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio.2018.http:\/\/arxiv.org\/abs\/1710."},{"key":"e_1_3_2_1_13_1","first-page":"4823","article-title":"Heterogeneous graph attention networks for semi- supervised short text classfication[C]\/\/","volume":"2019","author":"Linmei Hu","unstructured":"Linmei Hu, Tianchi Yang, Heterogeneous graph attention networks for semi- supervised short text classfication[C]\/\/In EMNLP,2019: 4823 - 4832.","journal-title":"EMNLP"},{"key":"e_1_3_2_1_14_1","volume-title":"Attention is all you need[J]. Advances in neural information processing systems","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Attention is all you need[J]. Advances in neural information processing systems, 2017, 30."},{"key":"e_1_3_2_1_15_1","first-page":"6281","volume-title":"Deep Modular Co-Attention Networks for Visual Question Answering[C].CVPR","author":"Yu Z","year":"2019","unstructured":"Yu Z, Yu J , Cui Y , Deep Modular Co-Attention Networks for Visual Question Answering[C].CVPR 2019, pp.6281-6290."},{"key":"e_1_3_2_1_16_1","first-page":"2425","volume-title":"ICCV","author":"Antol A.","year":"2015","unstructured":"S. Antol, A. Agrawal, J. Lu, VQA: visual question answering[C].IEEE International Conference on Computer Vision, ICCV, Santiago, Chile, December 7-13, 2015, 2425-2433."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Krishna R Zhu Y K Groth O et al Visual Genome: connecting languageand vision using crowdsourced dense image annotations [J].International journal of computer vision 2017 123(1) :32.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","volume-title":"Ba J. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980","author":"Kingma D P","year":"2014","unstructured":"Kingma D P, Ba J. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980, 2014."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Goyal Y Khot T Summers-Stay D Making the v in vqa matter: Elevating the role of image understanding in visual question answering[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 6904-6913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Object-difference drived graph convolutional networks for visual question answering[J].","volume":"80","author":"Zhu X","year":"2020","unstructured":"Zhu X,Mao Z D,Chen Z N,et al, Object-difference drived graph convolutional networks for visual question answering[J].Multimedia Tools and Applications , 2020,80:1.","journal-title":"Multimedia Tools and Applications"},{"key":"e_1_3_2_1_22_1","volume-title":"Prior visual relationship reasoning for visual question answering[C]\/\/IEEE International Conference on Image Processing (ICIP)","author":"Yang Z Q","year":"2020","unstructured":"Yang Z Q,Qin Z C, Yu J,et al. Prior visual relationship reasoning for visual question answering[C]\/\/IEEE International Conference on Image Processing (ICIP). Paris:IEER,2020:1411."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Tang K H Zhang H W Wu B Y et al Learning to compose dynamic tree structures for VisualContexts [C]\/\/IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach :IEEE 2019:6612.","DOI":"10.1109\/CVPR.2019.00678"}],"event":{"name":"AIPR 2023: 2023 6th International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2023","location":"Xiamen China"},"container-title":["2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641584.3641770","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641584.3641770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:12Z","timestamp":1750291392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641584.3641770"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,22]]},"references-count":23,"alternative-id":["10.1145\/3641584.3641770","10.1145\/3641584"],"URL":"https:\/\/doi.org\/10.1145\/3641584.3641770","relation":{},"subject":[],"published":{"date-parts":[[2023,9,22]]},"assertion":[{"value":"2024-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}