{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T14:47:28Z","timestamp":1762094848444,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["62276242"],"award-info":[{"award-number":["62276242"]}]},{"name":"Anhui Province Key Research and Development Program","award":["202104a05020007"],"award-info":[{"award-number":["202104a05020007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612850","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9487-9491","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Answer-Based Entity Extraction and Alignment for Visual Text Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3891-9207","authenticated-orcid":false,"given":"Mohan","family":"Jing","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4385-2734","authenticated-orcid":false,"given":"Weihao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4576-1178","authenticated-orcid":false,"given":"Tongxu","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6000-6631","authenticated-orcid":false,"given":"Bingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8974-3813","authenticated-orcid":false,"given":"Keda","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1678-1118","authenticated-orcid":false,"given":"Fangyu","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3598-8564","authenticated-orcid":false,"given":"Jianqing","family":"Sun","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co.,Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8309-1301","authenticated-orcid":false,"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co.,Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_3_1","volume-title":"Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts. In Advances in Neural Information Processing Systems. 32897--32912."},{"key":"e_1_3_2_1_4_1","volume-title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning. arXiv preprint arXiv:2303.02635","author":"Chen Kang","year":"2023","unstructured":"Kang Chen and Xiangqian Wu. 2023. VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning. arXiv preprint arXiv:2303.02635 (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Zhe Gan Yen-Chun Chen Linjie Li Chen Zhu Yu Cheng and Jingjing Liu. 2020. Large-Scale Adversarial Training for Vision-and-Language Representation Learning. In Advances in Neural Information Processing Systems. 6616--6628."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"e_1_3_2_1_11_1","volume-title":"Pythia v0. 1: the winning entry to the vqa challenge","author":"Jiang Yu","year":"2018","unstructured":"Yu Jiang, Vivek Natarajan, Xinlei Chen, Marcus Rohrbach, Dhruv Batra, and Devi Parikh. 2018. Pythia v0. 1: the winning entry to the vqa challenge 2018. arXiv preprint arXiv:1807.09956 (2018)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1351"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In Proceedings of the 38th International Conference on Machine Learning. 5583--5594."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_15_1","unstructured":"Junnan Li Ramprasaath Selvaraju Akhilesh Gotmare Shafiq Joty Caiming Xiong and Steven Chu Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Advances in Neural Information Processing Systems. 9694--9705."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"e_1_3_2_1_17_1","unstructured":"Jiasen Lu Dhruv Batra Devi Parikh and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_18_1","unstructured":"Mengye Ren Ryan Kiros and Richard Zemel. 2015. Exploring Models and Data for Image Question Answering. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_21_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572833"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612850","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:13:45Z","timestamp":1755821625000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":25,"alternative-id":["10.1145\/3581783.3612850","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612850","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}