{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:13:05Z","timestamp":1784178785087,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation of China","award":["62276029"],"award-info":[{"award-number":["62276029"]}]},{"name":"National Key R&D Program of China","award":["2023YFF0725103"],"award-info":[{"award-number":["2023YFF0725103"]}]},{"DOI":"10.13039\/501100006374","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","award":["6120220261"],"award-info":[{"award-number":["6120220261"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Zhipu.AI Large Model Fund","award":["202217"],"award-info":[{"award-number":["202217"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657790","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1984-1994","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Let Me Show You Step by Step: An Interpretable Graph Routing Network for Knowledge-based Visual Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3290-7303","authenticated-orcid":false,"given":"Duokang","family":"Wang","sequence":"first","affiliation":[{"name":"SCS, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0993-8495","authenticated-orcid":false,"given":"Linmei","family":"Hu","sequence":"additional","affiliation":[{"name":"SCST, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6634-3156","authenticated-orcid":false,"given":"Rui","family":"Hao","sequence":"additional","affiliation":[{"name":"SCS, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-2628","authenticated-orcid":false,"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[{"name":"SCS, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8062-0675","authenticated-orcid":false,"given":"Xin","family":"Lv","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"SCST, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6244-0664","authenticated-orcid":false,"given":"Juanzi","family":"Li","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045034"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1068"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00154"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462838"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 10294--10303","author":"Hu Ronghang","year":"2019","unstructured":"Ronghang Hu, Anna Rohrbach, Trevor Darrell, and Kate Saenko. 2019. Languageconditioned graph networks for relational reasoning. In Proceedings of the IEEE\/CVF international conference on computer vision. 10294--10303."},{"key":"e_1_3_2_1_13_1","first-page":"5901","article-title":"Learning by Abstraction: The Neural State Machine","volume":"32","author":"Hudson Drew A.","year":"2019","unstructured":"Drew A. Hudson and Christopher D. Manning. 2019. Learning by Abstraction: The Neural State Machine. In Advances in Neural Information Processing Systems, Vol. 32. 5901--5914.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"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 International Conference on Machine Learning. 5583--5594."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_7"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/611"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531753"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.02985"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.maiworkshop-1.12"},{"key":"e_1_3_2_1_22_1","volume-title":"LRTA: a transparent neural-symbolic reasoning framework with modular supervision for visual question answering. arXiv preprint arXiv:2011.10731","author":"Liang Weixin","year":"2020","unstructured":"Weixin Liang, Feiyang Niu, Aishwarya Reganti, Govind Thattai, and Gokhan Tur. 2020. LRTA: a transparent neural-symbolic reasoning framework with modular supervision for visual question answering. arXiv preprint arXiv:2011.10731 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"e_1_3_2_1_24_1","volume-title":"On the Variance of the Adaptive Learning Rate and Beyond. In International Conference on Learning Representations.","author":"Liu Liyuan","year":"2020","unstructured":"Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Jiawei Han. 2020. On the Variance of the Adaptive Learning Rate and Beyond. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_1_28_1","volume-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering. Advances in Neural Information Processing Systems","author":"Narasimhan Medhini","year":"2018","unstructured":"Medhini Narasimhan, Svetlana Lazebnik, and Alexander G Schwing. 2018. Out of the box: Reasoning with graph convolution nets for factual visual question answering. Advances in Neural Information Processing Systems (2018), 2654--2665."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"e_1_3_2_1_30_1","volume-title":"Oh (Eds.)","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 27730--27744."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing, Alessandro Moschitti, Bo Pang, and Walter Daelemans (Eds.). 1532--1543","author":"Pennington Jeffrey","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Alessandro Moschitti, Bo Pang, and Walter Daelemans (Eds.). 1532--1543."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371812"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591629"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.412"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence 33","author":"Shah S.","year":"2019","unstructured":"S. Shah, A. Mishra, N. Yadati, and P. P. Talukdar. 2019. KVQA: Knowledge-Aware Visual Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence 33 (2019), 8876--8884."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.341"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6426"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556245"},{"key":"e_1_3_2_1_44_1","volume-title":"Fvqa: Fact-based visual question answering","author":"Wang Peng","year":"2017","unstructured":"Peng Wang, Qi Wu, Chunhua Shen, Anthony Dick, and Anton Van Den Hengel. 2017. Fvqa: Fact-based visual question answering. IEEE transactions on pattern analysis and machine intelligence 40, 10 (2017), 2413--2427."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"e_1_3_2_1_48_1","volume-title":"Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering","author":"Yu Zhou","year":"2018","unstructured":"Zhou Yu, Jun Yu, Chenchao Xiang, Jianping Fan, and Dacheng Tao. 2018. Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering. IEEE transactions on neural networks and learning systems 29, 12 (2018), 5947--5959."},{"key":"e_1_3_2_1_49_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1440"},{"key":"e_1_3_2_1_51_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv:2205.01068 [cs.CL]"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12057"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 1097--1103","author":"Zhu Zihao","year":"2021","unstructured":"Zihao Zhu, Jing Yu, Yujing Wang, Yajing Sun, Yue Hu, and Qi Wu. 2021. Mucko: multi-layer cross-modal knowledge reasoning for fact-based visual question answering. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 1097--1103."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657790","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:43:12Z","timestamp":1755841392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":53,"alternative-id":["10.1145\/3626772.3657790","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657790","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}