{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:20:50Z","timestamp":1784092850516,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"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":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591629","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"110-120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1937-2615","authenticated-orcid":false,"given":"Alireza","family":"Salemi","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1891-2919","authenticated-orcid":false,"given":"Juan","family":"Altmayer Pizzorno","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0800-3340","authenticated-orcid":false,"given":"Hamed","family":"Zamani","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2021.103076"},{"key":"e_1_3_2_2_2_1","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson, X. He, C. Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. 2018. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018), 6077--6086."},{"key":"e_1_3_2_2_3_1","volume-title":"VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV).","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh. 2015. VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","unstructured":"Danqi Chen Adam Fisch Jason Weston and Antoine Bordes. 2017. Reading Wikipedia to Answer Open-Domain Questions. https:\/\/doi.org\/10.48550\/ARXIV.1704.00051","DOI":"10.48550\/ARXIV.1704.00051"},{"key":"e_1_3_2_2_5_1","volume-title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection. CoRR","author":"Chen Zhuo","year":"2022","unstructured":"Zhuo Chen, Yufeng Huang, Jiaoyan Chen, Yuxia Geng, Yin Fang, Jeff Z. Pan, Ningyu Zhang, and Wen Zhang. 2022. LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection. CoRR, Vol. abs\/2207.12888 (2022)."},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1942","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying Vision-and-Language Tasks via Text Generation. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 1931--1942."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_9_1","volume-title":"Combination of Multiple Searches. In Text Retrieval Conference.","author":"Edward","unstructured":"Edward A. Fox and Joseph A. Shaw. 1993. Combination of Multiple Searches. In Text Retrieval Conference."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.342"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6294"},{"key":"e_1_3_2_2_16_1","volume-title":"FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation. ArXiv","author":"Hofst\u00e4tter Sebastian","year":"2022","unstructured":"Sebastian Hofst\u00e4tter, Jiecao Chen, Karthik Raman, and Hamed Zamani. 2022. FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation. ArXiv, Vol. abs\/2209.14290 (2022)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Jia Cheng Hu Roberto Cavicchioli and Alessandro Capotondi. 2022. ExpansionNet v2: Block Static Expansion in fast end to end training for Image Captioning. https:\/\/doi.org\/10.48550\/ARXIV.2208.06551","DOI":"10.48550\/ARXIV.2208.06551"},{"key":"e_1_3_2_2_19_1","unstructured":"Samuel Humeau Kurt Shuster Marie-Anne Lachaux and Jason Weston. 2020. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations. https:\/\/openreview.net\/forum\"id=SkxgnnNFvH"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_2_21_1","volume-title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In International Conference on Machine Learning.","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_25_1","volume-title":"Garnett (Eds.)","volume":"31","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. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/96ea64f3a1aa2fd00c72faacf0cb8ac9-Paper.pdf"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.6980"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/278459.258587"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","unstructured":"Weizhe Lin and Bill Byrne. 2022. Retrieval Augmented Visual Question Answering with Outside Knowledge. https:\/\/doi.org\/10.48550\/ARXIV.2210.03809","DOI":"10.48550\/ARXIV.2210.03809"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","unstructured":"Zhenghao Liu Chenyan Xiong Yuanhuiyi Lv Zhiyuan Liu and Ge Yu. 2022. Universal Multi-Modality Retrieval with One Unified Embedding Space. https:\/\/doi.org\/10.48550\/ARXIV.2209.00179","DOI":"10.48550\/ARXIV.2209.00179"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401093"},{"key":"e_1_3_2_2_37_1","volume-title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Marino Kenneth","year":"2020","unstructured":"Kenneth Marino, Xinlei Chen, Devi Parikh, Abhinav Kumar Gupta, and Marcus Rohrbach. 2020. KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 14106--14116."},{"key":"e_1_3_2_2_38_1","volume-title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Marino Kenneth","year":"2019","unstructured":"Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462987"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_2_43_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, Vol. 21, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems -","volume":"1","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS'15). MIT Press, Cambridge, MA, USA, 91--99."},{"key":"e_1_3_2_2_46_1","volume-title":"Self-Critical Sequence Training for Image Captioning. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rennie Steven J.","year":"2016","unstructured":"Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, and Vaibhava Goel. 2016. Self-Critical Sequence Training for Image Captioning. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 1179--1195."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the Third Text REtrieval Conference (TREC-3). Gaithersburg, MD: NIST, 109--126","author":"Robertson Stephen","unstructured":"Stephen Robertson, S. Walker, S. Jones, M. M. Hancock-Beaulieu, and M. Gatford. 1995. Okapi at TREC-3. In Proceedings of the Third Text REtrieval Conference (TREC-3). Gaithersburg, MD: NIST, 109--126."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118669"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the Third Workshop on Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). Association for Computational Linguistics","author":"Shevchenko Violetta","year":"2021","unstructured":"Violetta Shevchenko, Damien Teney, Anthony Dick, and Anton van den Hengel. 2021. Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge. In Proceedings of the Third Workshop on Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). Association for Computational Linguistics, Kyiv, Ukraine, 1--18. https:\/\/aclanthology.org\/2021.lantern-1.1"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_52_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ee6W5UgQLa","author":"Talmor Alon","year":"2021","unstructured":"Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant. 2021. MultiModalQA: complex question answering over text, tables and images. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ee6W5UgQLa"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","unstructured":"Hao Tan and Mohit Bansal. 2019. LXMERT: Learning Cross-Modality Encoder Representations from Transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics Hong Kong China 5100--5111. https:\/\/doi.org\/10.18653\/v1\/D19-1514","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_55_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","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, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"e_1_3_2_2_58_1","volume-title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. ArXiv","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Z. Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason R. Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Gregory S. Corrado, Macduff Hughes, and Jeffrey Dean. 2016. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. ArXiv, Vol. abs\/1609.08144 (2016)."},{"key":"e_1_3_2_2_59_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zeFrfgyZln","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_2_60_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Yang Zhengyuan","year":"2021","unstructured":"Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, and Lijuan Wang. 2021. An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531722"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531791"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591629","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591629"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":63,"alternative-id":["10.1145\/3539618.3591629","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591629","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}