{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:00:58Z","timestamp":1766138458437,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":32,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612837","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9420-9424","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Finetuning Language Models for Multimodal Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2550-3056","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7849-338X","authenticated-orcid":false,"given":"Wen","family":"Xie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0425-0149","authenticated-orcid":false,"given":"Ziqi","family":"Dai","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5804-1508","authenticated-orcid":false,"given":"Jun","family":"Rao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0633-3722","authenticated-orcid":false,"given":"Haokun","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2969-9858","authenticated-orcid":false,"given":"Xuan","family":"Luo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1340","authenticated-orcid":false,"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, 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":"10.1109\/CVPR.2018.00636"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.02635"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406109"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xiaolin Chen Xuemeng Song Yinwei Wei Liqiang Nie and Tat-Seng Chua. 2023. Dual Semantic Knowledge Composed Multimodal Dialog Systems. In SIGIR. ACM 1518--1527.","DOI":"10.1145\/3539618.3591673"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"e_1_3_2_1_10_1","unstructured":"Geoffrey E. Hinton Oriol Vinyals and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In NeurIPS."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"volume-title":"Reducing language biases in visual question answering with visually-grounded question encoder","author":"Kv Gouthaman","key":"e_1_3_2_1_12_1","unstructured":"Gouthaman Kv and Anurag Mittal. 2020. Reducing language biases in visual question answering with visually-grounded question encoder. In ECCV. Springer, 18--34."},{"key":"e_1_3_2_1_13_1","unstructured":"Junnan Li Ramprasaath R. Selvaraju Akhilesh Gotmare Shafiq R. Joty Caiming Xiong and Steven Chu-Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In NeurIPS. 9694--9705."},{"volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","key":"e_1_3_2_1_14_1","unstructured":"Ilya Loshchilov and Frank Hutter. [n.,d.]. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"The 36th Conference on Neural Information Processing Systems (NeurIPS).","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022a. Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering. In The 36th Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.518"},{"volume-title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","author":"Marino Kenneth","key":"e_1_3_2_1_17_1","unstructured":"Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge. In CVPR. Computer Vision Foundation \/ IEEE, 3195--3204."},{"key":"e_1_3_2_1_18_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_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3236837"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.15308"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Jun Rao Tao Qian Shuhan Qi Yulin Wu Qing Liao and Xuan Wang. 2021. Student Can Also be a Good Teacher: Extracting Knowledge from Vision-and-Language Model for Cross-Modal Retrieval. In CIKM.","DOI":"10.1145\/3459637.3482194"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Jun Rao Fei Wang Liang Ding Shuhan Qi Yibing Zhan Weifeng Liu and Dacheng Tao. 2022b. Where Does the Performance Improvement Come From? -A Reproducibility Concern about Image-Text Retrieval. In SIGIR. 2727--2737.","DOI":"10.1145\/3477495.3531715"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 91--99","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the Conference on Neural Information Processing Systems. 91--99."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Learning Representationss.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the International Conference on Learning Representationss."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. MIT Press, 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of the Advances in Neural Information Processing Systems. MIT Press, 5998--6008."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Haokun Wen Xuemeng Song Xin Yang Yibing Zhan and Liqiang Nie. 2021. Comprehensive Linguistic-Visual Composition Network for Image Retrieval. In SIGIR. ACM 1369--1378.","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_1_27_1","volume-title":"Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush.","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Perric Cistac, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. Association for Computational Linguistics, 38--45. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 21--29","author":"Yang Zichao","key":"e_1_3_2_1_28_1","unstructured":"Zichao Yang, Xiaodong He, Jianfeng Gao, Li Deng, and Alexander J. Smola. 2016. Stacked Attention Networks for Image Question Answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 21--29."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"volume-title":"From Recognition to Cognition: Visual Commonsense Reasoning","author":"Zellers Rowan","key":"e_1_3_2_1_30_1","unstructured":"Rowan Zellers, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. From Recognition to Cognition: Visual Commonsense Reasoning. In CVPR. Computer Vision Foundation \/ IEEE, 6720--6731."},{"key":"e_1_3_2_1_31_1","volume-title":"Being the Foundation of Chinese Cognitive Intelligence. CoRR","author":"Zhang Jiaxing","year":"2022","unstructured":"Jiaxing Zhang, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Lin Zhang, Ping Yang, Xinyu Gao, Ziwei Wu, Xiaoqun Dong, Junqing He, Jianheng Zhuo, Qi Yang, Yongfeng Huang, Xiayu Li, Yanghan Wu, Junyu Lu, Xinyu Zhu, Weifeng Chen, Ting Han, Kunhao Pan, Rui Wang, Hao Wang, Xiaojun Wu, Zhongshen Zeng, and Chongpei Chen. 2022. Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence. CoRR, Vol. abs\/2209.02970 (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese. arxiv: 2110.06696 [cs.CL]","author":"Zhang Zhuosheng","year":"2021","unstructured":"Zhuosheng Zhang, Hanqing Zhang, Keming Chen, Yuhang Guo, Jingyun Hua, Yulong Wang, and Ming Zhou. 2021. Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese. arxiv: 2110.06696 [cs.CL]"}],"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\/3581783.3612837","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:13:03Z","timestamp":1755821583000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":32,"alternative-id":["10.1145\/3581783.3612837","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612837","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"}}]}}