{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:04:52Z","timestamp":1761897892390,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":63,"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":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"LIACS Media Lab"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611958","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:52:54Z","timestamp":1698436374000},"page":"7796-7807","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["FedVQA: Personalized Federated Visual Question Answering over Heterogeneous Scenes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4931-6351","authenticated-orcid":false,"given":"Mingrui","family":"Lao","sequence":"first","affiliation":[{"name":"Leiden University, Leiden, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-8301","authenticated-orcid":false,"given":"Nan","family":"Pu","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8202-0544","authenticated-orcid":false,"given":"Zhun","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Nottingham, Nottingham, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4353-1840","authenticated-orcid":false,"given":"Michael S.","family":"Lew","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Matthew Mattina, Paul N Whatmough, and Venkatesh Saligrama.","author":"Emre Acar Durmus Alp","year":"2021","unstructured":"Durmus Alp Emre Acar, Yue Zhao, Ramon Matas Navarro, Matthew Mattina, Paul N Whatmough, and Venkatesh Saligrama. 2021. Federated learning based on dynamic regularization. arXiv preprint arXiv:2111.04263 (2021)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/UCC56403.2022.00036"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_6_1","volume-title":"Privacy preserving visual question answering. arXiv preprint arXiv:2202.07712","author":"Bara Cristian-Paul","year":"2022","unstructured":"Cristian-Paul Bara, Qing Ping, Abhinav Mathur, Govind Thattai, Rohith MV, and Gaurav S Sukhatme. 2022. Privacy preserving visual question answering. arXiv preprint arXiv:2202.07712 (2022)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01123"},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of machine learning and systems 1","author":"Bonawitz Keith","year":"2019","unstructured":"Keith Bonawitz, Hubert Eichner, Wolfgang Grieskamp, Dzmitry Huba, Alex Ingerman, Vladimir Ivanov, Chloe Kiddon, Jakub Kone\u010dn\u1ef4, Stefano Mazzocchi, Brendan McMahan, et al. 2019. Towards federated learning at scale: System design. Proceedings of machine learning and systems 1 (2019), 374--388."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207469"},{"key":"e_1_3_2_2_11_1","volume-title":"Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu.","author":"Chen Yen-Chun","year":"2019","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2019. Uniter: Learning universal image-text representations. (2019)."},{"key":"e_1_3_2_2_12_1","volume-title":"Personalized federated learning: A meta-learning approach. arXiv preprint arXiv:2002.07948","author":"Fallah Alireza","year":"2020","unstructured":"Alireza Fallah, Aryan Mokhtari, and Asuman Ozdaglar. 2020. Personalized federated learning: A meta-learning approach. arXiv preprint arXiv:2002.07948 (2020)."},{"key":"e_1_3_2_2_13_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016","unstructured":"Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach. 2016. Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331186"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"e_1_3_2_2_18_1","volume-title":"On the convergence of local descent methods in federated learning. arXiv preprint arXiv:1910.14425","author":"Haddadpour Farzin","year":"2019","unstructured":"Farzin Haddadpour and Mehrdad Mahdavi. 2019. On the convergence of local descent methods in federated learning. arXiv preprint arXiv:1910.14425 (2019)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_40"},{"key":"e_1_3_2_2_20_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_2_23_1","volume-title":"Factorized-fl: Agnostic personalized federated learning with kernel factorization & similarity matching. arXiv preprint arXiv:2202.00270","author":"Jeong Wonyong","year":"2022","unstructured":"Wonyong Jeong and Sung Ju Hwang. 2022. Factorized-fl: Agnostic personalized federated learning with kernel factorization & similarity matching. arXiv preprint arXiv:2202.00270 (2022)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475350"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"e_1_3_2_2_26_1","volume-title":"Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al.","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, H Brendan McMahan, Brendan Avent, Aur\u00e9lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. 2021. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning 14, 1--2 (2021), 1--210."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 4519--4529","author":"Khaled Ahmed","year":"2020","unstructured":"Ahmed Khaled, Konstantin Mishchenko, and Peter Richt\u00e1rik. 2020. Tighter theory for local SGD on identical and heterogeneous data. In International Conference on Artificial Intelligence and Statistics. PMLR, 4519--4529."},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language trans-former without convolution or region supervision. In International Conference on Machine Learning. PMLR, 5583--5594."},{"key":"e_1_3_2_2_29_1","volume-title":"Ananda Theertha Suresh, and Dave Bacon","author":"Kone\u010dn\u1ef4 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef4, H Brendan McMahan, Felix X Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492 (2016)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WorldS450073.2020.9210355"},{"key":"e_1_3_2_2_31_1","volume-title":"VQA-BC: Robust Visual Question Answering Via Bidirectional Chaining. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4833--4837","author":"Lao Mingrui","year":"2022","unstructured":"Mingrui Lao, Yanming Guo, Wei Chen, Nan Pu, and Michael S Lew. 2022. VQA-BC: Robust Visual Question Answering Via Bidirectional Chaining. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4833--4837."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475492"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.071"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26527"},{"key":"e_1_3_2_2_35_1","volume-title":"Fedmd: Heterogenous federated learning via model distillation. arXiv preprint arXiv:1910.03581","author":"Li Daliang","year":"2019","unstructured":"Daliang Li and Junpu Wang. 2019. Fedmd: Heterogenous federated learning via model distillation. arXiv preprint arXiv:1910.03581 (2019)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"e_1_3_2_2_38_1","volume-title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection","author":"Li Qinbin","year":"2021","unstructured":"Qinbin Li, Zeyi Wen, Zhaomin Wu, Sixu Hu, Naibo Wang, Yuan Li, Xu Liu, and Bingsheng He. 2021. A survey on federated learning systems: Vision, hype and reality for data privacy and protection. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of Machine learning and systems 2","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems 2 (2020), 429--450."},{"key":"e_1_3_2_2_40_1","volume-title":"On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189","author":"Li Xiang","year":"2019","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. 2019. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189 (2019)."},{"key":"e_1_3_2_2_41_1","volume-title":"Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623","author":"Li Xiaoxiao","year":"2021","unstructured":"Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, and Qi Dou. 2021. Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623 (2021)."},{"key":"e_1_3_2_2_42_1","volume-title":"Think locally, act globally: Federated learning with local and global representations. arXiv preprint arXiv:2001.01523","author":"Liang Paul Pu","year":"2020","unstructured":"Paul Pu Liang, Terrance Liu, Liu Ziyin, Nicholas B Allen, Randy P Auerbach, David Brent, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2020. Think locally, act globally: Federated learning with local and global representations. arXiv preprint arXiv:2001.01523 (2020)."},{"key":"e_1_3_2_2_43_1","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"33","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. 2020. Ensemble distillation for robust model fusion in federated learning. Advances in Neural Information Processing Systems 33 (2020), 2351--2363.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6824"},{"key":"e_1_3_2_2_45_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_46_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR 1273--1282."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"e_1_3_2_2_48_1","volume-title":"Exploring models and data for image question answering. Advances in neural information processing systems 28","author":"Ren Mengye","year":"2015","unstructured":"Mengye Ren, Ryan Kiros, and Richard Zemel. 2015. Exploring models and data for image question answering. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"e_1_3_2_2_51_1","volume-title":"Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490","author":"Tan Hao","year":"2019","unstructured":"Hao Tan and Mohit Bansal. 2019. Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)."},{"key":"e_1_3_2_2_52_1","volume-title":"Contrastive representation distillation. arXiv preprint arXiv:1910.10699","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_2_54_1","volume-title":"Communication-efficient federated learning via knowledge distillation. Nature communications 13, 1","author":"Wu Chuhan","year":"2022","unstructured":"Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang, and Xing Xie. 2022. Communication-efficient federated learning via knowledge distillation. Nature communications 13, 1 (2022), 2032."},{"key":"e_1_3_2_2_55_1","volume-title":"Salvaging federated learning by local adaptation. arXiv preprint arXiv:2002.04758","author":"Yu Tao","year":"2020","unstructured":"Tao Yu, Eugene Bagdasaryan, and Vitaly Shmatikov. 2020. Salvaging federated learning by local adaptation. arXiv preprint arXiv:2002.04758 (2020)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"e_1_3_2_2_58_1","first-page":"10092","article-title":"Parameterized knowledge transfer for personalized federated learning","volume":"34","author":"Zhang Jie","year":"2021","unstructured":"Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wenchao Xu, and Feijie Wu. 2021. Parameterized knowledge transfer for personalized federated learning. Advances in Neural Information Processing Systems 34 (2021), 10092--10104.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_2_60_1","volume-title":"Places: A 10 million image database for scene recognition","author":"Zhou Bolei","year":"2017","unstructured":"Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence 40, 6 (2017), 1452--1464."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"e_1_3_2_2_62_1","volume-title":"Plenty is plague: Fine-grained learning for visual question answering","author":"Zhou Yiyi","year":"2019","unstructured":"Yiyi Zhou, Rongrong Ji, Xiaoshuai Sun, Jinsong Su, Deyu Meng, Yue Gao, and Chunhua Shen. 2019. Plenty is plague: Fine-grained learning for visual question answering. IEEE transactions on pattern analysis and machine intelligence 44, 2 (2019), 697--709."},{"key":"e_1_3_2_2_63_1","volume-title":"International conference on machine learning. PMLR, 12878--12889","author":"Zhu Zhuangdi","year":"2021","unstructured":"Zhuangdi Zhu, Junyuan Hong, and Jiayu Zhou. 2021. Data-free knowledge distillation for heterogeneous federated learning. In International conference on machine learning. PMLR, 12878--12889"}],"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\/3581783.3611958","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:20Z","timestamp":1755821300000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":63,"alternative-id":["10.1145\/3581783.3611958","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611958","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"}}]}}