{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:23:45Z","timestamp":1781259825878,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":65,"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\/3581783.3612121","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:52:06Z","timestamp":1698436326000},"page":"4747-4758","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Domain Lifelong Visual Question Answering via Self-Critical Distillation"],"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-396X","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2624-5271","authenticated-orcid":false,"given":"Erwin M.","family":"Bakker","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1971.10488811"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00047"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5716--5725","author":"Chao Wei-Lun","year":"2018","unstructured":"Wei-Lun Chao, Hexiang Hu, and Fei Sha. 2018. Cross-dataset adaptation for visual question answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5716--5725."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073279"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222934"},{"key":"e_1_3_2_2_10_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_11_1","volume-title":"A continual learning survey: Defying forgetting in classification tasks","author":"Lange Matthias De","year":"2021","unstructured":"Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ale? Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. 2021. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence 44, 7 (2021), 3366--3385."},{"key":"e_1_3_2_2_12_1","volume-title":"Episodic memory in lifelong language learning. Advances in Neural Information Processing Systems 32","author":"de Masson D'Autume Cyprien","year":"2019","unstructured":"Cyprien de Masson D'Autume, Sebastian Ruder, Lingpeng Kong, and Dani Yogatama. 2019. Episodic memory in lifelong language learning. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_13_1","first-page":"16736","article-title":"Ratt: Recurrent attention to transient tasks for continual image captioning","volume":"33","author":"Chiaro Riccardo Del","year":"2020","unstructured":"Riccardo Del Chiaro, Bart\u0140omiej Twardowski, Andrew Bagdanov, and Joost Van de Weijer. 2020. Ratt: Recurrent attention to transient tasks for continual image captioning. Advances in Neural Information Processing Systems 33 (2020), 16736--16748.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0.","author":"Garcia Noa","year":"2018","unstructured":"Noa Garcia and George Vogiatzis. 2018. How to read paintings: semantic art un-derstanding with multi-modal retrieval. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_8"},{"key":"e_1_3_2_2_16_1","volume-title":"Low-Level Linguistic Controls for Style Transfer and Content Preservation. arXiv preprint arXiv:1911.03385","author":"Gero Katy","year":"2019","unstructured":"Katy Gero, Chris Kedzie, Jonathan Reeve, and Lydia Chilton. 2019. Low-Level Linguistic Controls for Style Transfer and Content Preservation. arXiv preprint arXiv:1911.03385 (2019)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_19_1","volume-title":"Psycholinguistics meets continual learning: Measuring catastrophic forgetting in visual question answering. arXiv preprint arXiv:1906.04229","author":"Greco Claudio","year":"2019","unstructured":"Claudio Greco, Barbara Plank, Raquel Fern\u00e1ndez, and Raffaella Bernardi. 2019. Psycholinguistics meets continual learning: Measuring catastrophic forgetting in visual question answering. arXiv preprint arXiv:1906.04229 (2019)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_22_1","volume-title":"International conference on learning representations.","author":"Hu Wenpeng","year":"2018","unstructured":"Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao, Jinwen Ma, Dongyan Zhao, and Rui Yan. 2018. Overcoming catastrophic forgetting for continual learning via model adaptation. In International conference on learning representations."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_2_25_1","volume-title":"Meta-learning representations for continual learning. Advances in neural information processing systems 32","author":"Javed Khurram","year":"2019","unstructured":"Khurram Javed and Martha White. 2019. Meta-learning representations for continual learning. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475350"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"James M Joyce. 2011. Kullback-leibler divergence. In International encyclopedia of statistical science. 720--722.","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"e_1_3_2_2_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475492"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26527"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25208"},{"key":"e_1_3_2_2_34_1","volume-title":"Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges. Information fusion 58","author":"Lesort Timoth\u00e9e","year":"2020","unstructured":"Timoth\u00e9e Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, and Natalia D\u00edaz-Rodr\u00edguez. 2020. Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges. Information fusion 58 (2020), 52--68."},{"key":"e_1_3_2_2_35_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_2_36_1","volume-title":"Learning without forgetting","author":"Li Zhizhong","year":"2017","unstructured":"Zhizhong Li and Derek Hoiem. 2017. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence 40, 12 (2017), 2935--2947."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"e_1_3_2_2_38_1","volume-title":"Model behavior preserving for class-incremental learning","author":"Liu Yu","year":"2022","unstructured":"Yu Liu, Xiaopeng Hong, Xiaoyu Tao, Songlin Dong, Jingang Shi, and Yihong Gong. 2022. Model behavior preserving for class-incremental learning. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_2_39_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_40_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_41_1","volume-title":"Psychology of learning and motivation.","author":"McCloskey Michael","unstructured":"Michael McCloskey and Neal J Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation. Vol. 24. Elsevier, 109--165."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"e_1_3_2_2_44_1","volume-title":"Christopher Kanan, and Stefan Wermter.","author":"Parisi German I","year":"2019","unstructured":"German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. 2019. Continual lifelong learning with neural networks: A review. Neural networks 113 (2019), 54--71."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00343"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00781"},{"key":"e_1_3_2_2_47_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","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. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01072"},{"key":"e_1_3_2_2_50_1","volume-title":"From deterministic to generative: Multimodal stochastic RNNs for video captioning","author":"Song Jingkuan","year":"2018","unstructured":"Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, Alan Hanjalic, and Heng Tao Shen. 2018. From deterministic to generative: Multimodal stochastic RNNs for video captioning. IEEE transactions on neural networks and learning systems 30, 10 (2018), 3047--3058."},{"key":"e_1_3_2_2_51_1","first-page":"29440","article-title":"Climb: A continual learning benchmark for vision-and-language tasks","volume":"35","author":"Srinivasan Tejas","year":"2022","unstructured":"Tejas Srinivasan, Ting-Yun Chang, Leticia Pinto Alva, Georgios Chochlakis, Mohammad Rostami, and Jesse Thomason. 2022. Climb: A continual learning benchmark for vision-and-language tasks. Advances in Neural Information Processing Systems 35 (2022), 29440--29453.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"e_1_3_2_2_53_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_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_2_55_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_56_1","volume-title":"Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. arXiv preprint arXiv:1905.09418","author":"Voita Elena","year":"2019","unstructured":"Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich, and Ivan Titov. 2019. Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. arXiv preprint arXiv:1905.09418 (2019)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Athanasios Voulodimos Nikolaos Doulamis Anastasios Doulamis Eftychios Protopapadakis et al. 2018. Deep learning for computer vision: A brief review. Computational intelligence and neuroscience 2018 (2018).","DOI":"10.1155\/2018\/7068349"},{"key":"e_1_3_2_2_58_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3628--3638","author":"Wang Kai","unstructured":"Kai Wang, Luis Herranz, and Joost van de Weijer. 2021. Continual learning in cross-modal retrieval. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3628--3638."},{"key":"e_1_3_2_2_59_1","volume-title":"Open-ended visual question answering by multi-modal domain adaptation. arXiv preprint arXiv:1911.04058","author":"Xu Yiming","year":"2019","unstructured":"Yiming Xu, Lin Chen, Zhongwei Cheng, Lixin Duan, and Jiebo Luo. 2019. Open-ended visual question answering by multi-modal domain adaptation. arXiv preprint arXiv:1911.04058 (2019)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_2"},{"key":"e_1_3_2_2_61_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2907--2916","author":"Yu Lu","unstructured":"Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost van de Weijer, Yongmei Cheng, and Arnau Ramisa. 2019. Learning metrics from teachers: Compact networks for image embedding. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2907--2916."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"e_1_3_2_2_63_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_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00697"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612121","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:43Z","timestamp":1755821023000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":65,"alternative-id":["10.1145\/3581783.3612121","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612121","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"}}]}}