{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:26Z","timestamp":1755825026347,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"Sichuan Science and Technology Program","award":["2025ZNSFSC0482"],"award-info":[{"award-number":["2025ZNSFSC0482"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733463","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"255-264","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ViT-Enhanced Prompts: Integrating Pre-Trained Knowledge for Robust Continuous Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8564-3843","authenticated-orcid":false,"given":"Xiaoyu","family":"Du","sequence":"first","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2165-476X","authenticated-orcid":false,"given":"Guoqiang","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4353-1840","authenticated-orcid":false,"given":"Michael S.","family":"Lew","sequence":"additional","affiliation":[{"name":"LIACS Media Lab, Leiden University, Leiden, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6575-5928","authenticated-orcid":false,"given":"Song","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chonqqing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Jae Hee Lee, and Stefan Wermter.","author":"Ahrens Kyra","year":"2023","unstructured":"Kyra Ahrens, Hans Hergen Lehmann, Jae Hee Lee, and Stefan Wermter. 2023. Read Between the Layers: Leveraging Intra-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models. ArXiv, Vol. abs\/2312.08888 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266210201"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1007\/978--3-030-01219--9_9"},{"key":"e_1_3_2_1_3_1","volume-title":"Online Continual Learning with Maximally Interfered Retrieval. ArXiv","author":"Aljundi Rahaf","year":"2019","unstructured":"Rahaf Aljundi, Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Min Lin, Laurent Charlin, and Tinne Tuytelaars. 2019a. Online Continual Learning with Maximally Interfered Retrieval. ArXiv, Vol. abs\/1908.04742 (2019). https:\/\/api.semanticscholar.org\/CorpusID:199552250"},{"key":"e_1_3_2_1_4_1","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Aljundi Rahaf","year":"2016","unstructured":"Rahaf Aljundi, Punarjay Chakravarty, and Tinne Tuytelaars. 2016. Expert Gate: Lifelong Learning with a Network of Experts. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 7120--7129. https:\/\/api.semanticscholar.org\/CorpusID:914027"},{"unstructured":"Rahaf Aljundi Min Lin Baptiste Goujaud and Yoshua Bengio. 2019b. Gradient based sample selection for online continual learning. In Neural Information Processing Systems. https:\/\/api.semanticscholar.org\/CorpusID:195345359","key":"e_1_3_2_1_5_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1109\/CVPR46437.2021.00812"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"e_1_3_2_1_8_1","volume-title":"2020 25th International Conference on Pattern Recognition (ICPR)","author":"Buzzega Pietro","year":"2020","unstructured":"Pietro Buzzega, Matteo Boschini, Angelo Porrello, and Simone Calderara. 2020. Rethinking Experience Replay: a Bag of Tricks for Continual Learning. 2020 25th International Conference on Pattern Recognition (ICPR) (2020), 2180--2187. https:\/\/api.semanticscholar.org\/CorpusID:222290541"},{"key":"e_1_3_2_1_9_1","volume-title":"Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models. ArXiv","author":"Cao Boxi","year":"2023","unstructured":"Boxi Cao, Qiaoyu Tang, Hongyu Lin, Xianpei Han, Jiawei Chen, Tianshu Wang, and Le Sun. 2023. Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models. ArXiv, Vol. abs\/2305.09144 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258715133"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1007\/978--3-030--58452--8_13"},{"key":"e_1_3_2_1_11_1","volume-title":"Philip H. S. Torr, and Marc'Aurelio Ranzato.","author":"Chaudhry Arslan","year":"2019","unstructured":"Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Philip H. S. Torr, and Marc'Aurelio Ranzato. 2019. Continual Learning with Tiny Episodic Memories. ArXiv, Vol. abs\/1902.10486 (2019). https:\/\/api.semanticscholar.org\/CorpusID:67855851"},{"key":"e_1_3_2_1_12_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv","author":"Dosovitskiy Alexey","year":"1929","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv, Vol. abs\/2010.11929 (2020). https:\/\/api.semanticscholar.org\/CorpusID:225039882"},{"key":"e_1_3_2_1_13_1","volume-title":"Orthogonal Gradient Descent for Continual Learning. ArXiv","author":"Farajtabar Mehrdad","year":"2019","unstructured":"Mehrdad Farajtabar, Navid Azizan, Alexander Mott, and Ang Li. 2019. Orthogonal Gradient Descent for Continual Learning. ArXiv, Vol. abs\/1910.07104 (2019). https:\/\/api.semanticscholar.org\/CorpusID:204734380"},{"key":"e_1_3_2_1_14_1","volume-title":"An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks. CoRR","author":"Goodfellow Ian J.","year":"2013","unstructured":"Ian J. Goodfellow, Mehdi Mirza, Xia Da, Aaron C. Courville, and Yoshua Bengio. 2013. An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks. CoRR, Vol. abs\/1312.6211 (2013). https:\/\/api.semanticscholar.org\/CorpusID:12730344"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"e_1_3_2_1_16_1","volume-title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting. ArXiv","author":"Hayes Tyler L.","year":"2019","unstructured":"Tyler L. Hayes, Kushal Kafle, Robik Shrestha, Manoj Acharya, and Christopher Kanan. 2019. REMIND Your Neural Network to Prevent Catastrophic Forgetting. ArXiv, Vol. abs\/1910.02509 (2019). https:\/\/api.semanticscholar.org\/CorpusID:203837695"},{"key":"e_1_3_2_1_17_1","volume-title":"Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019","author":"Tyler","year":"2025","unstructured":"Tyler L. Hayes and Christopher Kanan. 2019. Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019), 887--896. https:\/\/api.semanticscholar.org\/CorpusID:202539644"},{"key":"e_1_3_2_1_18_1","volume-title":"Exemplar-Free Online Continual Learning. 2022 IEEE International Conference on Image Processing (ICIP)","author":"He Jiangpeng","year":"2022","unstructured":"Jiangpeng He and Fengqing Maggie Zhu. 2022. Exemplar-Free Online Continual Learning. 2022 IEEE International Conference on Image Processing (ICIP) (2022), 541--545. https:\/\/api.semanticscholar.org\/CorpusID:246824015"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","volume-title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2020","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Lixuan Zhu, Samyak Parajuli, Mike Guo, Dawn Xiaodong Song, Jacob Steinhardt, and Justin Gilmer. 2020. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2020), 8320--8329. https:\/\/api.semanticscholar.org\/CorpusID:220250257"},{"key":"e_1_3_2_1_21_1","volume-title":"Visual Prompt Tuning. ArXiv","author":"Jia Menglin","year":"2022","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge J. Belongie, Bharath Hariharan, and Ser Nam Lim. 2022. Visual Prompt Tuning. ArXiv, Vol. abs\/2203.12119 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247618727"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1109\/ICCV51070.2023.01053"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1073\/pnas.1611835114"},{"unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. https:\/\/api.semanticscholar.org\/CorpusID:18268744","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","volume-title":"Hinton","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey E. Hinton. 2015. Deep Learning. https:\/\/api.semanticscholar.org\/CorpusID:3074096"},{"key":"e_1_3_2_1_26_1","volume-title":"The Power of Scale for Parameter-Efficient Prompt Tuning. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:233296808","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:233296808"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"19742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730--19742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.18653\/v1\/2021.acl-long.353"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/TPAMI.2017.2773081"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_31_1","volume-title":"Batches. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Lomonaco Vincenzo","year":"2019","unstructured":"Vincenzo Lomonaco, Davide Maltoni, and Lorenzo Pellegrini. 2019. Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019), 989--998. https:\/\/api.semanticscholar.org\/CorpusID:216036341"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1016\/S0079--7421(08)60536--8"},{"key":"e_1_3_2_1_33_1","volume-title":"Toward Understanding Catastrophic Forgetting in Continual Learning. ArXiv","author":"Nguyen Cuong V","year":"2019","unstructured":"Cuong V Nguyen, Alessandro Achille, Michael Lam, Tal Hassner, Vijay Mahadevan, and Stefano Soatto. 2019. Toward Understanding Catastrophic Forgetting in Continual Learning. ArXiv, Vol. abs\/1908.01091 (2019). https:\/\/api.semanticscholar.org\/CorpusID:199442601"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1109\/TMC.2021.3097912"},{"key":"e_1_3_2_1_35_1","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016","author":"Rebuffi Sylvestre-Alvise","year":"2065","unstructured":"Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, G. Sperl, and Christoph H. Lampert. 2016. iCaRL: Incremental Classifier and Representation Learning. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 5533--5542. https:\/\/api.semanticscholar.org\/CorpusID:206596260"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/CVPR52733.2024.02229"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1109\/ICCV51070.2023.00542"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_38_1","DOI":"10.1109\/ICCV48922.2021.00924"},{"key":"e_1_3_2_1_39_1","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Smith James","year":"2022","unstructured":"James Smith, Junjiao Tian, Yen-Chang Hsu, and Zsolt Kira. 2022. A Closer Look at Rehearsal-Free Continual Learning *. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2022), 2410--2420. https:\/\/api.semanticscholar.org\/CorpusID:247839519"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1109\/CVPR52729.2023.01146"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1109\/CVPRW59228.2023.00239"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1109\/ICCV51070.2023.00164"},{"key":"e_1_3_2_1_43_1","volume-title":"Few-Shot Class-Incremental Learning. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tao Xiaoyu","year":"2020","unstructured":"Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, and Yihong Gong. 2020. Few-Shot Class-Incremental Learning. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 12180--12189. https:\/\/api.semanticscholar.org\/CorpusID:216080738"},{"key":"e_1_3_2_1_44_1","volume-title":"Functional Regularisation for Continual Learning using Gaussian Processes. ArXiv","author":"Titsias Michalis K.","year":"2019","unstructured":"Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, and Yee Whye Teh. 2019. Functional Regularisation for Continual Learning using Gaussian Processes. ArXiv, Vol. abs\/1901.11356 (2019). https:\/\/api.semanticscholar.org\/CorpusID:59523607"},{"key":"e_1_3_2_1_45_1","volume-title":"Nature Communications","volume":"11","author":"Gido","year":"2020","unstructured":"Gido M. van de Ven, Hava T. Siegelmann, and Andreas Savas Tolias. 2020. Brain-inspired replay for continual learning with artificial neural networks. Nature Communications, Vol. 11 (2020). https:\/\/api.semanticscholar.org\/CorpusID:221111120"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_47_1","volume-title":"Efficient Feature Transformations for Discriminative and Generative Continual Learning. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Verma Vinay Kumar","year":"2021","unstructured":"Vinay Kumar Verma, Kevin J Liang, Nikhil Mehta, Piyush Rai, and Lawrence Carin. 2021. Efficient Feature Transformations for Discriminative and Generative Continual Learning. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 13860--13870. https:\/\/api.semanticscholar.org\/CorpusID:232352560"},{"key":"e_1_3_2_1_48_1","volume-title":"Belongie","author":"Wah Catherine","year":"2011","unstructured":"Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge J. Belongie. 2011. The Caltech-UCSD Birds-200--2011 Dataset. https:\/\/api.semanticscholar.org\/CorpusID:16119123"},{"key":"e_1_3_2_1_49_1","volume-title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning. ArXiv","author":"Wang Yabin","year":"2022","unstructured":"Yabin Wang, Zhiwu Huang, and Xiaopeng Hong. 2022a. S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning. ArXiv, Vol. abs\/2207.12819 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251066766"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1007\/978--3-031--19809-0_36"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1109\/CVPR52688.2022.00024"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_52_1","DOI":"10.1016\/j.engappai.2024.107990"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1016\/j.eswa.2024.125291"},{"key":"e_1_3_2_1_54_1","volume-title":"Large Scale Incremental Learning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019","author":"Wu Yue","year":"2019","unstructured":"Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Raymond Fu. 2019. Large Scale Incremental Learning. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 374--382. https:\/\/api.semanticscholar.org\/CorpusID:173187918"},{"key":"e_1_3_2_1_55_1","volume-title":"Meta-attention for ViT-backed Continual Learning. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xue Mengqi","year":"2022","unstructured":"Mengqi Xue, Haofei Zhang, Jie Song, and Mingli Song. 2022. Meta-attention for ViT-backed Continual Learning. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), 150--159. https:\/\/api.semanticscholar.org\/CorpusID:247596966"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_56_1","DOI":"10.5555\/2832249.2832392"},{"key":"e_1_3_2_1_57_1","volume-title":"Revisiting Incremental Learning with Pre-trained Language Models. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:266191340","author":"Zheng Junhao","year":"2023","unstructured":"Junhao Zheng, Shengjie Qiu, and Qianli Ma. 2023. Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:266191340"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_58_1","DOI":"10.24963\/ijcai.2024\/924"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"ICMR '25","name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:12:42Z","timestamp":1755749562000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":58,"alternative-id":["10.1145\/3731715.3733463","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733463","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}