{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:15:37Z","timestamp":1783102537481,"version":"3.54.6"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQN26F020039"],"award-info":[{"award-number":["LQN26F020039"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62501532"],"award-info":[{"award-number":["62501532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008043","name":"Zhejiang Sci-Tech University","doi-asserted-by":"publisher","award":["26232179-Y"],"award-info":[{"award-number":["26232179-Y"]}],"id":[{"id":"10.13039\/501100008043","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.cviu.2026.104798","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T07:47:11Z","timestamp":1778572031000},"page":"104798","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["PSM: Prompt specialization module for prompt-based continual learning"],"prefix":"10.1016","volume":"269","author":[{"given":"Jun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinyue","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1785-7847","authenticated-orcid":false,"given":"Zheming","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104798_b1","doi-asserted-by":"crossref","unstructured":"Aljundi,\u00a0R., Babiloni,\u00a0F., Elhoseiny,\u00a0M., Rohrbach,\u00a0M., Tuytelaars,\u00a0T., 2018. Memory aware synapses: Learning what (not) to forget. In: Proc. Eur. Conf. Comput. Vis.. ECCV, pp. 139\u2013154.","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"10.1016\/j.cviu.2026.104798_b2","article-title":"Online continual learning with maximal interfered retrieval","volume":"vol. 32","author":"Aljundi","year":"2019"},{"key":"10.1016\/j.cviu.2026.104798_b3","series-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"10.1016\/j.cviu.2026.104798_b4","doi-asserted-by":"crossref","unstructured":"Bang,\u00a0J., Kim,\u00a0H., Yoo,\u00a0Y., Ha,\u00a0J.-W., Choi,\u00a0J., 2021. Rainbow memory: Continual learning with a memory of diverse samples. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 8218\u20138227.","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"10.1016\/j.cviu.2026.104798_b5","doi-asserted-by":"crossref","unstructured":"Belouadah,\u00a0E., Popescu,\u00a0A., 2019. IL2M: Class incremental learning with dual memory. In: Proc. IEEE Int. Conf. Comput. Vis.. ICCV, pp. 583\u2013592.","DOI":"10.1109\/ICCV.2019.00067"},{"key":"10.1016\/j.cviu.2026.104798_b6","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neunet.2020.12.003","article-title":"A comprehensive study of class incremental learning algorithms for visual tasks","volume":"135","author":"Belouadah","year":"2021","journal-title":"Neural Netw."},{"key":"10.1016\/j.cviu.2026.104798_b7","series-title":"Efficient lifelong learning with A-GEM","author":"Chaudhry","year":"2018"},{"key":"10.1016\/j.cviu.2026.104798_b8","series-title":"Domain incremental lifelong learning in an open world","author":"Dai","year":"2023"},{"key":"10.1016\/j.cviu.2026.104798_b9","doi-asserted-by":"crossref","unstructured":"Deng,\u00a0J., Dong,\u00a0W., Socher,\u00a0R., Li,\u00a0L.-J., Li,\u00a0K., Fei-Fei,\u00a0L., 2009. ImageNet: A large-scale hierarchical image database. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.. pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.cviu.2026.104798_b10","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.cviu.2026.104798_b11","doi-asserted-by":"crossref","unstructured":"Douillard,\u00a0A., Ram\u00e9,\u00a0A., Couairon,\u00a0G., Cord,\u00a0M., 2022. DyTox: Transformers for continual learning with dynamic token expansion. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 9285\u20139295.","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"10.1016\/j.cviu.2026.104798_b12","series-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b13","doi-asserted-by":"crossref","unstructured":"Gao,\u00a0Z., Cen,\u00a0J., Chang,\u00a0X., 2024. Consistent prompting for rehearsal-free continual learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 28463\u201328473.","DOI":"10.1109\/CVPR52733.2024.02689"},{"key":"10.1016\/j.cviu.2026.104798_b14","doi-asserted-by":"crossref","unstructured":"Hayes,\u00a0T.L., Cahill,\u00a0N.D., Kanan,\u00a0C., 2019. Memory efficient experience replay for streaming learning. In: Proc. Int. Conf. Robot. Autom.. ICRA, pp. 9769\u20139776.","DOI":"10.1109\/ICRA.2019.8793982"},{"key":"10.1016\/j.cviu.2026.104798_b15","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., Sun,\u00a0J., 2016. Deep residual learning for image recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.cviu.2026.104798_b16","doi-asserted-by":"crossref","unstructured":"Hendrycks,\u00a0D., Basart,\u00a0S., Mu,\u00a0N., Kadavath,\u00a0S., Wang,\u00a0F., Dorundo,\u00a0E., Desai,\u00a0R., Zhu,\u00a0T., Parajuli,\u00a0S., Guo,\u00a0M., Song,\u00a0D., Steinhardt,\u00a0J., Gilmer,\u00a0J., 2021. The many faces of robustness: A critical analysis of out-of-distribution generalization. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis.. pp. 8340\u20138349.","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"10.1016\/j.cviu.2026.104798_b17","doi-asserted-by":"crossref","unstructured":"Iscen,\u00a0A., Zhang,\u00a0J., Lazebnik,\u00a0S., Schmid,\u00a0C., 2020. Memory-efficient incremental learning through feature adaptation. In: Proc. Eur. Conf. Comput. Vis.. ECCV, pp. 699\u2013715.","DOI":"10.1007\/978-3-030-58517-4_41"},{"key":"10.1016\/j.cviu.2026.104798_b18","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.cviu.2026.104798_b19","doi-asserted-by":"crossref","unstructured":"Jung,\u00a0D., Han,\u00a0D., Bang,\u00a0J., Song,\u00a0H., 2023. Generating instance-level prompts for rehearsal-free continual learning. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis.. pp. 11847\u201311857.","DOI":"10.1109\/ICCV51070.2023.01088"},{"key":"10.1016\/j.cviu.2026.104798_b20","series-title":"Deep generative dual memory network for continual learning","author":"Kamra","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b21","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"},{"issue":"13","key":"10.1016\/j.cviu.2026.104798_b22","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Nat. Acad. Sci."},{"key":"10.1016\/j.cviu.2026.104798_b23","unstructured":"Krizhevsky,\u00a0A., Hinton,\u00a0G., 2009. Learning Multiple Layers of Features from Tiny Images. Tech. Rep.."},{"key":"10.1016\/j.cviu.2026.104798_b24","article-title":"Overcoming catastrophic forgetting by incremental moment matching","volume":"vol. 30","author":"Lee","year":"2017"},{"issue":"12","key":"10.1016\/j.cviu.2026.104798_b25","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104798_b26","series-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.cviu.2026.104798_b27","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Z., Zhao,\u00a0L., Zhang,\u00a0Z., Zhang,\u00a0H., Liu,\u00a0D., Liu,\u00a0T., Metaxas,\u00a0D.N., 2024. Steering prototypes with prompt-tuning for rehearsal-free continual learning. In: Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.. pp. 2523\u20132533.","DOI":"10.1109\/WACV57701.2024.00251"},{"key":"10.1016\/j.cviu.2026.104798_b28","series-title":"Preserving earlier knowledge in continual learning with the help of all previous feature extractors","author":"Li","year":"2021"},{"key":"10.1016\/j.cviu.2026.104798_b29","unstructured":"Li,\u00a0X., Zhou,\u00a0Y., Wu,\u00a0T., Socher,\u00a0R., Xiong,\u00a0C., 2019. Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting. In: Proc. Int. Conf. Mach. Learn.. pp. 3925\u20133934."},{"key":"10.1016\/j.cviu.2026.104798_b30","article-title":"Gradient episodic memory for continual learning","volume":"vol. 30","author":"Lopez-Paz","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b31","article-title":"Task-to-instance prompt learning for vision-language models at test time","author":"Lu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"10.1016\/j.cviu.2026.104798_b32","first-page":"3366","article-title":"A continual learning survey: Defying forgetting in classification tasks","volume":"44","author":"M.\u00a0De\u00a0Lange","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104798_b33","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.neucom.2021.10.021","article-title":"Online continual learning in image classification: An empirical survey","volume":"469","author":"Mai","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cviu.2026.104798_b34","doi-asserted-by":"crossref","unstructured":"Mallya,\u00a0A., Lazebnik,\u00a0S., 2018. PackNet: Adding multiple tasks to a single network by iterative pruning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.. pp. 7765\u20137773.","DOI":"10.1109\/CVPR.2018.00810"},{"issue":"5","key":"10.1016\/j.cviu.2026.104798_b35","doi-asserted-by":"crossref","first-page":"5513","DOI":"10.1109\/TPAMI.2022.3213473","article-title":"Class-incremental learning: Survey and performance evaluation on image classification","volume":"45","author":"Masana","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104798_b36","first-page":"109","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"vol. 24","author":"McCloskey","year":"1989"},{"key":"10.1016\/j.cviu.2026.104798_b37","article-title":"RanPAC: Random projections and pre-trained models for continual learning","volume":"vol. 36","author":"McDonnell","year":"2024"},{"issue":"6","key":"10.1016\/j.cviu.2026.104798_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.cviu.2026.104798_b39","series-title":"Tiny ImageNet","author":"Moustafa","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b40","doi-asserted-by":"crossref","unstructured":"Ostapenko,\u00a0O., Puscas,\u00a0M., Klein,\u00a0T., Jahnichen,\u00a0P., Nabi,\u00a0M., 2019. Learning to remember: A synaptic plasticity driven framework for continual learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 11321\u201311329.","DOI":"10.1109\/CVPR.2019.01158"},{"key":"10.1016\/j.cviu.2026.104798_b41","unstructured":"Ramasesh,\u00a0V.V., Lewkowycz,\u00a0A., Dyer,\u00a0E., 2021. Effect of scale on catastrophic forgetting in neural networks. In: Proc. Int. Conf. Learn. Represent.."},{"key":"10.1016\/j.cviu.2026.104798_b42","doi-asserted-by":"crossref","unstructured":"Rebuffi,\u00a0S.-A., Kolesnikov,\u00a0A., Sperl,\u00a0G., Lampert,\u00a0C.H., 2017. iCaRL: Incremental classifier and representation learning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.. pp. 2001\u20132010.","DOI":"10.1109\/CVPR.2017.587"},{"key":"10.1016\/j.cviu.2026.104798_b43","unstructured":"Serra,\u00a0J., Suris,\u00a0D., Miron,\u00a0M., Karatzoglou,\u00a0A., 2018. Overcoming catastrophic forgetting with hard attention to the task. In: Proc. Int. Conf. Mach. Learn.. pp. 4548\u20134557."},{"key":"10.1016\/j.cviu.2026.104798_b44","article-title":"Continual learning with deep generative replay","volume":"vol. 30","author":"Shin","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b45","doi-asserted-by":"crossref","unstructured":"Smith,\u00a0J.S., Karlinsky,\u00a0L., Gutta,\u00a0V., Cascante-Bonilla,\u00a0P., Kim,\u00a0D., Arbelle,\u00a0A., Panda,\u00a0R., Feris,\u00a0R., Kira,\u00a0Z., 2023. CODA-Prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 11909\u201311919.","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"10.1016\/j.cviu.2026.104798_b46","series-title":"Three scenarios for continual learning","author":"Van de Ven","year":"2019"},{"key":"10.1016\/j.cviu.2026.104798_b47","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.cviu.2026.104798_b48","series-title":"The Caltech-UCSD Birds-200\u20132011 Dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.cviu.2026.104798_b49","first-page":"5682","article-title":"S-Prompts learning with pre-trained transformers: An Occam\u2019s razor for domain incremental learning","volume":"vol. 35","author":"Wang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104798_b50","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Z., Jian,\u00a0T., Chowdhury,\u00a0K., Wang,\u00a0Y., Dy,\u00a0J., Ioannidis,\u00a0S., 2020. Learn-Prune-Share for lifelong learning. In: Proc. IEEE Int. Conf. Data Mining. ICDM, pp. 641\u2013650.","DOI":"10.1109\/ICDM50108.2020.00073"},{"key":"10.1016\/j.cviu.2026.104798_b51","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Y., Ma,\u00a0Z., Huang,\u00a0Z., Wang,\u00a0Y., Su,\u00a0Z., Hong,\u00a0X., 2023. Isolation and impartial aggregation: A paradigm of incremental learning without interference. In: Proc. AAAI Conf. Artif. Intell.. pp. 10209\u201310217.","DOI":"10.1609\/aaai.v37i8.26216"},{"key":"10.1016\/j.cviu.2026.104798_b52","article-title":"Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality","volume":"vol. 36","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104798_b53","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Z., Zhang,\u00a0Z., Ebrahimi,\u00a0S., Sun,\u00a0R., Zhang,\u00a0H., Lee,\u00a0C.-Y., Ren,\u00a0X., Su,\u00a0G., Perot,\u00a0V., Dy,\u00a0J., Pfister,\u00a0T., 2022a. DualPrompt: Complementary prompting for rehearsal-free continual learning. In: Proc. Eur. Conf. Comput. Vis.. ECCV, pp. 139\u2013149.","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"10.1016\/j.cviu.2026.104798_b54","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Z., Zhang,\u00a0Z., Lee,\u00a0C.-Y., Zhang,\u00a0H., Sun,\u00a0R., Ren,\u00a0X., Su,\u00a0G., Perot,\u00a0V., Dy,\u00a0J., Pfister,\u00a0T., 2022b. Learning to prompt for continual learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 139\u2013149.","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"10.1016\/j.cviu.2026.104798_b55","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0F.-Y., Zhou,\u00a0D.-W., Ye,\u00a0H.-J., Zhan,\u00a0D.-C., 2022. FOSTER: Feature boosting and compression for class-incremental learning. In: Proc. Eur. Conf. Comput. Vis.. ECCV, pp. 398\u2013414.","DOI":"10.1007\/978-3-031-19806-9_23"},{"key":"10.1016\/j.cviu.2026.104798_b56","doi-asserted-by":"crossref","unstructured":"Yan,\u00a0S., Xie,\u00a0J., He,\u00a0X., 2021. DER: Dynamically expandable representation for class incremental learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 3014\u20133023.","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"10.1016\/j.cviu.2026.104798_b57","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.aiopen.2024.01.004","article-title":"CPT: Colorful prompt tuning for pre-trained vision-language models","volume":"5","author":"Yao","year":"2024","journal-title":"AI Open"},{"key":"10.1016\/j.cviu.2026.104798_b58","article-title":"COLA: Context-aware language-driven test-time adaptation","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104798_b59","series-title":"Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need","author":"Zhou","year":"2024"},{"key":"10.1016\/j.cviu.2026.104798_b60","doi-asserted-by":"crossref","unstructured":"Zhou,\u00a0D.-W., Sun,\u00a0H.-L., Ye,\u00a0H.-J., Zhan,\u00a0D.-C., 2024b. Expandable subspace ensemble for pre-trained model-based class-incremental learning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.. pp. 23554\u201323564.","DOI":"10.1109\/CVPR52733.2024.02223"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001657?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001657?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:22:57Z","timestamp":1783099377000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":60,"alternative-id":["S1077314226001657"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104798","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PSM: Prompt specialization module for prompt-based continual learning","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104798","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104798"}}