{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:54:41Z","timestamp":1777568081707,"version":"3.51.4"},"reference-count":149,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62320106010"],"award-info":[{"award-number":["62320106010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2042"],"award-info":[{"award-number":["U21B2042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376267"],"award-info":[{"award-number":["62376267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L253019"],"award-info":[{"award-number":["L253019"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2035 Innovation Program of CAS"},{"name":"InnoHK program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3654115","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:41Z","timestamp":1768510181000},"page":"5928-5944","source":"Crossref","is-referenced-by-count":1,"title":["Practical Continual Forgetting for Pre-Trained Vision Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4859-275X","authenticated-orcid":false,"given":"Hongbo","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3016-5538","authenticated-orcid":false,"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7160-5523","authenticated-orcid":false,"given":"Bolin","family":"Ni","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zhu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7103-6321","authenticated-orcid":false,"given":"Gaofeng","family":"Meng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-021-01301-1"},{"key":"ref2","article-title":"ImageNet roulette\u2013trevor paglen","author":"Paglen","year":"2020"},{"issue":"1","key":"ref3","article-title":"General Data Protection Regulation (GDPR)","volume":"24","author":"Regulation","year":"2018","journal-title":"Intersoft Consulting"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3211013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref6","article-title":"Certifiable machine unlearning for linear models","author":"Mahadevan","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-018-1772-4"},{"key":"ref9","first-page":"2008","article-title":"Approximate data deletion from machine learning models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Izzo"},{"key":"ref10","article-title":"Certified data removal from machine learning models","author":"Guo","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00932"},{"key":"ref12","first-page":"18075","article-title":"Remember what you want to forget: Algorithms for machine unlearning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sekhari"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref17","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01833"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02705"},{"key":"ref25","article-title":"Continual classification learning using generative models","author":"Lavda","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02279"},{"key":"ref29","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref30","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225117"},{"key":"ref33","article-title":"Diffusepast: Diffusion-based generative replay for class incremental semantic segmentation","author":"Chen","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref36","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schwarz"},{"key":"ref37","first-page":"14306","article-title":"Class-incremental learning via dual augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3568886"},{"key":"ref39","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3417431"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3510536"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.315"},{"key":"ref50","article-title":"MLLM-CL: Continual learning for multimodal large language models","author":"Zhao","year":"2025"},{"key":"ref51","article-title":"Measuring and regularizing networks in function space","author":"Benjamin","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.04.010"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02272"},{"key":"ref56","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3749987"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tetci.2024.3379240"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/137"},{"key":"ref60","first-page":"1092","article-title":"Machine unlearning for random forests","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brophy"},{"key":"ref61","article-title":"Making ai forget you: Data deletion in machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ginart"},{"issue":"6","key":"ref62","first-page":"7210","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Chundawat"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1109\/TIFS.2023.3265506","volume":"18","author":"Chundawat","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2026.113785"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06178-9"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6222-8_32"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.805"},{"key":"ref68","article-title":"Towards unbounded machine unlearning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kurmanji"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_6"},{"key":"ref70","article-title":"Model sparsity can simplify machine unlearning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28996"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266233"},{"key":"ref73","article-title":"Towards robust and parameter-efficient knowledge unlearning for LLMs","author":"Cha","year":"2024"},{"key":"ref74","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"issue":"8","key":"ref75","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref78","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref79","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref82","article-title":"Sam fails to segment anything?\u2013Sam-adapter: Adapting sam in underperformed scenes: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref84","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","author":"Zhang","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref88","article-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked languagemodels","author":"Ravfogel","year":"2021"},{"key":"ref89","article-title":"What would elsa do? Freezing layers during transformer fine-tuning","author":"Lee","year":"2019"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"ref91","article-title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","author":"Chavan","year":"2023"},{"key":"ref92","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.12.011"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109480"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref100","first-page":"195","article-title":"One-shot learning with a hierarchical nonparametric bayesian model","volume-title":"Proc. ICML Workshop Unsupervised Transfer Learn. JMLR Workshop Conf. Proc.","author":"Salakhutdinov"},{"key":"ref101","article-title":"Pattern recognition from one example by chopping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fleuret"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.142"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1868"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"ref108","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. ICML Deep Learn. Workshop","author":"Koch"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1201\/9781420034639-179"},{"key":"ref110","article-title":"Adapted deep embeddings: A synthesis of methods for k-shot inductive transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Scott"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143895"},{"key":"ref112","article-title":"Learning to remember rare events","author":"Kaiser","year":"2017"},{"key":"ref113","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref114","article-title":"Learning feed-forward one-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bertinetto"},{"key":"ref115","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.16"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.355"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_10"},{"key":"ref119","first-page":"983","article-title":"Low-shot learning via covariance-preserving adversarial augmentation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref121","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019956318069"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref124","first-page":"6642","article-title":"DetNAS: Backbone search for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363226"},{"key":"ref129","volume-title":"Information Theory and Statistics","author":"Kullback","year":"1997"},{"key":"ref130","article-title":"Learning face representation from scratch","author":"Yi","year":"2014"},{"key":"ref131","article-title":"Face transformer for recognition","author":"Zhong","year":"2021"},{"key":"ref132","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref133","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref134","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref136","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref138","first-page":"7377","article-title":"A single-loop smoothed gradient descent-ascent algorithm for nonconvex-concave min-max problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref139","first-page":"18613","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cubuk","year":"2020"},{"key":"ref140","article-title":"Locating and editing factual knowledge in GPT","author":"Meng","year":"2022"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.95"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.63317\/2igni6uj3xpq"},{"key":"ref145","first-page":"9446","article-title":"Deep image prior","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ulyanov"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1145\/3523273"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11353047.pdf?arnumber=11353047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:11Z","timestamp":1775505371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":149,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3654115","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}