{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:00:22Z","timestamp":1792166422556,"version":"4.4.0"},"reference-count":200,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFF1105104"],"award-info":[{"award-number":["2023YFF1105104"]}]},{"name":"National Key R&D Program of China","award":["2021ZD0111901"],"award-info":[{"award-number":["2021ZD0111901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2025"],"award-info":[{"award-number":["U21B2025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3672629","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:53:19Z","timestamp":1773172399000},"page":"8547-8566","source":"Crossref","is-referenced-by-count":5,"title":["A Survey on Interpretability in Visual Recognition"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2498-4499","authenticated-orcid":false,"given":"Qiyang","family":"Wan","sequence":"first","affiliation":[{"name":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengzhi","family":"Gao","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/ail2.60"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3495013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/21-SS133"},{"key":"ref5","article-title":"On the relationship between interpretability and explainability in machine learning","author":"Leblanc","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/a18090556"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00867-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10179-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3561048"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13200"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3100641"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"ref14","article-title":"Opportunities and challenges in explainable artificial intelligence (XAI): A survey","author":"Das","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103184"},{"issue":"2","key":"ref17","first-page":"11","article-title":"Building trustworthy multimodal AI: A review of fairness, transparency, and ethics in vision-language tasks","volume":"8","author":"Saleh","year":"2025","journal-title":"Int. J. Web Res."},{"key":"ref18","article-title":"A review of multimodal explainable artificial intelligence: Past, present and future","author":"Sun","year":"2024"},{"key":"ref19","article-title":"Explainable and interpretable multimodal large language models: A comprehensive survey","author":"Dang","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3467062"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/s25134166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2024.09.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104194"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3581136"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102303"},{"key":"ref27","article-title":"Attribution-based XAI methods in computer vision: A review","author":"Abhishek","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.09.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/computers13040092"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-026-21313-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3563691"},{"key":"ref32","article-title":"A systematic review of explainable artificial intelligence models and applications: Recent developments and future trends","volume":"7","author":"Saranya","year":"2023","journal-title":"Decis. Analytics J."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2024.3467001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.110786"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106668"},{"key":"ref37","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref40","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref42","article-title":"SmoothGrad: Removing noise by adding noise","author":"Smilkov","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93736-2_34"},{"key":"ref44","article-title":"Explaining classifiers with causal concept effect (CaCE)","author":"Goyal","year":"2019"},{"key":"ref45","first-page":"5338","article-title":"Concept bottleneck models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh","year":"2020"},{"key":"ref46","first-page":"8930","article-title":"This looks like that: Deep learning for interpretable image recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01469"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2982882"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_8"},{"key":"ref54","first-page":"23926","article-title":"DISSECT: Disentangled simultaneous explanations via concept traversals","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ghandeharioun","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01055"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00711-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01550"},{"key":"ref58","article-title":"Best of both worlds: Local and global explanations with human-understandable concepts","author":"Schrouff","year":"2021"},{"key":"ref59","first-page":"21826","article-title":"Explain any concept: Segment anything meets concept-based explanation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun","year":"2023"},{"key":"ref60","first-page":"6594","article-title":"Visualizing the emergence of intermediate visual patterns in DNNs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00353"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN64981.2025.11227842"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v7i1.5265"},{"key":"ref64","first-page":"25830","article-title":"Natural language descriptions of deep visual features","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hernandez","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00269"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00197"},{"key":"ref67","first-page":"39212","article-title":"This looks like those: Illuminating prototypical concepts using multiple visualizations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI59109.2023.00048"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref70","first-page":"5","article-title":"Interactive explanations of internal representations of neural network layers: An exploratory study on outcome prediction of comatose patients","volume-title":"Proc. 5th Int. Workshop Knowl. Discov. Healthcare Data","author":"Nauta","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00944"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3469288"},{"key":"ref73","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00265-z"},{"key":"ref76","first-page":"20554","article-title":"On completeness-aware concept-based explanations in deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yeh","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01294"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17389"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3167702"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01004"},{"key":"ref81","article-title":"ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features","author":"Ramaswamy","year":"2022"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110146"},{"key":"ref83","article-title":"UFO: A unified method for controlling understandability and faithfulness objectives in concept-based explanations for CNNs","author":"Ramaswamy","year":"2023"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"ref86","first-page":"9277","article-title":"Towards automatic concept-based explanations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ghorbani","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_17"},{"key":"ref89","article-title":"Revisiting the importance of individual units in CNNs via ablation","author":"Zhou","year":"2018"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1002\/ail2.55"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98131-4_6"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00481"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2954501"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00085"},{"key":"ref95","article-title":"Towards interpretable deep neural networks by leveraging adversarial examples","author":"Dong","year":"2017"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10924"},{"key":"ref97","article-title":"Unsupervised learning of neural networks to explain neural networks","author":"Zhang","year":"2018"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/409"},{"key":"ref99","article-title":"SegDiscover: Visual concept discovery via unsupervised semantic segmentation","author":"Huang","year":"2022"},{"key":"ref100","first-page":"1","article-title":"Visualising the training process of convolutional neural networks for non-experts","volume-title":"Proc. 31st Benelux Conf. Artif. Intell.","author":"Peters","year":"2019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3583558"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54024-5_6"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref104","first-page":"9245","article-title":"Beyond grids: Learning graph representations for visual recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00476"},{"key":"ref107","article-title":"Learn to explain yourself, when you can: Equipping concept bottleneck models with the ability to abstain on their concept predictions","author":"Lockhart","year":"2022"},{"key":"ref108","first-page":"22283","article-title":"Label-free concept bottleneck models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oikarinen","year":"2023"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/742"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2021.802938"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref112","article-title":"Conditional generative models for counterfactual explanations","author":"Looveren","year":"2021"},{"key":"ref113","first-page":"1488","article-title":"CounteRGAN: Generating counterfactuals for real-time recourse and interpretability using residual GANs","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Nemirovsky","year":"2022"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00996"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.825565"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-06329-8_17"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_10"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2510"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-32-396098-4.00008-9"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124710"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44064-9_21"},{"issue":"34","key":"ref122","first-page":"1","article-title":"Quantus: An explainable AI toolkit for responsible evaluation of neural network explanations and beyond","volume":"24","author":"Hedstr\u00f6m","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref123","article-title":"Unifying VXAI: A systematic review and framework for the evaluation of explainable AI","author":"Dembinsky","year":"2025"},{"key":"ref124","article-title":"Towards a unified evaluation of explanation methods without ground truth","author":"Zhang","year":"2019"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00163"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8080832"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90403-0_9"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1175\/aies-d-23-0074.1"},{"key":"ref129","first-page":"67106","article-title":"Navigating the maze of explainable AI: A systematic approach to evaluating methods and metrics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Klein","year":"2024"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3774643"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128111"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2599820"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref134","article-title":"RISE: Randomized input sampling for explanation of black-box models","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Petsiuk","year":"2018"},{"key":"ref135","article-title":"Benchmarking attribution methods with relative feature importance","author":"Yang","year":"2019"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6064"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559536"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.04.004"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450689"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467148"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501965"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.008"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref144","first-page":"19225","article-title":"Faithful vision-language interpretation via concept bottleneck models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lai","year":"2024"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01049"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref147","article-title":"Captum: A unified and generic model interpretability library for PyTorch","author":"Kokhlikyan","year":"2020"},{"key":"ref148","article-title":"Xplique: A deep learning explainability toolbox","author":"Fel","year":"2022"},{"key":"ref149","first-page":"1","article-title":"Synthetic benchmarks for scientific research in explainable machine learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Liu","year":"2021"},{"key":"ref150","article-title":"XAI benchmark for visual explanation","author":"Zhang","year":"2023"},{"key":"ref151","first-page":"8182","article-title":"LVLM-Intrepret: An interpretability tool for large vision-language models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Ben Melech Stan","year":"2024"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093360"},{"key":"ref154","first-page":"1","article-title":"Features understanding in 3D CNNs for actions recognition in video","volume-title":"Proc. 10th Int. Conf. Image Process. Theory Tools Appl.","author":"Fuad","year":"2020"},{"key":"ref155","article-title":"Use HiResCAM instead of grad-CAM for faithful explanations of convolutional neural networks","author":"Draelos","year":"2020"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.146"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP61759.2024.10743968"},{"key":"ref161","article-title":"CAMs as Shapley value-based explainers","author":"Cai","year":"2025"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00898"},{"key":"ref163","article-title":"Improving concept alignment in vision-language concept bottleneck models","author":"Selvaraj","year":"2024"},{"key":"ref164","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011","journal-title":"California Inst. Technol."},{"key":"ref165","article-title":"PyTorch library for CAM methods","author":"Gildenblat Contributors","year":"2021"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref168","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_8"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3403167"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85181-0_19"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0027"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01053"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01119"},{"key":"ref175","article-title":"Vision transformers with natural language semantics","author":"Kim","year":"2024"},{"key":"ref176","first-page":"25461","article-title":"Towards interpreting visual information processing in vision-language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Neo","year":"2025"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.60"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-8746-5_7"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.64"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21375"},{"key":"ref181","article-title":"Blocks as probes: Dissecting categorization ability of large multimodal models","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Fu","year":"2024"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01818"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412941"},{"key":"ref185","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu","year":"2020"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_56"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-14463-9_1"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-pathmechdis-051222-113147"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.3390\/s23020634"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1145\/3609333"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3146552"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12041020"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3287678"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-022-00926-7"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3204171"},{"key":"ref199","article-title":"GLEAMS: Bridging the gap between local and global explanations","author":"Visani","year":"2024"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-54605-1_24"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11427331.pdf?arnumber=11427331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:52:18Z","timestamp":1781034738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11427331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":200,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3672629","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":[[2026,7]]}}}