{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T12:57:38Z","timestamp":1769777858674,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry for Transport (BMV), Germany","award":["01F2271A"],"award-info":[{"award-number":["01F2271A"]}]},{"DOI":"10.13039\/501100001838","name":"German Federal Ministry for Economic Affairs and Energy (BMWE), Germany","doi-asserted-by":"publisher","award":["01MJ22012D"],"award-info":[{"award-number":["01MJ22012D"]}],"id":[{"id":"10.13039\/501100001838","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2025.3649809","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:45:15Z","timestamp":1767206715000},"page":"13193-13201","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Explainability and Accuracy in CLIP for Object Recognition via Joint Probability Over Rationales and Categories"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6808-6730","authenticated-orcid":false,"given":"Ali","family":"Rasekh","sequence":"first","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3832-9236","authenticated-orcid":false,"given":"Sepehr","family":"Kazemi Ranjbar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milad","family":"Heidari Sorkhehdizaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2576-4640","authenticated-orcid":false,"given":"Simon","family":"Gottschalk","sequence":"additional","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Nejdl","sequence":"additional","affiliation":[{"name":"L3S Research Center, Leibniz University Hannover, Hanover, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076221074488"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3431437"},{"key":"ref4","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_35"},{"key":"ref10","article-title":"Explainable AI meets healthcare: A study on heart disease dataset","author":"Dave","year":"2020","journal-title":"arXiv:2011.03195"},{"key":"ref11","article-title":"Visual question answering: A survey on techniques and common trends in recent literature","author":"de Faria","year":"2023","journal-title":"arXiv:2305.11033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2478\/9788395669606-004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref17","article-title":"Explainable artificial intelligence approaches: A survey","author":"Islam","year":"2021","journal-title":"arXiv:2101.09429"},{"key":"ref18","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584078"},{"key":"ref21","first-page":"21487","article-title":"Generating images with multimodal language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Koh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref23","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref25","article-title":"Enhancing image retrieval: A comprehensive study on photo search using the CLIP mode","author":"Lahajal","year":"2024","journal-title":"arXiv:2401.13613"},{"key":"ref26","article-title":"Caltech 101","author":"Li","year":"2022","journal-title":"CaltechDATA"},{"key":"ref27","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref29","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"ref32","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_6"},{"key":"ref35","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref36","article-title":"RISE: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018","journal-title":"arXiv:1806.07421"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s44206-023-00081-z"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref44","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013","journal-title":"arXiv:1312.6034"},{"key":"ref45","first-page":"17365","article-title":"Salient ImageNet: How to discover spurious features in deep learning?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Singla"},{"key":"ref46","article-title":"SmoothGrad: Removing noise by adding noise","author":"Smilkov","year":"2017","journal-title":"arXiv:1706.03825"},{"key":"ref47","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. ICML","author":"Sundararajan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00142-y"},{"key":"ref51","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref53","article-title":"Parameter-efficient fine-tuning for pre-trained vision models: A survey and benchmark","author":"Xin","year":"2024","journal-title":"arXiv:2402.02242"},{"key":"ref54","article-title":"Where do large vision-language models look at when answering questions?","author":"Xing","year":"2025","journal-title":"arXiv:2503.13891"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32236-6_51"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12143142"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11320255.pdf?arnumber=11320255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:25:45Z","timestamp":1769721945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11320255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3649809","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}