{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T05:43:53Z","timestamp":1777787033593,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62202217"],"award-info":[{"award-number":["62202217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023AI515012889"],"award-info":[{"award-number":["2023AI515012889"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Key Program","award":["2021QN02X794"],"award-info":[{"award-number":["2021QN02X794"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tvcg.2025.3634257","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:42:26Z","timestamp":1763750546000},"page":"615-625","source":"Crossref","is-referenced-by-count":0,"title":["VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9339-1941","authenticated-orcid":false,"given":"Huanchen","family":"Wang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wencheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4007-7873","authenticated-orcid":false,"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7761-6351","authenticated-orcid":false,"given":"Zhicong","family":"Lu","sequence":"additional","affiliation":[{"name":"George Mason University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0484-668X","authenticated-orcid":false,"given":"Yuxin","family":"Ma","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.02072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2798607"},{"key":"ref5","first-page":"65","article-title":"METEOR: An automatic metric for MT eval-uation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop","author":"Banerjee","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9071152"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2020.2969185"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3326588"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3138933"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2020.2973258"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3282258"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3456150"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2021.3071405"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2020.3028976"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref19","author":"DeVries","year":"2017","journal-title":"Improved regularization of convolutional neural networks with cutout"},{"key":"ref20","first-page":"4356","article-title":"How should pre-trained language models be fine-tuned towards adversarial robustness?","volume-title":"Proc. NeurIPS","volume":"34","author":"Dong","year":"2021"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00463"},{"key":"ref24","article-title":"Domino: Discovering systematic errors with cross-modal embeddings","volume-title":"Proc. ICLR","author":"Eyuboglu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00463"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01731"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01610"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw58289.2023.00042"},{"key":"ref29","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. ICLR","author":"Hendrycks","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01501"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3114683"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129167"},{"key":"ref34","article-title":"Adversarial machine learning at scale","volume-title":"Proc. ICLR","author":"Kurakin","year":"2017"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","volume":"202","author":"Li","year":"2023"},{"key":"ref36","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","volume":"162","author":"Li","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cisai54367.2021.00078"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3388514"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3261935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref43","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop","author":"Lin","year":"2004"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. NeurIPS","volume":"36","author":"Liu","year":"2023"},{"key":"ref46","first-page":"16363","article-title":"Detecting backdoors during the inference stage based on corruption ro-bustness consistency","volume-title":"Proc. CVPR","author":"Liu","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3270479"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2019.2934631"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/icdmw.2017.12"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref53","first-page":"3571","article-title":"On interaction between augmentations and corruptions in natural corruption robustness","volume-title":"Proc. NeurIPS","volume":"34","author":"Mintun","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref55","article-title":"Benchmarking robustness of multimodal image-text models under distri-bution shift","author":"Qiu","year":"2024","journal-title":"Journal of Data-centric Machine Learning Research"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","volume":"139","author":"Radford","year":"2021"},{"key":"ref57","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners"},{"key":"ref58","first-page":"5402","article-title":"Auto-matic data augmentation for generalization in reinforcement learning","volume-title":"Proc. NeurIPS","volume":"34","author":"Raileanu","year":"2021"},{"key":"ref59","first-page":"8594","article-title":"Visualizing and measuring the geometry of bert","volume-title":"Proc. NeurIPS","volume":"32","author":"Reif","year":"2019"},{"key":"ref60","first-page":"34405","article-title":"Robustness analysis of video-language models against visual and language pertur-bations","volume-title":"Proc. NeurIPS","volume":"35","author":"Schiappa","year":"2022"},{"key":"ref61","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adap-tation","volume-title":"Proc. NeurIPS","volume":"33","author":"Schneider","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.74"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3243676"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3148210"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32869"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_13"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3546644"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3535896"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3345340"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0393-x"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3327163"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00612"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3209465"},{"key":"ref82","first-page":"54111","article-title":"On evaluating adversarial robustness of large vision-language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Zhao","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/icdmw60847.2023.00023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11373125\/11264374.pdf?arnumber=11264374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:49:11Z","timestamp":1777492151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":83,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3634257","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}