{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:40Z","timestamp":1763192020336,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229323","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models"],"prefix":"10.1109","author":[{"given":"Shaeke","family":"Salman","sequence":"first","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Montasir","family":"Shams","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Lingjiong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Mathematics,Tallahassee,Florida"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT 2019","author":"Devlin"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref3"},{"issue":"140","key":"ref4","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref5"},{"key":"ref6","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Henaff"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591723"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Bioformer: an efficient transformer language model for biomedical text mining","year":"2023","author":"Fang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref12"},{"year":"2023","key":"ref13","article-title":"Gpt-4 technical report"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","volume":"139","author":"Radford"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref16"},{"key":"ref17","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","year":"2021","author":"Jia","key":"ref18"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref22","article-title":"Exploring generalization in deep learning","author":"Neyshabur","year":"2017","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1459"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-4828"},{"key":"ref25","article-title":"Are aligned neural networks adversarially aligned?","author":"Carlini","year":"2023","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30150"},{"article-title":"Universal and transferable adversarial attacks on aligned language models","year":"2023","author":"Zou","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"article-title":"Understanding and improving robustness of vision transformers through patch-based negative augmentation","year":"2023","author":"Qin","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01471"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01306"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-33266-0"},{"article-title":"Intriguing equivalence structures of the embedding space of vision transformers","year":"2024","author":"Salman","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"article-title":"Openclip","year":"2021","author":"Ilharco","key":"ref37"},{"article-title":"Understanding zero-shot adversarial robustness for large-scale models","year":"2023","author":"Mao","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802618"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229323.pdf?arnumber=11229323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:46Z","timestamp":1763191846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229323","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}