{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:17Z","timestamp":1777865417533,"version":"3.51.4"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00852","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9113-9123","source":"Crossref","is-referenced-by-count":0,"title":["Not All Views Are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models"],"prefix":"10.1109","author":[{"given":"Mateusz Michalkiewicz Rice","family":"University","sequence":"first","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheena","family":"Bai","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahsa","family":"Baktashmotlagh","sequence":"additional","affiliation":[{"name":"The University of Queensland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guha","family":"Balakrishnan","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00498"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.94.2.115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01514"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"and Shan-Hung Brandon Wu","volume":"32","author":"Chen","year":"2019","journal-title":"Cnn\\^{}\\{2\\}: Viewpoint generalization via a binocular vision. Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"When vision transformers outperform resnets without pretraining or strong data augmentations","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"issue":"3","key":"ref8","first-page":"145","article-title":"and G\u00e9rard Medioni","volume":"10","author":"Chen","year":"1992","journal-title":"Object modelling by registration of multiple range images. Image and vision computing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref12","author":"Diederik","year":"2014","journal-title":"Adam: A method for stochastic optimization. (No Title)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2666"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3327"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref17","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/368542a0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00208721"},{"key":"ref20","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02283-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00437-5"},{"key":"ref29","article-title":"Understanding zero-shot adversarial robustness for large-scale models","author":"Mao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-018-0182-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1559"},{"key":"ref33","first-page":"2","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"issue":"3","key":"ref35","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Advances in large margin classifiers"},{"key":"ref36","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International Conference on Machine Learning. PMLR","author":"Radford"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00434"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_18"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref43","article-title":"Robust clip: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models","author":"Schlarmann","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1601883"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247698"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref48","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"A closer look at the robustness of contrastive language-image pre-training (clip)","volume":"36","author":"Tu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","first-page":"443","article-title":"Variants of the borda count method for combining ranked classifier hypotheses","volume-title":"In 7th International Workshop on frontiers in handwriting recognition","author":"Van Erp","year":"2000"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-084320-6.50022-0"},{"issue":"5","key":"ref53","first-page":"1095","article-title":"Radke","volume":"37","author":"Wu","year":"2014","journal-title":"Viewpoint invariant human re-identification in camera networks using pose priors and subject-discriminative features. IEEE transactions on pattern analysis and machine intelligence"},{"key":"ref54","first-page":"2","article-title":"Multiview equivariance improves 3d correspondence understanding with minimal feature finetuning","author":"You","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"and Geoffrey E Hinton","volume":"3","author":"Zemel","year":"1990","journal-title":"Discovering viewpoint-invariant relationships that characterize objects. Advances in neural information processing systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref57","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Ood-cv: A benchmark for robustness to individual nuisances in real-world out-of-distribution shifts","volume-title":"In ICML 2022 Shift Happens Workshop","author":"Zhao","year":"2022"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443511.pdf?arnumber=11443511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:29:54Z","timestamp":1777530594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00852","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}