{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:20:01Z","timestamp":1778052001671,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00351","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3598-3605","source":"Crossref","is-referenced-by-count":0,"title":["Feature Inversion as a Lens on Vision Encoders"],"prefix":"10.1109","author":[{"given":"Eduard","family":"Allakhverdov","sequence":"first","affiliation":[{"name":"FusionBrain Lab,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitrii","family":"Tarasov","sequence":"additional","affiliation":[{"name":"FusionBrain Lab,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elizaveta","family":"Goncharova","sequence":"additional","affiliation":[{"name":"FusionBrain Lab,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"FusionBrain Lab,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref2","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref4","article-title":"Vision transformers need registers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Darcet"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-08317-3_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref8","article-title":"What do we learn from inverting clip models?","author":"Kazemi","year":"2024"},{"key":"ref9","author":"Kim","year":"2018","journal-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)"},{"key":"ref10","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00073"},{"key":"ref14","author":"Lim","year":"2025","journal-title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0911-8"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref19","author":"Sun","year":"2023","journal-title":"Eva-clip: Improved training techniques for clip at scale"},{"key":"ref20","author":"Thasarathan","year":"2025","journal-title":"Universal sparse autoencoders: Interpretable cross-model concept alignment"},{"key":"ref21","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1057\/9781137410405.0018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492189.pdf?arnumber=11492189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:38:19Z","timestamp":1778049499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00351","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}