{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:12:34Z","timestamp":1778530354105,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EU Projects ELIAS","award":["101120237"],"award-info":[{"award-number":["101120237"]}]},{"name":"ELLIOT","award":["101214398"],"award-info":[{"award-number":["101214398"]}]},{"name":"FAIR - Future AI Research","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3657989","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:59:22Z","timestamp":1769633962000},"page":"6127-6138","source":"Crossref","is-referenced-by-count":0,"title":["Vocabulary-Free Image Classification and Semantic Segmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3044-1320","authenticated-orcid":false,"given":"Alessandro","family":"Conti","sequence":"first","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1671-875X","authenticated-orcid":false,"given":"Enrico","family":"Fini","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8595-9955","authenticated-orcid":false,"given":"Massimiliano","family":"Mancini","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-5659","authenticated-orcid":false,"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5932-4371","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-1147","authenticated-orcid":false,"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref3","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref6","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2023"},{"key":"ref7","first-page":"71078","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Ma","year":"2023"},{"key":"ref8","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuo","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref16","article-title":"LAION-400M: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"Proc. NeurIPS Workshop Datacentric AI","author":"Schuhmann","year":"2021"},{"key":"ref17","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.218"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref21","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref23","article-title":"Improved baselines for vision-language pre-training","author":"Fini","year":"2023","journal-title":"TMLR"},{"key":"ref24","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng","year":"2022"},{"key":"ref25","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref28","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref32","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Guu","year":"2020"},{"key":"ref33","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Lewis","year":"2020"},{"key":"ref34","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Borgeaud","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00091"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref42","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bucher","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00113"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref47","first-page":"216","article-title":"BabelNet: Building a very large multilingual semantic network","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Navigli","year":"2010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref50","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref53","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","author":"Shu","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref58","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref64","article-title":"Automatically discovering and learning new visual categories with ranking statistics","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref66","article-title":"Web2 dictionary (revision 326913)","year":"2023"},{"key":"ref67","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref71","article-title":"RedCaps: Web-curated image-text data created by the people, for the people","author":"Desai","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref76","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref77","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref78","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref79","article-title":"Democratizing contrastive language-image pre-training: A clip benchmark of data, model, and supervision","author":"Cui","year":"2022."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11365986.pdf?arnumber=11365986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:46:33Z","timestamp":1778528793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3657989","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}