{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:29:06Z","timestamp":1781587746107,"version":"3.54.5"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"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":[[2024,9,18]]},"DOI":"10.1109\/cbmi62980.2024.10859215","type":"proceedings-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T18:30:52Z","timestamp":1738693852000},"page":"1-8","source":"Crossref","is-referenced-by-count":9,"title":["Is CLIP the main roadblock for fine-grained open-world perception?"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3519-2991","authenticated-orcid":false,"given":"Lorenzo","family":"Bianchi","sequence":"first","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5014-5089","authenticated-orcid":false,"given":"Fabio","family":"Carrara","sequence":"additional","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3011-2487","authenticated-orcid":false,"given":"Nicola","family":"Messina","sequence":"additional","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6258-5313","authenticated-orcid":false,"given":"Fabrizio","family":"Falchi","sequence":"additional","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Arandjelovi\u0107","year":"2023","journal-title":"Three ways to improve feature alignment for open vocabulary detection"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02125"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref6","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks","author":"Darkhalil","year":"2022"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01369"},{"key":"ref9","author":"Faghri","year":"2018","journal-title":"Vse++: Improving visual-semantic embeddings with hard negatives"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","author":"Gu","year":"2022","journal-title":"Open-vocabulary object detection via vision and language knowledge distillation"},{"key":"ref12","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.241"},{"key":"ref15","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref18","first-page":"32","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549576"},{"key":"ref22","author":"Minderer","year":"2023","journal-title":"Scaling openvocabulary object detection"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"PMLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413269"},{"key":"ref31","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","volume-title":"International Conference on Learning Representations","author":"Su","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref36","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"event":{"name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Reykjavik, Iceland","start":{"date-parts":[[2024,9,18]]},"end":{"date-parts":[[2024,9,20]]}},"container-title":["2024 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10858870\/10858871\/10859215.pdf?arnumber=10859215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T05:54:06Z","timestamp":1741067646000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10859215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/cbmi62980.2024.10859215","relation":{},"subject":[],"published":{"date-parts":[[2024,9,18]]}}}