{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:01:01Z","timestamp":1784131261875,"version":"3.55.0"},"reference-count":65,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02045","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22025-22035","source":"Crossref","is-referenced-by-count":5,"title":["Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation"],"prefix":"10.1109","author":[{"given":"Luca","family":"Barsellotti","sequence":"first","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Bianchi","sequence":"additional","affiliation":[{"name":"ISTI-CNR,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Messina","sequence":"additional","affiliation":[{"name":"ISTI-CNR,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Carrara","sequence":"additional","affiliation":[{"name":"ISTI-CNR,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcella","family":"Cornia","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrizio","family":"Falchi","sequence":"additional","affiliation":[{"name":"ISTI-CNR,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00149"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"ref4","article-title":"Improving fine-grained understanding in imagetext pre-training","author":"Bica","year":"2024","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref6","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","article-title":"Vision Transformers Need Registers","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref14","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref15","author":"Everingham","year":"2012","journal-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref20","article-title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref23","article-title":"Diffusion Models for Zero-Shot OpenVocabulary Segmentation","author":"Karazija","year":"2024","journal-title":"ECCV"},{"key":"ref24","article-title":"Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials","author":"Kr\u00e4henb\u00fchl","year":"2011","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref27","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","article-title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","author":"Luo","year":"2023","journal-title":"ICML"},{"key":"ref33","article-title":"Scaling Open-Vocabulary Object Detection","author":"Minderer","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"ref37","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref40","article-title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","author":"Ren","year":"2023","journal-title":"ICLR"},{"key":"ref41","article-title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","author":"Shin","year":"2022","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref46","article-title":"A Closer Look at the Robustness of Contrastive Language-Image PreTraining (CLIP)","author":"Tu","year":"2023","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305122"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref57","article-title":"A Simple Baseline for OpenVocabulary Semantic Segmentation with Pre-trained VisionLanguage Model","author":"Xu","year":"2022","journal-title":"ECCV"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11443403.pdf?arnumber=11443403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:42Z","timestamp":1777530162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02045","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}