{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:30Z","timestamp":1777889130086,"version":"3.51.4"},"reference-count":84,"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\/iccv51701.2025.00406","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4264-4274","source":"Crossref","is-referenced-by-count":0,"title":["DIP: Unsupervised Dense In-Context Post-Training of Visual Representations"],"prefix":"10.1109","author":[{"given":"Sophia","family":"Sirko-Galouchenko","sequence":"first","affiliation":[{"name":"Valeo.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spyros","family":"Gidaris","sequence":"additional","affiliation":[{"name":"Valeo.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonin","family":"Vobecky","sequence":"additional","affiliation":[{"name":"Valeo.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei","family":"Bursuc","sequence":"additional","affiliation":[{"name":"Valeo.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Thome","sequence":"additional","affiliation":[{"name":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2020","journal-title":"ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref3","article-title":"Towards in-context scene understanding","author":"Bala\u017eevi\u0107","year":"2023","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2022","journal-title":"ICLR"},{"key":"ref5","article-title":"Efros. Visual prompting via image inpainting","author":"Bar","year":"2022","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Vicreg: Variance-invariance-covariance regularization for selfsupervised learning","author":"Bardes","year":"2022","journal-title":"ICLR"},{"key":"ref7","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00019"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref15","article-title":"Diffcut: Catalyzing zero-shot semantic segmentation with diffusion features and recursive normalized cut","author":"Couairon","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Vision transformers need registers","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref18","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref20","article-title":"Modelagnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00676"},{"key":"ref25","article-title":"Moca: Self-supervised representation learning by predicting masked online codebook assignments","author":"Gidaris","year":"2024","journal-title":"TMLR"},{"key":"ref26","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Progressive knowledge distillation of stable diffusion xl using layer level loss","author":"Gupta","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","author":"Hamilton","year":"2022","journal-title":"ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02094"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_8"},{"key":"ref35","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Milan: Masked image pretraining on language assisted representation","author":"Hou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462533"},{"key":"ref41","article-title":"Dino-foresight: Looking into the future with dino","author":"Karypidis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref44","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref45","article-title":"Smooseg: smoothness prior for unsupervised semantic segmentation","author":"Lan","year":"2024","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Cribo: Selfsupervised learning via cross-image object-level bootstrapping","author":"Lebailly","year":"2024","journal-title":"ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00692"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref50","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2018","journal-title":"ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref53","article-title":"Unsupervised learning of dense visual representations","author":"Pinheiro","year":"2020","journal-title":"NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref55","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"TMLR"},{"key":"ref56","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref57","author":"Pariza","year":"2024","journal-title":"Hummingbird evaluation for vision encoders"},{"key":"ref58","article-title":"Near, far:Patch-ordering enhances vision foundation models\u2019 scene understanding","author":"Pariza","year":"2025","journal-title":"ICLR"},{"key":"ref59","article-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref61","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref62","article-title":"Optimization as a model for few-shot learning","author":"Ravi","year":"2017","journal-title":"ICLR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01516"},{"key":"ref65","article-title":"Meta-learning with memory-augmented neural networks","author":"Santoro","year":"2016","journal-title":"ICML"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01872"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref68","article-title":"No train, all gain: Self-supervised gradients improve deep frozen representations","author":"Simoncini","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00452"},{"key":"ref70","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00676"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref74","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref75","article-title":"Franca: Nested matryoshka clustering for scalable visual representation learning","author":"Venkataramanan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"NeurIPS"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02320-3"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref83","article-title":"ibot: Image bert pre-training with online tokenizer","author":"Zhou","year":"2022","journal-title":"ICLR"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01410"}],"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\/11444832.pdf?arnumber=11444832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:44Z","timestamp":1777612064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00406","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}