{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:32:51Z","timestamp":1777887171012,"version":"3.51.4"},"reference-count":268,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010909","name":"Excellent Young Scientists Fund","doi-asserted-by":"publisher","award":["2024HWYQ-027"],"award-info":[{"award-number":["2024HWYQ-027"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF124"],"award-info":[{"award-number":["ZR2023QF124"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009108","name":"Shandong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406177"],"award-info":[{"award-number":["62406177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.cviu.2026.104679","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T16:56:22Z","timestamp":1771433782000},"page":"104679","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Recent advances of local mechanisms in vision foundation models: A survey and outlook"],"prefix":"10.1016","volume":"265","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3707-1761","authenticated-orcid":false,"given":"Qiangchang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104679_b1","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b2","doi-asserted-by":"crossref","unstructured":"Akiva,\u00a0P., Purri,\u00a0M., Leotta,\u00a0M., 2022. Self-supervised material and texture representation learning for remote sensing tasks. In: CVPR. pp. 8203\u20138215.","DOI":"10.1109\/CVPR52688.2022.00803"},{"key":"10.1016\/j.cviu.2026.104679_b3","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b4","doi-asserted-by":"crossref","unstructured":"Antol,\u00a0S., Agrawal,\u00a0A., Lu,\u00a0J., Mitchell,\u00a0M., Batra,\u00a0D., Zitnick,\u00a0C., Parikh,\u00a0D., 2015. Vqa: Visual question answering. In: ICCV. pp. 2425\u20132433.","DOI":"10.1109\/ICCV.2015.279"},{"key":"10.1016\/j.cviu.2026.104679_b5","doi-asserted-by":"crossref","unstructured":"Arar,\u00a0M., Shamir,\u00a0A., Bermano,\u00a0A., 2022. Learned queries for efficient local attention. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01057"},{"key":"10.1016\/j.cviu.2026.104679_b6","doi-asserted-by":"crossref","unstructured":"Astruc,\u00a0G., Gonthier,\u00a0N., Mallet,\u00a0C., Landrieu,\u00a0L., 2025. Anysat: One earth observation model for many resolutions, scales, and modalities. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 19530\u201319540.","DOI":"10.1109\/CVPR52734.2025.01819"},{"key":"10.1016\/j.cviu.2026.104679_b7","doi-asserted-by":"crossref","unstructured":"Ayush,\u00a0K., Uzkent,\u00a0B., Meng,\u00a0C., Tanmay,\u00a0K., Burke,\u00a0M., Lobell,\u00a0D., Ermon,\u00a0S., 2021. Geography-aware self-supervised learning. In: ICCV. pp. 10181\u201310190.","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"10.1016\/j.cviu.2026.104679_b8","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.cviu.2026.104679_b9","doi-asserted-by":"crossref","unstructured":"Bai,\u00a0Y., Chen,\u00a0X., Kirillov,\u00a0A., Yuille,\u00a0A., Berg,\u00a0A., 2022. Point-level region contrast for object detection pre-training. In: CVPR. pp. 16061\u201316070.","DOI":"10.1109\/CVPR52688.2022.01559"},{"key":"10.1016\/j.cviu.2026.104679_b10","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2018","journal-title":"T-PAMI"},{"key":"10.1016\/j.cviu.2026.104679_b11","series-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b12","unstructured":"Bao,\u00a0H., Dong,\u00a0L., Piao,\u00a0S., Wei,\u00a0F., 2022. BEit: BERT pre-training of image transformers. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b13","series-title":"NeurIPS","article-title":"VICRegl: Self-supervised learning of local visual features","author":"Bardes","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b14","doi-asserted-by":"crossref","unstructured":"Bastani,\u00a0F., Wolters,\u00a0P., Gupta,\u00a0R., Ferdinando,\u00a0J., Kembhavi,\u00a0A., 2023. Satlaspretrain: A large-scale dataset for remote sensing image understanding. In: ICCV. pp. 16772\u201316782.","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"10.1016\/j.cviu.2026.104679_b15","series-title":"ICML","first-page":"3974","article-title":"Improving fine-grained understanding in image-text pre-training","author":"Bica","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b16","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b17","unstructured":"Cai,\u00a0H., Gan,\u00a0C., Han,\u00a0S., 2023. Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition. In: CVPR."},{"key":"10.1016\/j.cviu.2026.104679_b18","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b19","doi-asserted-by":"crossref","unstructured":"Caron,\u00a0M., Touvron,\u00a0H., Misra,\u00a0I., J\u00e9gou,\u00a0H., Mairal,\u00a0J., Bojanowski,\u00a0P., Joulin,\u00a0A., 2021. Emerging properties in self-supervised vision transformers. In: ICCV. pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10.1016\/j.cviu.2026.104679_b20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3465055","article-title":"An attentive survey of attention models","volume":"12","author":"Chaudhari","year":"2021","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"10.1016\/j.cviu.2026.104679_b21","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume":"34","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b22","series-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.cviu.2026.104679_b23","series-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"10.1016\/j.cviu.2026.104679_b24","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0S., Li,\u00a0B., 2022. Multi-modal dynamic graph transformer for visual grounding. In: CVPR. pp. 15534\u201315543.","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"10.1016\/j.cviu.2026.104679_b25","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0M., Lin,\u00a0M., Li,\u00a0K., Shen,\u00a0Y., Wu,\u00a0Y., Chao,\u00a0F., Cf-vit,\u00a0R., 2023b. A general coarse-to-fine method for vision transformer. In: AAAI.","DOI":"10.1609\/aaai.v37i6.25860"},{"key":"10.1016\/j.cviu.2026.104679_b26","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0K., Liu,\u00a0Z., Hong,\u00a0L., Xu,\u00a0H., Li,\u00a0Z., Yeung,\u00a0D., 2023a. Mixed autoencoder for self-supervised visual representation learning. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"10.1016\/j.cviu.2026.104679_b27","unstructured":"Chen,\u00a0C., Panda,\u00a0R., Fan,\u00a0Q., 2022a. Regionvit: Regional-to-local attention for vision transformers. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b28","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0B., Rouditchenko,\u00a0A., Duarte,\u00a0K., Kuehne,\u00a0H., Thomas,\u00a0S., Boggust,\u00a0A., Panda,\u00a0R., Kingsbury,\u00a0B., Feris,\u00a0R., Harwath,\u00a0D., et al., 2021a. Multimodal clustering networks for self-supervised learning from unlabeled videos. In: ICCV. pp. 8012\u20138021.","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"10.1016\/j.cviu.2026.104679_b29","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0J., Sun,\u00a0S., He,\u00a0J., Torr,\u00a0P., Yuille,\u00a0A., Bai,\u00a0S., 2022b. Transmix: Attend to mix for vision transformers. In: CVPR. pp. 12135\u201312144.","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"10.1016\/j.cviu.2026.104679_b30","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0L., Zhang,\u00a0Y., Song,\u00a0Y., Liu,\u00a0L., Wang,\u00a0J., 2022c. Self-supervised learning of adversarial example: Towards good generalizations for deepfake detection. In: CVPR. pp. 18710\u201318719.","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"10.1016\/j.cviu.2026.104679_b31","series-title":"NeurIPS","article-title":"Tokenmixup: Efficient attention-guided token-level data augmentation for transformers","author":"Choi","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b32","article-title":"Unsupervised part discovery from contrastive reconstruction","volume":"34","author":"Choudhury","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b33","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b34","doi-asserted-by":"crossref","unstructured":"Ci,\u00a0Y., Lin,\u00a0C., Bai,\u00a0L., Ouyang,\u00a0W., 2022. Fast-moco: Boost momentum-based contrastive learning with combinatorial patches. In: ECCV.","DOI":"10.1007\/978-3-031-19809-0_17"},{"key":"10.1016\/j.cviu.2026.104679_b35","first-page":"197","article-title":"Satmae: Pre-training transformers for temporal and multi-spectral satellite imagery","volume":"35","author":"Cong","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b36","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/nrn755","article-title":"Control of goal-directed and stimulus-driven attention in the brain","volume":"3","author":"Corbetta","year":"2002","journal-title":"Nature Rev. Neurosci."},{"key":"10.1016\/j.cviu.2026.104679_b37","series-title":"CVPR","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.cviu.2026.104679_b38","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.cviu.2026.104679_b39","doi-asserted-by":"crossref","unstructured":"Deng,\u00a0J., Guo,\u00a0J., Xue,\u00a0N., Zafeiriou,\u00a0S., 2019. Arcface: Additive angular margin loss for deep face recognition. In: CVPR. pp. 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"10.1016\/j.cviu.2026.104679_b40","doi-asserted-by":"crossref","unstructured":"Deng,\u00a0J., Yang,\u00a0Z., Chen,\u00a0T., Zhou,\u00a0W., Li,\u00a0H., 2021. Transvg: End-to-end visual grounding with transformers. In: ICCV. pp. 1769\u20131779.","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"10.1016\/j.cviu.2026.104679_b41","unstructured":"Diao,\u00a0S., Zhou,\u00a0W., Zhang,\u00a0X., Wang,\u00a0J., 2023. Write and paint: Generative vision-language models are unified modal learners. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b42","series-title":"ECCV","first-page":"74","article-title":"Davit: Dual attention vision transformers","author":"Ding","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b43","doi-asserted-by":"crossref","unstructured":"Donahue,\u00a0G., Elhamifar,\u00a0E., 2024. Learning to predict activity progress by self-supervised video alignment. In: CVPR. pp. 18667\u201318677.","DOI":"10.1109\/CVPR52733.2024.01766"},{"key":"10.1016\/j.cviu.2026.104679_b44","doi-asserted-by":"crossref","unstructured":"Dong,\u00a0X., Bao,\u00a0J., Chen,\u00a0D., Zhang,\u00a0W., Yu,\u00a0N., Yuan,\u00a0L., Chen,\u00a0D., Guo,\u00a0B., 2022. Cswin transformer: A general vision transformer backbone with cross-shaped windows. In: CVPR. pp. 12124\u201312134.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"10.1016\/j.cviu.2026.104679_b45","unstructured":"Dosovitskiy,\u00a0A., Beyer,\u00a0L., Kolesnikov,\u00a0A., Weissenborn,\u00a0D., Zhai,\u00a0X., Unterthiner,\u00a0T., Dehghani,\u00a0M., Minderer,\u00a0M., Heigold,\u00a0G., Gelly,\u00a0S., et al., 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b46","series-title":"NeurIPS","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","author":"Dou","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b47","doi-asserted-by":"crossref","unstructured":"Dou,\u00a0Z., Xu,\u00a0Y., Gan,\u00a0Z., Wang,\u00a0J., Wang,\u00a0S., Wang,\u00a0L., Zhu,\u00a0C., Zhang,\u00a0P., Yuan,\u00a0L., Peng,\u00a0N., et al., 2022b. An empirical study of training end-to-end vision-and-language transformers. In: CVPR. pp. 18166\u201318176.","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"10.1016\/j.cviu.2026.104679_b48","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"IJCV"},{"key":"10.1016\/j.cviu.2026.104679_b49","unstructured":"Fang,\u00a0Y., Dong,\u00a0L., Bao,\u00a0H., Wang,\u00a0X., Wei,\u00a0F., 2023. Corrupted image modeling for self-supervised visual pre-training. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b50","doi-asserted-by":"crossref","unstructured":"Fang,\u00a0Z., Wang,\u00a0J., Hu,\u00a0X., Liang,\u00a0L., Gan,\u00a0Z., Wang,\u00a0L., Yang,\u00a0Y., Liu,\u00a0Z., 2022. Injecting semantic concepts into end-to-end image captioning. In: CVPR. pp. 18009\u201318019.","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"10.1016\/j.cviu.2026.104679_b51","doi-asserted-by":"crossref","unstructured":"Fayyaz,\u00a0M., Koohpayegani,\u00a0S., Rezaei,\u00a0F., Gall,\u00a0S., 2022. Adaptive token sampling for efficient vision transformers. In: ECCV.","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"10.1016\/j.cviu.2026.104679_b52","article-title":"Monarch mixer: A simple sub-quadratic gemm-based architecture","volume":"36","author":"Fu","year":"2024","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b53","series-title":"NeurIPS","article-title":"MCMAE: Masked convolution meets masked autoencoders","author":"Gao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b54","doi-asserted-by":"crossref","unstructured":"Gao,\u00a0L., Nie,\u00a0D., Li,\u00a0B., Ren,\u00a0X., 2022a. Doubly-fused vit: Fuse information from vision transformer doubly with local representation. In: ECCV.","DOI":"10.1007\/978-3-031-20050-2_43"},{"key":"10.1016\/j.cviu.2026.104679_b55","unstructured":"Gao,\u00a0H., Qian,\u00a0K., Ni,\u00a0J., Gan,\u00a0C., Hasegawa-Johnson,\u00a0M., Chang,\u00a0S., Zhang,\u00a0Y., 2024a. Speech self-supervised learning using diffusion model synthetic data. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b56","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"509","article-title":"Desam: Decoupled segment anything model for generalizable medical image segmentation","author":"Gao","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b57","doi-asserted-by":"crossref","unstructured":"Ge,\u00a0Y., Ge,\u00a0Y., Liu,\u00a0X., Li,\u00a0D., Shan,\u00a0Y., Qie,\u00a0X., Luo,\u00a0P., 2022. Bridging video-text retrieval with multiple choice questions. In: CVPR. pp. 16167\u201316176.","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"10.1016\/j.cviu.2026.104679_b58","first-page":"4193","article-title":"Revitalizing cnn attention via transformers in self-supervised visual representation learning","volume":"34","author":"Ge","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b59","doi-asserted-by":"crossref","unstructured":"Goyal,\u00a0Y., Khot,\u00a0T., Summers-Stay,\u00a0D., Batra,\u00a0D., Parikh,\u00a0D., 2017. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In: CVPR. pp. 6904\u20136913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"10.1016\/j.cviu.2026.104679_b60","series-title":"AAAI","first-page":"1959","article-title":"Self-supervised representation learning with meta comprehensive regularization","author":"Guo","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b61","doi-asserted-by":"crossref","unstructured":"Guo,\u00a0X., Lao,\u00a0J., Dang,\u00a0B., Zhang,\u00a0Y., Yu,\u00a0L., Ru,\u00a0L., Zhong,\u00a0L., Huang,\u00a0Z., Wu,\u00a0K., Hu,\u00a0D., et al., 2024b. Skysense: A multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery. In: CVPR. pp. 27672\u201327683.","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"10.1016\/j.cviu.2026.104679_b62","doi-asserted-by":"crossref","unstructured":"Guo,\u00a0Y., Sun,\u00a0S., Ma,\u00a0S., Zheng,\u00a0K., Bao,\u00a0X., Ma,\u00a0S., Zou,\u00a0W., Zheng,\u00a0Y., 2024c. Crossmae: Cross-modality masked autoencoders for region-aware audio-visual pre-training. In: CVPR. pp. 26721\u201326731.","DOI":"10.1109\/CVPR52733.2024.02523"},{"key":"10.1016\/j.cviu.2026.104679_b63","article-title":"Cross-domain foundation model adaptation: Pioneering computer vision models for geophysical data analysis","volume":"2","author":"Guo","year":"2025","journal-title":"J. Geophys. Res.: Mach. Learn. Comput."},{"key":"10.1016\/j.cviu.2026.104679_b64","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: A survey","volume":"8","author":"Guo","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.cviu.2026.104679_b65","doi-asserted-by":"crossref","unstructured":"Gupta,\u00a0A., Dollar,\u00a0P., Girshick,\u00a0R., 2019. Lvis: A dataset for large vocabulary instance segmentation. In: CVPR. pp. 5356\u20135364.","DOI":"10.1109\/CVPR.2019.00550"},{"key":"10.1016\/j.cviu.2026.104679_b66","article-title":"In-context symmetries: Self-supervised learning through contextual world models","author":"Gupta","year":"2024","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b67","doi-asserted-by":"crossref","unstructured":"Haghighi,\u00a0F., Taher,\u00a0M., Gotway,\u00a0M., Liang,\u00a0J., 2022. Dira: Discriminative, restorative, and adversarial learning for self-supervised medical image analysis. In: CVPR. pp. 20824\u201320834.","DOI":"10.1109\/CVPR52688.2022.02016"},{"key":"10.1016\/j.cviu.2026.104679_b68","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE T-PAMI"},{"key":"10.1016\/j.cviu.2026.104679_b69","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b70","doi-asserted-by":"crossref","unstructured":"Han,\u00a0B., Zhang,\u00a0S., Shi,\u00a0X., Reichstein,\u00a0M., 2024. Bridging remote sensors with multisensor geospatial foundation models. In: CVPR. pp. 27852\u201327862.","DOI":"10.1109\/CVPR52733.2024.02631"},{"key":"10.1016\/j.cviu.2026.104679_b71","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102417","article-title":"Visual attention methods in deep learning: An in-depth survey","volume":"108","author":"Hassanin","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.cviu.2026.104679_b72","series-title":"ECCV","first-page":"37","article-title":"Diffit: Diffusion vision transformers for image generation","author":"Hatamizadeh","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b73","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Chen,\u00a0X., Xie,\u00a0S., Li,\u00a0Y., Doll\u00e1r,\u00a0P., Girshick,\u00a0R., 2022. Masked autoencoders are scalable vision learners. In: CVPR. pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.cviu.2026.104679_b74","series-title":"NeurIPS","article-title":"Preventing dimensional collapse in self-supervised learning via orthogonality regularization","author":"He","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b75","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Gkioxari,\u00a0G., Doll\u00e1r,\u00a0P., Girshick,\u00a0R., 2017. Mask r-cnn. In: ICCV. pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.cviu.2026.104679_b76","unstructured":"He,\u00a0Z., Yang,\u00a0Y., Chen,\u00a0P., Xu,\u00a0Q., Ho,\u00a0T., 2024b. Be your own neighborhood: Detecting adversarial example by the neighborhood relations built on self-supervised learning. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b77","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., Sun,\u00a0J., 2016. Deep residual learning for image recognition. In: CVPR. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.cviu.2026.104679_b78","series-title":"How to represent part-whole hierarchies in a neural network","author":"Hinton","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b79","doi-asserted-by":"crossref","unstructured":"Hu,\u00a0H., Cui,\u00a0J., Wang,\u00a0L., 2021. Region-aware contrastive learning for semantic segmentation. In: ICCV. pp. 16291\u201316301.","DOI":"10.1109\/ICCV48922.2021.01598"},{"key":"10.1016\/j.cviu.2026.104679_b80","article-title":"Unsupervised domain adaptation with hierarchical masked dual-adversarial network for end-to-end classification of multisource remote sensing data","author":"Hu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104679_b81","unstructured":"Hu, L., Liu, Y., Liu, N., Huai, M., Sun, L., Wang, D., 2024. Improving interpretation faithfulness for vision transformers. ICML."},{"key":"10.1016\/j.cviu.2026.104679_b82","unstructured":"Huang,\u00a0L., Qiu,\u00a0Q., Sapiro,\u00a0G., 2025. Ssole: Rethinking orthogonal low-rank embedding for self-supervised learning. In: The Thirteenth International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104679_b83","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0L., You,\u00a0S., Zheng,\u00a0M., Wang,\u00a0F., Qian,\u00a0C., Yamasaki,\u00a0T., 2022b. Learning where to learn in cross-view self-supervised learning. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01405"},{"key":"10.1016\/j.cviu.2026.104679_b84","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0Z., Zeng,\u00a0Z., Huang,\u00a0Y., Liu,\u00a0B., Fu,\u00a0D., Fu,\u00a0J., 2021. Seeing out of the box: End-to-end pre-training for vision-language representation learning. In: CVPR. pp. 12976\u201312985.","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"10.1016\/j.cviu.2026.104679_b85","series-title":"NeurIPS","article-title":"Orthogonal transformer: An efficient vision transformer backbone with token orthogonalization","author":"Huang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b86","doi-asserted-by":"crossref","unstructured":"Hung,\u00a0W., Jampani,\u00a0V., Liu,\u00a0S., Molchanov,\u00a0P., Yang,\u00a0M., Kautz,\u00a0J., 2019. Scops: Self-supervised co-part segmentation. In: CVPR. pp. 869\u2013878.","DOI":"10.1109\/CVPR.2019.00096"},{"key":"10.1016\/j.cviu.2026.104679_b87","series-title":"ECCV","first-page":"434","article-title":"Nerf-mae: Masked autoencoders for self-supervised 3d representation learning for neural radiance fields","author":"Irshad","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b88","article-title":"All tokens matter: Token labeling for training better vision transformers","volume":"34","author":"Jiang","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b89","doi-asserted-by":"crossref","unstructured":"Jin,\u00a0X., Zhang,\u00a0B., Gong,\u00a0W., Xu,\u00a0K., Deng,\u00a0X., Wang,\u00a0P., Zhang,\u00a0Z., Shen,\u00a0X., Feng,\u00a0J., 2024. Mv-adapter: Multimodal video transfer learning for video text retrieval. In: CVPR. pp. 27134\u201327143.","DOI":"10.1109\/CVPR52733.2024.02563"},{"key":"10.1016\/j.cviu.2026.104679_b90","doi-asserted-by":"crossref","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","article-title":"Self-supervised visual feature learning with deep neural networks: A survey","volume":"43","author":"Jing","year":"2020","journal-title":"TPAMI"},{"key":"10.1016\/j.cviu.2026.104679_b91","unstructured":"Jing,\u00a0S., Yu,\u00a0A., Zhang,\u00a0S., Zhang,\u00a0S., 2024. Fedsc: Provable federated self-supervised learning with spectral contrastive objective over non-i.i.d. data. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b92","doi-asserted-by":"crossref","first-page":"eaaw4325","DOI":"10.1126\/science.aaw4325","article-title":"Memory engrams: Recalling the past and imagining the future","volume":"367","author":"Josselyn","year":"2020","journal-title":"Science"},{"key":"10.1016\/j.cviu.2026.104679_b93","series-title":"ECCV","first-page":"300","article-title":"What to hide from your students: Attention-guided masked image modeling","author":"Kakogeorgiou","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b94","doi-asserted-by":"crossref","unstructured":"Kang,\u00a0W., Liu,\u00a0G., Shah,\u00a0M., Yan,\u00a0Y., 2024a. Segvg: Transferring object bounding box to segmentation for visual grounding. In: ECCV.","DOI":"10.1007\/978-3-031-72920-1_4"},{"key":"10.1016\/j.cviu.2026.104679_b95","series-title":"Visual grounding with attention-driven constraint balancing","author":"Kang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b96","unstructured":"Kenton,\u00a0J., Toutanova,\u00a0L., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT. pp. 4171\u20134186."},{"key":"10.1016\/j.cviu.2026.104679_b97","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.cviu.2026.104679_b98","doi-asserted-by":"crossref","unstructured":"Kim,\u00a0S., Jo,\u00a0D., Lee,\u00a0D., Kim,\u00a0J., 2023. Magvlt: Masked generative vision-and-language transformer. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.02235"},{"key":"10.1016\/j.cviu.2026.104679_b99","series-title":"ICML","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b100","series-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"10.1016\/j.cviu.2026.104679_b101","doi-asserted-by":"crossref","unstructured":"Kirillov,\u00a0A., Mintun,\u00a0E., Ravi,\u00a0N., Mao,\u00a0H., Rolland,\u00a0C., Gustafson,\u00a0L., Xiao,\u00a0T., Whitehead,\u00a0S., Berg,\u00a0A., Lo,\u00a0W., et al., 2023. Segment anything. In: ICCV. pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.cviu.2026.104679_b102","doi-asserted-by":"crossref","unstructured":"Konwer,\u00a0A., Yang,\u00a0Z., Bas,\u00a0E., Xiao,\u00a0C., Prasanna,\u00a0P., Bhatia,\u00a0P., Kass-Hout,\u00a0T., 2025. Enhancing sam with efficient prompting and preference optimization for semi-supervised medical image segmentation. In: CVPR. pp. 20990\u201321000.","DOI":"10.1109\/CVPR52734.2025.01955"},{"key":"10.1016\/j.cviu.2026.104679_b103","series-title":"NeurIPS","article-title":"Learning to merge tokens via decoupled embedding for efficient vision transformers","author":"Lee","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b104","unstructured":"Lee,\u00a0K., Sim,\u00a0Y., Cho,\u00a0H., Eo,\u00a0M., Yoon,\u00a0S., Yoon,\u00a0S., Lim,\u00a0W., 2024b. Binning as a pretext task: Improving self-supervised learning in tabular domains. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b105","series-title":"ICML","first-page":"27094","article-title":"STELLA: Continual audio-video pre-training with SpatioTemporal localized alignment","author":"Lee","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b106","doi-asserted-by":"crossref","unstructured":"Leng,\u00a0Y., Jin,\u00a0R., Chen,\u00a0Y., Han,\u00a0Z., Shi,\u00a0L., Peng,\u00a0J., Yang,\u00a0L., Xiao,\u00a0J., Xiong,\u00a0D., 2025. Praetor: A fine-grained generative llm evaluator with instance-level customizable evaluation criteria. In: ACL. pp. 10386\u201310418.","DOI":"10.18653\/v1\/2025.acl-long.513"},{"key":"10.1016\/j.cviu.2026.104679_b107","first-page":"1","article-title":"Geographical knowledge-driven representation learning for remote sensing images","volume":"60","author":"Li","year":"2021","journal-title":"IEEE TGRS"},{"key":"10.1016\/j.cviu.2026.104679_b108","article-title":"Mst: Masked self-supervised transformer for visual representation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b109","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Y., Fan,\u00a0H., Hu,\u00a0R., Feichtenhofer,\u00a0C., He,\u00a0K., 2023c. Scaling language-image pre-training via masking. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"10.1016\/j.cviu.2026.104679_b110","doi-asserted-by":"crossref","unstructured":"Li,\u00a0T., Foo,\u00a0L., Hu,\u00a0P., Shang,\u00a0X., Rahmani,\u00a0H., Yuan,\u00a0Z., Liu,\u00a0J., 2023a. Token boosting for robust self-supervised visual transformer pre-training. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.02301"},{"key":"10.1016\/j.cviu.2026.104679_b111","doi-asserted-by":"crossref","unstructured":"Li,\u00a0W., Gao,\u00a0C., Niu,\u00a0G., Xiao,\u00a0X., Liu,\u00a0H., Liu,\u00a0J., Wu,\u00a0H., Wang,\u00a0H., 2021c. Unimo: Towards unified-modal understanding and generation via cross-modal contrastive learning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). pp. 2592\u20132607.","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"10.1016\/j.cviu.2026.104679_b112","first-page":"1","article-title":"Global and local contrastive self-supervised learning for semantic segmentation of hr remote sensing images","volume":"60","author":"Li","year":"2022","journal-title":"IEEE TGRS"},{"key":"10.1016\/j.cviu.2026.104679_b113","article-title":"Stitching, fine-tuning, re-training: A sam-enabled framework for semi-supervised 3d medical image segmentation","author":"Li","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.cviu.2026.104679_b114","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b115","doi-asserted-by":"crossref","unstructured":"Li,\u00a0G., Wei,\u00a0Y., Tian,\u00a0Y., Xu,\u00a0C., Wen,\u00a0J., Hu,\u00a0D., 2022a. Learning to answer questions in dynamic audio-visual scenarios. In: CVPR. pp. 19108\u201319118.","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"10.1016\/j.cviu.2026.104679_b116","doi-asserted-by":"crossref","unstructured":"Li,\u00a0W., Xie,\u00a0J., Loy,\u00a0C., 2023b. Correlational image modeling for self-supervised visual pre-training. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.01450"},{"key":"10.1016\/j.cviu.2026.104679_b117","series-title":"ECCV","first-page":"306","article-title":"Genview: Enhancing view quality with pretrained generative model for self-supervised learning","author":"Li","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b118","series-title":"NeurIPS","article-title":"Resource-aware federated self-supervised learning with global class representations","author":"Li","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b119","doi-asserted-by":"crossref","unstructured":"Li,\u00a0L., Zhang,\u00a0P., Zhang,\u00a0H., Yang,\u00a0J., Li,\u00a0C., Zhong,\u00a0Y., Wang,\u00a0L., Yuan,\u00a0L., Zhang,\u00a0L., Hwang,\u00a0J., et al., 2022d. Grounded language-image pre-training. In: CVPR. pp. 10965\u201310975.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"10.1016\/j.cviu.2026.104679_b120","series-title":"NeurIPS","article-title":"SemMAE: Semantic-guided masking for learning masked autoencoders","author":"Li","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b121","doi-asserted-by":"crossref","unstructured":"Li,\u00a0X., Zhou,\u00a0Y., Zhang,\u00a0Y., Zhang,\u00a0A., Wang,\u00a0W., Jiang,\u00a0N., Wu,\u00a0H., Wang,\u00a0W., 2021d. Dense semantic contrast for self-supervised visual representation learning. In: ACM MM. pp. 1368\u20131376.","DOI":"10.1145\/3474085.3475551"},{"key":"10.1016\/j.cviu.2026.104679_b122","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Z., Zhu,\u00a0Y., Chen,\u00a0Z., Gao,\u00a0Z., Zhao,\u00a0R., Zhao,\u00a0C., Tang,\u00a0M., Wang,\u00a0J., 2024c. Self-supervised representation learning from arbitrary scenarios. In: CVPR. pp. 22967\u201322977.","DOI":"10.1109\/CVPR52733.2024.02167"},{"key":"10.1016\/j.cviu.2026.104679_b123","unstructured":"Liang,\u00a0Y., Chongjian,\u00a0G., Tong,\u00a0Z., Song,\u00a0Y., Wang,\u00a0J., Xie,\u00a0P., 2022b. Evit: Expediting vision transformers via token reorganizations. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b124","doi-asserted-by":"crossref","unstructured":"Liang,\u00a0T., Lin,\u00a0G., Wan,\u00a0M., Li,\u00a0T., Ma,\u00a0G., Lv,\u00a0F., 2022a. Expanding large pre-trained unimodal models with multimodal information injection for image-text multimodal classification. In: CVPR. pp. 15492\u201315501.","DOI":"10.1109\/CVPR52688.2022.01505"},{"key":"10.1016\/j.cviu.2026.104679_b125","doi-asserted-by":"crossref","unstructured":"Liao,\u00a0G., Li,\u00a0J., Ye,\u00a0X., 2024. Vlm2scene: Self-supervised image-text-lidar learning with foundation models for autonomous driving scene understanding. In: AAAI. pp. 3351\u20133359.","DOI":"10.1609\/aaai.v38i4.28121"},{"key":"10.1016\/j.cviu.2026.104679_b126","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0T., Doll\u00e1r,\u00a0P., Girshick,\u00a0R., He,\u00a0K., Hariharan,\u00a0B., Belongie,\u00a0S., 2017a. Feature pyramid networks for object detection. In: CVPR. pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.cviu.2026.104679_b127","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0T., Goyal,\u00a0P., Girshick,\u00a0R., He,\u00a0K., Doll\u00e1r,\u00a0P., 2017b. Focal loss for dense object detection. In: ICCV. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.cviu.2026.104679_b128","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0K., Li,\u00a0L., Lin,\u00a0C., Ahmed,\u00a0F., Gan,\u00a0Z., Liu,\u00a0Z., Lu,\u00a0Y., Wang,\u00a0L., 2022. Swinbert: End-to-end transformers with sparse attention for video captioning. In: CVPR. pp. 17949\u201317958.","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"10.1016\/j.cviu.2026.104679_b129","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.cviu.2026.104679_b130","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0Y., Wang,\u00a0S., Nan,\u00a0L., Kooij,\u00a0J., Caesar,\u00a0H., 2025b. Voteflow: Enforcing local rigidity in self-supervised scene flow. In: CVPR 2025.","DOI":"10.1109\/CVPR52734.2025.01599"},{"key":"10.1016\/j.cviu.2026.104679_b131","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0L., Yu,\u00a0X., Pang,\u00a0Z., Wang,\u00a0Y., 2025a. Glus: Global-local reasoning unified into a single large language model for video segmentation. In: CVPR. pp. 8658\u20138667.","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"10.1016\/j.cviu.2026.104679_b132","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0H., Jiang,\u00a0X., Li,\u00a0X., Bao,\u00a0Z., Jiang,\u00a0D., Ren,\u00a0B., 2022a. Nommer: Nominate synergistic context in vision transformer for visual recognition. In: CVPR. pp. 12073\u201312082.","DOI":"10.1109\/CVPR52688.2022.01176"},{"key":"10.1016\/j.cviu.2026.104679_b133","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0Z., Lin,\u00a0Y., Cao,\u00a0Y., Hu,\u00a0H., Wei,\u00a0Y., Zhang,\u00a0Z., Lin,\u00a0S., Guo,\u00a0B., 2021b. Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.cviu.2026.104679_b134","series-title":"Tokenmix: Rethinking image mixing for data augmentation in vision transformers","author":"Liu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b135","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0J., Tang,\u00a0D., Huang,\u00a0Y., Zhang,\u00a0L., Zeng,\u00a0X., Li,\u00a0D., Lu,\u00a0M., Peng,\u00a0J., Wang,\u00a0Y., Jiang,\u00a0F., et al., 2024a. Updp: A unified progressive depth pruner for cnn and vision transformer. In: AAAI. pp. 13891\u201313899.","DOI":"10.1609\/aaai.v38i12.29296"},{"key":"10.1016\/j.cviu.2026.104679_b136","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0J., Teshome,\u00a0W., Ghimire,\u00a0S., Sznaier,\u00a0M., Camps,\u00a0O., 2024b. Solving masked jigsaw puzzles with diffusion vision transformers. In: CVPR. pp. 23009\u201323018.","DOI":"10.1109\/CVPR52733.2024.02171"},{"key":"10.1016\/j.cviu.2026.104679_b137","article-title":"Self-supervised learning: Generative or contrastive","author":"Liu","year":"2021","journal-title":"IEEE T-KDE"},{"key":"10.1016\/j.cviu.2026.104679_b138","doi-asserted-by":"crossref","unstructured":"Long,\u00a0J., Shelhamer,\u00a0E., Darrell,\u00a0T., 2015. Fully convolutional networks for semantic segmentation. In: CVPR. pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.cviu.2026.104679_b139","doi-asserted-by":"crossref","unstructured":"Lu,\u00a0H., Fei,\u00a0N., Huo,\u00a0Y., Gao,\u00a0Y., Lu,\u00a0Z., Wen,\u00a0J., 2022. Cots: Collaborative two-stream vision-language pre-training model for cross-modal retrieval. In: CVPR. pp. 15692\u201315701.","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"10.1016\/j.cviu.2026.104679_b140","unstructured":"Lu,\u00a0Z., Wang,\u00a0Z., Huang,\u00a0D., Wu,\u00a0C., Liu,\u00a0X., Ouyang,\u00a0W., Bai,\u00a0L., 2024. Fit: Flexible vision transformer for diffusion model. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b141","article-title":"Pattern integration and enhancement vision transformer for self-supervised learning in remote sensing","author":"Lu","year":"2025","journal-title":"IEEE TGRS"},{"key":"10.1016\/j.cviu.2026.104679_b142","series-title":"ICML","first-page":"34038","article-title":"SycoCa: Symmetrizing contrastive captioners with attentive masking for multimodal alignment","author":"Ma","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b143","series-title":"ICML","first-page":"23498","article-title":"Csp: Self-supervised contrastive spatial pre-training for geospatial-visual representations","author":"Mai","year":"2023"},{"key":"10.1016\/j.cviu.2026.104679_b144","doi-asserted-by":"crossref","unstructured":"Mall,\u00a0U., Hariharan,\u00a0B., Bala,\u00a0K., 2023. Change-aware sampling and contrastive learning for satellite images. In: CVPR. pp. 5261\u20135270.","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"10.1016\/j.cviu.2026.104679_b145","doi-asserted-by":"crossref","unstructured":"Mao,\u00a0X., Qi,\u00a0G., Chen,\u00a0Y., Li,\u00a0X., Duan,\u00a0R., Ye,\u00a0S., He,\u00a0Y., Xue,\u00a0H., 2022. Towards robust vision transformer. In: CVPR. pp. 12042\u201312051.","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"10.1016\/j.cviu.2026.104679_b146","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1038\/nrn3492","article-title":"The contextual brain: implications for fear conditioning, extinction and psychopathology","volume":"14","author":"Maren","year":"2013","journal-title":"Nature Rev. Neurosci."},{"key":"10.1016\/j.cviu.2026.104679_b147","doi-asserted-by":"crossref","unstructured":"Mei,\u00a0Y., Fan,\u00a0Y., Zhou,\u00a0Y., 2021. Image super-resolution with non-local sparse attention. In: CVPR. pp. 3517\u20133526.","DOI":"10.1109\/CVPR46437.2021.00352"},{"key":"10.1016\/j.cviu.2026.104679_b148","article-title":"Adaptive medical topic learning for enhanced fine-grained cross-modal alignment in medical report generation","author":"Mei","year":"2025","journal-title":"IEEE TMM"},{"key":"10.1016\/j.cviu.2026.104679_b149","article-title":"Connecting joint-embedding predictive architecture with contrastive self-supervised learning","author":"Mo","year":"2024","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b150","series-title":"NeurIPS","article-title":"You don\u2019t need domain-specific data augmentations when scaling self-supervised learning","author":"Moutakanni","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b151","doi-asserted-by":"crossref","unstructured":"Noman,\u00a0M., Naseer,\u00a0M., Cholakkal,\u00a0H., Anwer,\u00a0R., Khan,\u00a0S., Khan,\u00a0F., 2024. Rethinking transformers pre-training for multi-spectral satellite imagery. In: CVPR. pp. 27811\u201327819.","DOI":"10.1109\/CVPR52733.2024.02627"},{"key":"10.1016\/j.cviu.2026.104679_b152","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen","year":"1996","journal-title":"Nature"},{"key":"10.1016\/j.cviu.2026.104679_b153","doi-asserted-by":"crossref","unstructured":"Pathak,\u00a0D., Krahenbuhl,\u00a0P., Donahue,\u00a0J., Darrell,\u00a0T., Efros,\u00a0A., 2016. Context encoders: Feature learning by inpainting. In: CVPR. pp. 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"key":"10.1016\/j.cviu.2026.104679_b154","doi-asserted-by":"crossref","unstructured":"Plummer,\u00a0B., Wang,\u00a0L., Cervantes,\u00a0C., Caicedo,\u00a0J., Hockenmaier,\u00a0J., Lazebnik,\u00a0S., 2015. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV. pp. 2641\u20132649.","DOI":"10.1109\/ICCV.2015.303"},{"key":"10.1016\/j.cviu.2026.104679_b155","series-title":"NeurIPS","article-title":"Adapting self-supervised vision transformers by probing attention-conditioned masking consistency","author":"Prabhu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b156","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b157","doi-asserted-by":"crossref","unstructured":"Ranasinghe,\u00a0K., Naseer,\u00a0M., Khan,\u00a0S., Khan,\u00a0F., Ryoo,\u00a0M., 2022. Self-supervised video transformer. In: CVPR. pp. 2874\u20132884.","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"10.1016\/j.cviu.2026.104679_b158","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b159","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b160","doi-asserted-by":"crossref","unstructured":"Ren,\u00a0S., Wang,\u00a0H., Gao,\u00a0Z., He,\u00a0S., Yuille,\u00a0A., Zhou,\u00a0Y., Xie,\u00a0C., 2022a. A simple data mixing prior for improving self-supervised learning. In: CVPR. pp. 14595\u201314604.","DOI":"10.1109\/CVPR52688.2022.01419"},{"key":"10.1016\/j.cviu.2026.104679_b161","doi-asserted-by":"crossref","unstructured":"Ren,\u00a0S., Zhou,\u00a0D., He,\u00a0S., Feng,\u00a0J., Wang,\u00a0X., 2022b. Shunted self-attention via multi-scale token aggregation. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"10.1016\/j.cviu.2026.104679_b162","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1080\/135062800394667","article-title":"The dynamic representation of scenes","volume":"7","author":"Rensink","year":"2000","journal-title":"Vis. Cogn."},{"key":"10.1016\/j.cviu.2026.104679_b163","doi-asserted-by":"crossref","unstructured":"Roh,\u00a0B., Shin,\u00a0W., Kim,\u00a0I., Kim,\u00a0S., 2021. Spatially consistent representation learning. In: CVPR. pp. 1144\u20131153.","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"10.1016\/j.cviu.2026.104679_b164","article-title":"Tokenlearner: Adaptive space-time tokenization for videos","volume":"34","author":"Ryoo","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b165","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b166","doi-asserted-by":"crossref","unstructured":"Sameni,\u00a0S., Kafle,\u00a0K., Tan,\u00a0H., Jenni,\u00a0S., 2024. Building vision-language models on solid foundations with masked distillation. In: CVPR. pp. 14216\u201314226.","DOI":"10.1109\/CVPR52733.2024.01348"},{"key":"10.1016\/j.cviu.2026.104679_b167","doi-asserted-by":"crossref","unstructured":"Schroff,\u00a0F., Kalenichenko,\u00a0D., Philbin,\u00a0J., 2015. Facenet: A unified embedding for face recognition and clustering. In: CVPR. pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10.1016\/j.cviu.2026.104679_b168","unstructured":"Seong,\u00a0H., Shim,\u00a0H., 2024. Self-supervised interpretable end-to-end learning via latent functional modularity. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b169","doi-asserted-by":"crossref","unstructured":"Shao,\u00a0S., Bai,\u00a0Y., Wang,\u00a0Y., Liu,\u00a0B., Liu,\u00a0B., 2024. Collaborative consortium of foundation models for open-world few-shot learning. In: AAAI. pp. 4740\u20134747.","DOI":"10.1609\/aaai.v38i5.28275"},{"key":"10.1016\/j.cviu.2026.104679_b170","doi-asserted-by":"crossref","unstructured":"Shi,\u00a0D., 2024. Transnext: Robust foveal visual perception for vision transformers. In: CVPR. pp. 17773\u201317783.","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"10.1016\/j.cviu.2026.104679_b171","series-title":"ICML","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","author":"Shi","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b172","series-title":"ECCV","first-page":"241","article-title":"Learning representation for multitask learning through self-supervised auxiliary learning","author":"Shin","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b173","doi-asserted-by":"crossref","unstructured":"Shvetsova,\u00a0N., Chen,\u00a0B., Rouditchenko,\u00a0A., Thomas,\u00a0S., Kingsbury,\u00a0B., Feris,\u00a0R., Harwath,\u00a0D., Glass,\u00a0J., Kuehne,\u00a0H., 2022. Everything at once-multi-modal fusion transformer for video retrieval. In: CVPR. pp. 20020\u201320029.","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"10.1016\/j.cviu.2026.104679_b174","unstructured":"Silva,\u00a0T., Pedrini,\u00a0H., Rivera,\u00a0A., 2024. Learning from memory: Non-parametric memory augmented self-supervised learning of visual features. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b175","doi-asserted-by":"crossref","unstructured":"Singh,\u00a0A., Hu,\u00a0R., Goswami,\u00a0V., Couairon,\u00a0G., Galuba,\u00a0W., Rohrbach,\u00a0M., Kiela,\u00a0D., 2022. Flava: A foundational language and vision alignment model. In: CVPR. pp. 15638\u201315650.","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"10.1016\/j.cviu.2026.104679_b176","series-title":"ECCV","first-page":"379","article-title":"The role of masking for efficient supervised knowledge distillation of vision transformers","author":"Son","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b177","series-title":"ECCV","first-page":"325","article-title":"Removing rows and columns of tokens in vision transformer enables faster dense prediction without retraining","author":"Su","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b178","unstructured":"Su,\u00a0W., Zhu,\u00a0X., Cao,\u00a0Y., Li,\u00a0B., Lu,\u00a0L., Wei,\u00a0F., Dai,\u00a0J., 2020. Vl-bert: Pre-training of generic visual-linguistic representations. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b179","series-title":"A corpus for reasoning about natural language grounded in photographs","author":"Suhr","year":"2018"},{"key":"10.1016\/j.cviu.2026.104679_b180","doi-asserted-by":"crossref","unstructured":"Suhr,\u00a0A., Zhou,\u00a0S., Zhang,\u00a0A., Zhang,\u00a0I., Bai,\u00a0H., Artzi,\u00a0Y., 2019. A corpus for reasoning about natural language grounded in photographs. In: Meeting of the Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1644"},{"key":"10.1016\/j.cviu.2026.104679_b181","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1109\/TBME.2015.2476337","article-title":"Photoplethysmography revisited: from contact to noncontact, from point to imaging","volume":"63","author":"Sun","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.cviu.2026.104679_b182","first-page":"1","article-title":"Ringmo: A remote sensing foundation model with masked image modeling","volume":"61","author":"Sun","year":"2022","journal-title":"IEEE TGRS"},{"key":"10.1016\/j.cviu.2026.104679_b183","doi-asserted-by":"crossref","unstructured":"Tang,\u00a0Y., Han,\u00a0K., Wang,\u00a0Y., Xu,\u00a0C., Guo,\u00a0J., Xu,\u00a0C., Tao,\u00a0D., 2022a. Patch slimming for efficient vision transformers. In: CVPR. pp. 12165\u201312174.","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"10.1016\/j.cviu.2026.104679_b184","doi-asserted-by":"crossref","unstructured":"Tang,\u00a0Y., Yang,\u00a0D., Li,\u00a0W., Roth,\u00a0H., Landman,\u00a0B., Xu,\u00a0D., Nath,\u00a0V., Hatamizadeh,\u00a0A., 2022b. Self-supervised pre-training of swin transformers for 3d medical image analysis. In: CVPR. pp. 20730\u201320740.","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"10.1016\/j.cviu.2026.104679_b185","series-title":"NeurIPS","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b186","series-title":"Galileo: Learning global & local features of many remote sensing modalities","author":"Tseng","year":"2025"},{"key":"10.1016\/j.cviu.2026.104679_b187","series-title":"Medical Imaging with Deep Learning","article-title":"Disruptive autoencoders: Leveraging low-level features for 3d medical image pre-training","author":"Valanarasu","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b188","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke,\u00a0W., Vandenhende,\u00a0S., Georgoulis,\u00a0S., Van\u00a0Gool,\u00a0L., 2021. Unsupervised semantic segmentation by contrasting object mask proposals. In: ICCV. pp. 10052\u201310062.","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"10.1016\/j.cviu.2026.104679_b189","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b190","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1126\/science.287.5456.1273","article-title":"Sparse coding and decorrelation in primary visual cortex during natural vision","volume":"287","author":"Vinje","year":"2000","journal-title":"Science"},{"key":"10.1016\/j.cviu.2026.104679_b191","series-title":"Efficient vision transformers with partial attention","author":"Vo","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b192","series-title":"ECCV","first-page":"1","article-title":"Decoupling common and unique representations for multimodal self-supervised learning","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b193","unstructured":"Wang,\u00a0Z., Chen,\u00a0Z., Li,\u00a0Y., Guo,\u00a0Y., Yu,\u00a0J., Gong,\u00a0M., Liu,\u00a0T., 2023b. Mosaic representation learning for self-supervised visual pre-training. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b194","doi-asserted-by":"crossref","first-page":"4534","DOI":"10.1109\/TIFS.2021.3109463","article-title":"Dsa-face: Diverse and sparse attentions for face recognition robust to pose variation and occlusion","volume":"16","author":"Wang","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.cviu.2026.104679_b195","article-title":"Weakmedsam: Weakly-supervised medical image segmentation via sam with sub-class exploration and prompt affinity mining","author":"Wang","year":"2025","journal-title":"IEEE TMI"},{"key":"10.1016\/j.cviu.2026.104679_b196","article-title":"Not all images are worth 16x16 words: Dynamic vision transformers with adaptive sequence length","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b197","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Z., Li,\u00a0Q., Zhang,\u00a0G., Wan,\u00a0P., Zheng,\u00a0W., Wang,\u00a0N., Gong,\u00a0M., Liu,\u00a0T., 2022c. Exploring set similarity for dense self-supervised representation learning. In: CVPR. pp. 16590\u201316599.","DOI":"10.1109\/CVPR52688.2022.01609"},{"key":"10.1016\/j.cviu.2026.104679_b198","series-title":"ECCV","first-page":"101","article-title":"On learning discriminative features from synthesized data for self-supervised fine-grained visual recognition","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b199","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0H., Tang,\u00a0Y., Wang,\u00a0Y., Guo,\u00a0J., Deng,\u00a0Z., Han,\u00a0K., 2023a. Masked image modeling with local multi-scale reconstruction. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"10.1016\/j.cviu.2026.104679_b200","series-title":"NeurIPS","article-title":"Referencing where to focus: Improving visual grounding with referential query","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b201","series-title":"Scaling efficient masked autoencoder learning on large remote sensing dataset","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b202","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0J., Wu,\u00a0Z., Chen,\u00a0J., Han,\u00a0X., Shrivastava,\u00a0A., Lim,\u00a0S., Jiang,\u00a0Y., 2022b. Objectformer for image manipulation detection and localization. In: CVPR. pp. 2364\u20132373.","DOI":"10.1109\/CVPR52688.2022.00240"},{"key":"10.1016\/j.cviu.2026.104679_b203","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0Q., Wu,\u00a0T., Zheng,\u00a0H., Guo,\u00a0G., 2020. Hierarchical pyramid diverse attention networks for face recognition. In: CVPR. pp. 8326\u20138335.","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"10.1016\/j.cviu.2026.104679_b204","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0W., Xie,\u00a0E., Li,\u00a0X., Fan,\u00a0D., Song,\u00a0K., Liang,\u00a0D., Lu,\u00a0T., Luo,\u00a0P., Shao,\u00a0L., 2021a. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: ICCV. pp. 568\u2013578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.cviu.2026.104679_b205","first-page":"1","article-title":"An empirical study of remote sensing pretraining","volume":"61","author":"Wang","year":"2022","journal-title":"IEEE TGRS"},{"key":"10.1016\/j.cviu.2026.104679_b206","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0X., Zhang,\u00a0R., Shen,\u00a0C., Kong,\u00a0T., Li,\u00a0L., 2021b. Dense contrastive learning for self-supervised visual pre-training. In: CVPR. pp. 3024\u20133033.","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"10.1016\/j.cviu.2026.104679_b207","doi-asserted-by":"crossref","unstructured":"Wei,\u00a0C., Fan,\u00a0H., Xie,\u00a0S., Wu,\u00a0C., Yuille,\u00a0A., Feichtenhofer,\u00a0C., 2022. Masked feature prediction for self-supervised visual pre-training. In: CVPR. pp. 14668\u201314678.","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"10.1016\/j.cviu.2026.104679_b208","series-title":"ECCV","first-page":"1","article-title":"Towards latent masked image modeling for self-supervised visual representation learning","author":"Wei","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b209","unstructured":"Wen,\u00a0Q., Ju,\u00a0M., Ouyang,\u00a0Z., Zhang,\u00a0C., Ye,\u00a0Y., 2024. From coarse to fine: Enable comprehensive graph self-supervised learning with multi-granular semantic ensemble. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b210","series-title":"NeurIPS","article-title":"Self-supervised visual representation learning with semantic grouping","author":"Wen","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b211","doi-asserted-by":"crossref","unstructured":"Wu,\u00a0H., Xiao,\u00a0B., Codella,\u00a0N., Liu,\u00a0M., Dai,\u00a0X., Yuan,\u00a0L., Zhang,\u00a0L., 2021. Cvt: Introducing convolutions to vision transformers. In: ICCV. pp. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"10.1016\/j.cviu.2026.104679_b212","doi-asserted-by":"crossref","unstructured":"Xia,\u00a0Z., Pan,\u00a0X., Song,\u00a0S., Li,\u00a0L., Huang,\u00a0G., 2022. Vision transformer with deformable attention. In: CVPR. pp. 4794\u20134803.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"10.1016\/j.cviu.2026.104679_b213","doi-asserted-by":"crossref","unstructured":"Xia,\u00a0C., Wang,\u00a0X., Lv,\u00a0F., Hao,\u00a0X., Shi,\u00a0Y., 2024. Vit-comer: Vision transformer with convolutional multi-scale feature interaction for dense predictions. In: CVPR. pp. 5493\u20135502.","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"10.1016\/j.cviu.2026.104679_b214","doi-asserted-by":"crossref","unstructured":"Xiao,\u00a0T., Reed,\u00a0C., Wang,\u00a0X., Keutzer,\u00a0K., Darrell,\u00a0T., 2021. Region similarity representation learning. In: ICCV. pp. 10539\u201310548.","DOI":"10.1109\/ICCV48922.2021.01037"},{"key":"10.1016\/j.cviu.2026.104679_b215","doi-asserted-by":"crossref","unstructured":"Xiao,\u00a0J., Zhou,\u00a0P., Chua,\u00a0T., Yan,\u00a0S., 2022. Video graph transformer for video question answering. In: ECCV.","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"10.1016\/j.cviu.2026.104679_b216","series-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"10.1016\/j.cviu.2026.104679_b217","unstructured":"Xie,\u00a0J., Li,\u00a0W., Zhan,\u00a0X., Liu,\u00a0Z., Ong,\u00a0Y., Loy,\u00a0C., 2023. Masked frequency modeling for self-supervised visual pre-training. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b218","doi-asserted-by":"crossref","unstructured":"Xie,\u00a0S., Lingjing,\u00a0L., Zheng,\u00a0Y., Yao,\u00a0Y., Tang,\u00a0Z., Xing,\u00a0E., Chen,\u00a0G., Zhang,\u00a0K., 2025. Smartclip: Modular vision-language alignment with identification guarantees. In: CVPR. pp. 29780\u201329790.","DOI":"10.1109\/CVPR52734.2025.02772"},{"key":"10.1016\/j.cviu.2026.104679_b219","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1109\/TPAMI.2022.3170559","article-title":"Self-supervised learning of graph neural networks: A unified review","volume":"45","author":"Xie","year":"2022","journal-title":"IEEE T-PAMI"},{"key":"10.1016\/j.cviu.2026.104679_b220","doi-asserted-by":"crossref","unstructured":"Xie,\u00a0Z., Zhang,\u00a0Z., Cao,\u00a0Y., Lin,\u00a0Y., Bao,\u00a0J., Yao,\u00a0Z., Dai,\u00a0Q., Hu,\u00a0H., 2022b. Simmim: A simple framework for masked image modeling. In: CVPR. pp. 9653\u20139663.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"10.1016\/j.cviu.2026.104679_b221","doi-asserted-by":"crossref","unstructured":"Xiong,\u00a0Y., Varadarajan,\u00a0B., Wu,\u00a0L., Xiang,\u00a0X., Xiao,\u00a0F., Zhu,\u00a0C., Dai,\u00a0X., Wang,\u00a0D., Sun,\u00a0F., Iandola,\u00a0F., et al., 2024. Efficientsam: Leveraged masked image pretraining for efficient segment anything. In: CVPR. pp. 16111\u201316121.","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"10.1016\/j.cviu.2026.104679_b222","series-title":"ICML","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.cviu.2026.104679_b223","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0J., Mei,\u00a0T., Yao,\u00a0T., Rui,\u00a0Y., 2016. Msr-vtt: A large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5288\u20135296.","DOI":"10.1109\/CVPR.2016.571"},{"key":"10.1016\/j.cviu.2026.104679_b224","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0Y., Zhang,\u00a0Z., Zhang,\u00a0M., Sheng,\u00a0K., Li,\u00a0K., Dong,\u00a0W., Zhang,\u00a0L., Xu,\u00a0C., Sun,\u00a0X., 2022b. Evo-vit: Slow-fast token evolution for dynamic vision transformer. In: AAAI.","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"10.1016\/j.cviu.2026.104679_b225","series-title":"Regioncl: Exploring contrastive region pairs for self-supervised representation learning","author":"Xu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b226","article-title":"Multimodal learning with transformers: A survey","author":"Xu","year":"2023","journal-title":"IEEE T-PAMI"},{"key":"10.1016\/j.cviu.2026.104679_b227","first-page":"1","article-title":"A multimodal vision foundation model for clinical dermatology","author":"Yan","year":"2025","journal-title":"Nature Med."},{"key":"10.1016\/j.cviu.2026.104679_b228","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0J., Duan,\u00a0J., Tran,\u00a0S., Xu,\u00a0Y., Chanda,\u00a0S., Chen,\u00a0L., Zeng,\u00a0B., Chilimbi,\u00a0T., Huang,\u00a0J., 2022b. Vision-language pre-training with triple contrastive learning. In: CVPR. pp. 15671\u201315680.","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"10.1016\/j.cviu.2026.104679_b229","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0C., Wang,\u00a0Y., Zhang,\u00a0J., Zhang,\u00a0H., Wei,\u00a0Z., Lin,\u00a0Z., Yuille,\u00a0A., 2022a. Lite vision transformer with enhanced self-attention. In: CVPR. pp. 11998\u201312008.","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"10.1016\/j.cviu.2026.104679_b230","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0L., Xu,\u00a0Y., Yuan,\u00a0C., Liu,\u00a0W., Li,\u00a0B., Hu,\u00a0W., 2022c. Improving visual grounding with visual-linguistic verification and iterative reasoning. In: CVPR. pp. 9499\u20139508.","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"10.1016\/j.cviu.2026.104679_b231","doi-asserted-by":"crossref","unstructured":"Ye,\u00a0X., Gan,\u00a0Y., Ge,\u00a0Y., Zhang,\u00a0X., Tang,\u00a0Y., 2025. Atp-llava: Adaptive token pruning for large vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 24972\u201324982.","DOI":"10.1109\/CVPR52734.2025.02325"},{"key":"10.1016\/j.cviu.2026.104679_b232","doi-asserted-by":"crossref","unstructured":"Ye,\u00a0Y., Xie,\u00a0Y., Zhang,\u00a0J., Chen,\u00a0Z., Wu,\u00a0Q., Xia,\u00a0Y., 2024. Continual self-supervised learning: Towards universal multi-modal medical data representation learning. In: CVPR. pp. 11114\u201311124.","DOI":"10.1109\/CVPR52733.2024.01057"},{"key":"10.1016\/j.cviu.2026.104679_b233","series-title":"NeurIPS","article-title":"Contrastive-equivariant self-supervised learning improves alignment with primate visual area IT","author":"Yerxa","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b234","doi-asserted-by":"crossref","unstructured":"Yin,\u00a0H., Vahdat,\u00a0A., Alvarez,\u00a0J., Mallya,\u00a0A., Kautz,\u00a0J., Molchanov,\u00a0P., 2021. Adavit: Adaptive tokens for efficient vision transformer. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"10.1016\/j.cviu.2026.104679_b235","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104230","article-title":"Open-set domain adaptation with visual-language foundation models","volume":"250","author":"Yu","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104679_b236","doi-asserted-by":"crossref","unstructured":"Yu,\u00a0W., Luo,\u00a0M., Zhou,\u00a0P., Si,\u00a0C., Zhou,\u00a0Y., Wang,\u00a0X., Feng,\u00a0J., Yan,\u00a0S., 2022. Metaformer is actually what you need for vision. In: CVPR. pp. 10819\u201310829.","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"10.1016\/j.cviu.2026.104679_b237","series-title":"ECCV","first-page":"69","article-title":"Modeling context in referring expressions","author":"Yu","year":"2016"},{"key":"10.1016\/j.cviu.2026.104679_b238","doi-asserted-by":"crossref","unstructured":"Yuan,\u00a0L., Chen,\u00a0Y., Wang,\u00a0T., Yu,\u00a0W., Shi,\u00a0Y., Jiang,\u00a0Z., Tay,\u00a0F., Feng,\u00a0J., Yan,\u00a0S., 2021b. Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: ICCV. pp. 558\u2013567.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"10.1016\/j.cviu.2026.104679_b239","doi-asserted-by":"crossref","unstructured":"Yuan,\u00a0K., Guo,\u00a0S., Liu,\u00a0Z., Zhou,\u00a0A., Yu,\u00a0F., Wu,\u00a0W., 2021a. Incorporating convolution designs into visual transformers. In: ICCV. pp. 579\u2013588.","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"10.1016\/j.cviu.2026.104679_b240","doi-asserted-by":"crossref","unstructured":"Yun,\u00a0S., Lee,\u00a0H., Kim,\u00a0J., Shin,\u00a0J., 2022. Patch-level representation learning for self-supervised vision transformers. In: CVPR. pp. 8354\u20138363.","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"10.1016\/j.cviu.2026.104679_b241","doi-asserted-by":"crossref","unstructured":"Yun,\u00a0S., Ro,\u00a0Y., 2024. Shvit: Single-head vision transformer with memory efficient macro design. In: CVPR. pp. 5756\u20135767.","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"10.1016\/j.cviu.2026.104679_b242","series-title":"ICCV","first-page":"2011","article-title":"Pano-avqa: Grounded audio-visual question answering on 360\u00b0videos","author":"Yun","year":"2021"},{"key":"10.1016\/j.cviu.2026.104679_b243","doi-asserted-by":"crossref","unstructured":"Zeng,\u00a0W., Jin,\u00a0S., Liu,\u00a0W., Qian,\u00a0C., Luo,\u00a0P., Ouyang,\u00a0W., Wang,\u00a0X., 2022. Not all tokens are equal: Human-centric visual analysis via token clustering transformer. In: CVPR. pp. 11101\u201311111.","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"10.1016\/j.cviu.2026.104679_b244","unstructured":"Zhang,\u00a0H., Cisse,\u00a0M., Dauphin,\u00a0Y., Lopez-Paz,\u00a0D., 2018. mixup: Beyond empirical risk minimization. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104679_b245","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0T., Qiu,\u00a0C., Ke,\u00a0W., S\u00fcsstrunk,\u00a0S., Salzmann,\u00a0M., 2022b. Leverage your local and global representations: A new self-supervised learning strategy. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01608"},{"key":"10.1016\/j.cviu.2026.104679_b246","unstructured":"Zhang,\u00a0Y., Tan,\u00a0Z., Yang,\u00a0J., Huang,\u00a0W., Yuan,\u00a0Y., 2024d. Matrix information theory for self-supervised learning. In: ICML."},{"key":"10.1016\/j.cviu.2026.104679_b247","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0M., Tseng,\u00a0C., Kreiman,\u00a0G., 2020. Putting visual object recognition in context. In: CVPR. pp. 12985\u201312994.","DOI":"10.1109\/CVPR42600.2020.01300"},{"key":"10.1016\/j.cviu.2026.104679_b248","series-title":"ECCV","first-page":"146","article-title":"Learning representations from foundation models for domain generalized stereo matching","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b249","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0C., Xu,\u00a0X., Wang,\u00a0L., Dai,\u00a0Z., Yang,\u00a0J., 2024a. S2wat: Image style transfer via hierarchical vision transformer using strips window attention. In: AAAI. pp. 7024\u20137032.","DOI":"10.1609\/aaai.v38i7.28529"},{"key":"10.1016\/j.cviu.2026.104679_b250","article-title":"Rest: An efficient transformer for visual recognition","volume":"34","author":"Zhang","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b251","series-title":"ICML","first-page":"60288","article-title":"MLIP: Efficient multi-perspective language-image pretraining with exhaustive data utilization","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b252","series-title":"NeurIPS","article-title":"GLIPv2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104679_b253","article-title":"Vision transformer with quadrangle attention","author":"Zhang","year":"2024","journal-title":"IEEE T-PAMI"},{"key":"10.1016\/j.cviu.2026.104679_b254","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0H., Zhou,\u00a0Y., Wang,\u00a0G., 2024b. Dense vision transformer compression with few samples. In: CVPR. pp. 15825\u201315834.","DOI":"10.1109\/CVPR52733.2024.01498"},{"key":"10.1016\/j.cviu.2026.104679_b255","doi-asserted-by":"crossref","unstructured":"Zhao,\u00a0Y., Wang,\u00a0G., Luo,\u00a0C., Zeng,\u00a0W., Zha,\u00a0Z., 2021. Self-supervised visual representations learning by contrastive mask prediction. In: ICCV. pp. 10160\u201310169.","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"10.1016\/j.cviu.2026.104679_b256","series-title":"MM","first-page":"1187","article-title":"Resvg: Enhancing relation and semantic understanding in multiple instances for visual grounding","author":"Zheng","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b257","series-title":"ECCV","first-page":"73","article-title":"Dreamlip: Language-image pre-training with long captions","author":"Zheng","year":"2024"},{"key":"10.1016\/j.cviu.2026.104679_b258","doi-asserted-by":"crossref","unstructured":"Zhong,\u00a0Y., Yang,\u00a0J., Zhang,\u00a0P., Li,\u00a0C., Codella,\u00a0N., Li,\u00a0L., Zhou,\u00a0L., Dai,\u00a0X., Yuan,\u00a0L., Li,\u00a0Y., et al., 2022. Regionclip: Region-based language-image pretraining. In: CVPR. pp. 16793\u201316803.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"10.1016\/j.cviu.2026.104679_b259","series-title":"AAAI","article-title":"Towards automatic learning of procedures from web instructional videos","author":"Zhou","year":"2018"},{"key":"10.1016\/j.cviu.2026.104679_b260","doi-asserted-by":"crossref","unstructured":"Zhou,\u00a0Z., Xu,\u00a0H., Shu,\u00a0Y., Liu,\u00a0L., 2024. Unlocking the potential of pre-trained vision transformers for few-shot semantic segmentation through relationship descriptors. In: CVPR. pp. 3817\u20133827.","DOI":"10.1109\/CVPR52733.2024.00366"},{"key":"10.1016\/j.cviu.2026.104679_b261","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"IJCV"},{"key":"10.1016\/j.cviu.2026.104679_b262","doi-asserted-by":"crossref","unstructured":"Zhu,\u00a0K., Guo,\u00a0H., Yan,\u00a0T., Zhu,\u00a0Y., Wang,\u00a0J., Tang,\u00a0M., 2022. Part-aware self-supervised pre-training for person re-identification. In: ECCV.","DOI":"10.1007\/978-3-031-19781-9_12"},{"key":"10.1016\/j.cviu.2026.104679_b263","first-page":"17723","article-title":"Long-short transformer: Efficient transformers for language and vision","volume":"34","author":"Zhu","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.cviu.2026.104679_b264","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1007\/s11263-024-02224-2","article-title":"Weakclip: Adapting clip for weakly-supervised semantic segmentation","volume":"133","author":"Zhu","year":"2025","journal-title":"IJCV"},{"key":"10.1016\/j.cviu.2026.104679_b265","doi-asserted-by":"crossref","unstructured":"Zhu,\u00a0L., Yang,\u00a0Y., 2020. Actbert: Learning global-local video-text representations. In: CVPR. pp. 8746\u20138755.","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"10.1016\/j.cviu.2026.104679_b266","article-title":"Mim: Mask in mask self-supervised pre-training for 3d medical image analysis","author":"Zhuang","year":"2025","journal-title":"IEEE TMI"},{"key":"10.1016\/j.cviu.2026.104679_b267","doi-asserted-by":"crossref","unstructured":"Zhuang,\u00a0C., Zhai,\u00a0A., Yamins,\u00a0D., 2019. Local aggregation for unsupervised learning of visual embeddings. In: ICCV. pp. 6002\u20136012.","DOI":"10.1109\/ICCV.2019.00610"},{"key":"10.1016\/j.cviu.2026.104679_b268","doi-asserted-by":"crossref","unstructured":"Ziegler,\u00a0A., Asano,\u00a0Y., 2022. Self-supervised learning of object parts for semantic segmentation. In: CVPR. pp. 14502\u201314511.","DOI":"10.1109\/CVPR52688.2022.01410"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000469?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000469?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:03:22Z","timestamp":1777608202000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":268,"alternative-id":["S1077314226000469"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104679","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Recent advances of local mechanisms in vision foundation models: A survey and outlook","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104679","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104679"}}