{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:23Z","timestamp":1789207583655,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37335-9_14","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:10:03Z","timestamp":1789204203000},"page":"251-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SOCO: Benchmarking Semantic Object Correspondence in\u00a0Vision Foundation Models"],"prefix":"10.1007","author":[{"given":"Olaf","family":"D\u00fcnkel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basavaraj","family":"Sunagad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David T.","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Theobalt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Kortylewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS 35 (2022)","DOI":"10.52202\/068431-1723"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: CVPR, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"14_CR4","unstructured":"Aydemir, G., Xie, W., G\u00fcney, F.: Can visual foundation models achieve long-term point tracking? In: ECCV Workshops (2024)"},{"key":"14_CR5","unstructured":"Bai, J., et al.: Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"14_CR6","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL Technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"14_CR7","unstructured":"Bai, S., et al.: Qwen2.5-VL Technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"14_CR8","unstructured":"Baruch, G., et al.: ARKitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. arXiv preprint arXiv:2111.08897 (2021)"},{"key":"14_CR9","unstructured":"Bolya, D., et al.: Perception encoder: the best visual embeddings are not at the output of the network. arXiv preprint arXiv:2504.13181 (2025)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., Gkioxari, G.: Omni3D: a large benchmark and model for 3D object detection in the wild, CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: ECCV, pp. 611\u2013625 (2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"14_CR12","unstructured":"Cai, Z., Yeh, C.F., Xu, H., Liu, Z., Meyer, G., Lei, X., Zhao, C., Li, S.W., Chandra, V., Shi, Y.: DepthLM: Metric depth from vision language models. arXiv preprint arXiv:2509.25413 (2025)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers, p. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Chi, Y., et al.: C3PO: canonicalization of 3D pose from partial views with generalizable correspondence features. In: 3DV (2026)","DOI":"10.1109\/3DV69130.2026.00062"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding, pp. 3213\u20133223. CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: TAP-Vid: a benchmark for tracking any point in a video. In: NeurIPS, vol. 35, pp. 13610\u201313626 (2022)","DOI":"10.52202\/068431-0989"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"D\u00fcnkel, O., Jesslen, A., Xie, J., Theobalt, C., Rupprecht, C., Kortylewski, A.: CNS-Bench: benchmarking image classifier robustness under continuous nuisance shifts, ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01858"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"D\u00fcnkel, O., Wimmer, T., Theobalt, C., Rupprecht, C., Kortylewski, A.: Do it yourself: learning semantic correspondence from pseudo-labels, ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00552"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"El Banani, M., et al.: Probing the 3D awareness of visual foundation models, pp. 21795\u201321806. CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02059"},{"issue":"1","key":"14_CR21","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. IJCV 111(1), 98\u2013136 (2015)","journal-title":"IJCV"},{"issue":"2","key":"14_CR22","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"14_CR23","unstructured":"Florence, P.R., Manuelli, L., Tedrake, R.: Dense object nets: learning dense visual object descriptors by and for robotic manipulation. arXiv preprint arXiv:1806.08756 (2018)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: BLINK: multimodal large language models can see but not perceive. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Gan, C., et al.: Unleashing diffusion transformers for visual correspondence by modulating massive activations. In: NeurIPS (2025)","DOI":"10.52202\/085713-3816"},{"key":"14_CR26","unstructured":"Team, G.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow, pp. 3475\u20133484. CVPR (2016)","DOI":"10.1109\/CVPR.2016.378"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Heinrich, G., et al.: RADIOv2.5: improved baselines for agglomerative vision foundation models, CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02094"},{"key":"14_CR30","unstructured":"Hurst, A., et al. GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Jampani, V., et al.: NAVI: category-agnostic image collections with high-quality 3D shape and pose annotations. In: NeurIPS (2023)","DOI":"10.52202\/075280-3323"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., Le, Q.V.: Do better ImageNet models transfer better? In: CVPR, pp. 2661\u20132671 (2019)","DOI":"10.1109\/CVPR.2019.00277"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Lan, S., Yu, Z., Choy, C.B., Radhakrishnan, S., Liu, G., Zhu, Y., Anandkumar, A.: DiscoBox: weakly supervised instance segmentation and semantic correspondence from box supervision. In: ICCV, pp. 3406\u20133416 (2021)","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"14_CR34","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. TMLR (2025)"},{"key":"14_CR35","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.T.: SIFT Flow: dense correspondence across different scenes. In: ECCV, pp. 28\u201342 (2008)","DOI":"10.1007\/978-3-540-88690-7_3"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: ECCV, pp. 216\u2013233 (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Luo, G., Dunlap, L., Park, D.H., Holynski, A., Darrell, T.: Diffusion Hyperfeatures: searching through time and space for semantic correspondence. In: NeurIPS (2023)","DOI":"10.52202\/075280-2057"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: ImageNet3D: towards general-purpose object-level 3D understanding. In: NeurIPS, vol. 37, pp. 96127\u201396149 (2024)","DOI":"10.52202\/079017-3046"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Mariotti, O., Du, Z., Bhalgat, Y., Mac Aodha, O., Bilen, H.: Jamais Vu: Exposing the generalization gap in supervised semantic correspondence. arXiv preprint arXiv:2506.08220 (2025)","DOI":"10.52202\/085713-0536"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Mariotti, O., Mac Aodha, O., Bilen, H.: Improving semantic correspondence with viewpoint-guided spherical maps. In: CVPR, pp. 19521\u201319530 (2024)","DOI":"10.1109\/CVPR52733.2024.01846"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation, pp. 4040\u20134048. CVPR (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"14_CR46","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: SPair-71k: a large-scale benchmark for semantic correspondence. arXiv preprint arXiv:1908.10543 (2019)"},{"key":"14_CR47","unstructured":"Applin, S., et al.: GPT-4V(ision) system card, Technical report. OpenAI (2023)"},{"key":"14_CR48","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. In: TMLR (2024)"},{"key":"14_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Ranzinger, M., Heinrich, G., Kautz, J., Molchanov, P.: AM-RADIO: agglomerative vision foundation model reduce all domains into one. In: CVPR, pp. 12490\u201312500 (2024)","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"14_CR52","unstructured":"Ranzinger, M., et al.: C-RADIOv4 Technical report. arXiv preprint arXiv:2601.17237 (2026)"},{"key":"14_CR53","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching, pp. 6148\u20136157. CVPR (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Sar\u0131y\u0131ld\u0131z, M.B., Weinzaepfel, P., Lucas, T., De Jorge, P., Larlus, D., Kalantidis, Y.: DUNE: distilling a universal encoder from heterogeneous 2D and 3D teachers. In: CVPR, pp. 30084\u201330094 (2025)","DOI":"10.1109\/CVPR52734.2025.02800"},{"issue":"1","key":"14_CR56","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47(1), 7\u201342 (2002)","journal-title":"IJCV"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Sedaghat, N., Brox, T.: Unsupervised generation of a viewpoint annotated car dataset from videos, p. ICCV (2015)","DOI":"10.1109\/ICCV.2015.155"},{"key":"14_CR58","unstructured":"Shen, S., et al.: How much can CLIP benefit vision-and-language tasks?. In: ICLR (2022)"},{"key":"14_CR59","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A.: What does CLIP know about a red circle? visual prompt engineering for VLMs, ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGB-D images, ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"14_CR61","unstructured":"Sim\u00e9oni, O., et al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"14_CR62","doi-asserted-by":"crossref","unstructured":"Sommer, L., D\u00fcnkel, O., Theobalt, C., Kortylewski, A.: Common3D: self-supervised learning of 3D morphable models for common objects in neural feature space. In: CVPR, pp. 6468\u20136479 (2025)","DOI":"10.1109\/CVPR52734.2025.00606"},{"key":"14_CR63","doi-asserted-by":"crossref","unstructured":"Stracke, N., Baumann, S.A., Bauer, K., Fundel, F., Ommer, B.: CleanDIFT: diffusion features without noise. In: CVPR, pp. 117\u2013127 (2025)","DOI":"10.1109\/CVPR52734.2025.00020"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: MISC210K: a large-scale dataset for multi-instance semantic correspondence. In: CVPR, pp. 7121\u20137130 (2023)","DOI":"10.1109\/CVPR52729.2023.00688"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. In: NeurIPS vol. 36, pp. 1363\u20131389 (2023)","DOI":"10.52202\/075280-0068"},{"key":"14_CR66","doi-asserted-by":"crossref","unstructured":"Taniai, T., Sinha, S.N., Sato, Y.: Joint recovery of dense correspondence and cosegmentation in two images. In: CVPR, pp. 4246\u20134255 (2016)","DOI":"10.1109\/CVPR.2016.460"},{"key":"14_CR67","unstructured":"Venkataramanan, S., et al.: Franca: nested matryoshka clustering for scalable visual representation learning. arXiv preprint arXiv:2507.14137 (2025)"},{"key":"14_CR68","doi-asserted-by":"crossref","unstructured":"Wandel, K., Wang, H.: SemAlign3D: semantic correspondence between RGB images through aligning 3D object-class representations, CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00114"},{"key":"14_CR69","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: CVPR, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"14_CR70","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"14_CR71","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., et al.: CroCo V2: improved cross-view completion pre-training for stereo matching and optical flow, ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01647"},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark, pp. 2411\u20132418. CVPR (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"14_CR73","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 software (2019)"},{"key":"14_CR74","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: WACV, pp. 75\u201382 (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"14_CR75","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, Y., Peng, J., Ma, W., Jesslen, A., Ji, P., Hu, Q., Zhang, J., Liu, Q., Wang, J., et\u00a0al.: Animal3D: A comprehensive dataset of 3D animal pose and shape. In: ICCV. pp. 9099\u20139109 (2023)","DOI":"10.1109\/ICCV51070.2023.00835"},{"key":"14_CR76","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in Space: how multimodal large language models see, remember and recall spaces. arXiv preprint arXiv:2412.14171 (2024)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"14_CR77","unstructured":"Yang, L., et al.: In pursuit of pixel supervision for visual pre-training. arXiv preprint arXiv:2512.15715 (2025)"},{"key":"14_CR78","unstructured":"Yu, H., Xu, Y., Zhang, J., Zhao, W., Guan, Z., Tao, D.: AP-10K: A benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617 (2021)"},{"key":"14_CR79","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"14_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Telling left from right: identifying geometry-aware semantic correspondence. In: CVPR, pp. 3076\u20133085 (2024)","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"14_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: A tale of two features: stable Diffusion complements DINO for zero-shot semantic correspondence. In: NeurIPS, vol. 36, pp. 45533\u201345547 (2023)","DOI":"10.52202\/075280-1973"},{"key":"14_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR, pp. 633\u2013641. (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"14_CR83","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer, ICLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:10:25Z","timestamp":1789204225000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}