{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:22:56Z","timestamp":1777569776243,"version":"3.51.4"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11263-024-02204-6","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T18:01:57Z","timestamp":1723831317000},"page":"760-780","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Masked Channel Modeling for Bootstrapping Visual Pre-training"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8540-9154","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-7976","authenticated-orcid":false,"given":"Xinlong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3243-2356","authenticated-orcid":false,"given":"Muzhi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1679-0444","authenticated-orcid":false,"given":"Yue","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4234-6099","authenticated-orcid":false,"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"key":"2204_CR1","unstructured":"Arthur, D., & Vassilvitskii, S. (2006). K-means++ the advantages of careful seeding. In Proceedings of the first annual ACM-SIAM symposium on discrete algorithms."},{"key":"2204_CR2","unstructured":"Ba, J.\u00a0L., Kiros, J.\u00a0R., & Hinton, G.\u00a0E. (2016). Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"2204_CR3","unstructured":"Baevski, A., Hsu, W.-N., Xu, Q., Babu, A., Gu, J., & Auli, M. (2022). Data2vec: A general framework for self-supervised learning in speech, vision and language. In Proceedings of international conference on machine learning (pp. 1298\u20131312). PMLR."},{"key":"2204_CR4","unstructured":"Bao, H., Dong, L., Piao, S., & Wei, F. (2021). Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254"},{"key":"2204_CR5","unstructured":"Barbu, A., Mayo, D., Alverio, J., Luo, W., Wang, C., Gutfreund, D., Tenenbaum, J., & Katz, B. (2019). Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models. In Proceedings of advances in neural information processing systems (vol.\u00a032)."},{"key":"2204_CR6","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014). Food-101-mining discriminative components with random forests. In Proceedings of European conference on computer vision (pp. 446\u2013461). Springer.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2204_CR7","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., & Askell, A. (2020). Language models are few-shot learners. Proceedings of Advances in Neural Information Processing Systems, 33, 1877\u20131901.","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"2204_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE international conference on computer vision (pp. 9650\u20139660).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2204_CR9","unstructured":"Chen, M., Radford, A., Child, R., Wu, J., Jun, H., Luan, D., & Sutskever, I. (2020). Generative pretraining from pixels. In Proceedings of international conference on machine learning (pp. 1691\u20131703). PMLR."},{"issue":"1","key":"2204_CR10","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/s11263-023-01852-4","volume":"132","author":"X Chen","year":"2024","unstructured":"Chen, X., Ding, M., Wang, X., Xin, Y., Mo, S., Wang, Y., Han, S., Luo, P., Zeng, G., & Wang, J. (2024). Context autoencoder for self-supervised representation learning. International Journal of Computer Vision, 132(1), 208\u2013223.","journal-title":"International Journal of Computer Vision"},{"key":"2204_CR11","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014). Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3606\u20133613).","DOI":"10.1109\/CVPR.2014.461"},{"key":"2204_CR12","unstructured":"Clark, K., Luong, M.-T., Le, Q.\u00a0V., & Manning, C.\u00a0D. (2020). Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555"},{"key":"2204_CR13","unstructured":"Contributors, M. (2020). MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"2204_CR14","doi-asserted-by":"crossref","unstructured":"Cubuk, E.\u00a0D., Zoph, B., Shlens, J., & Le, Q.\u00a0V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 702\u2013703).","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2204_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2204_CR16","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"2204_CR17","unstructured":"Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. In Proceedings of advances in neural information processing systems (vol.\u00a034, pp. 8780\u20138794)."},{"key":"2204_CR18","unstructured":"Dong, X., Bao, J., Zhang, T., Chen, D., Gu, S., Zhang, W., Yuan, L., Chen, D., Wen, F., & Yu, N. (2022). Clip itself is a strong fine-tuner: Achieving 85.7% and 88.0% top-1 accuracy with vit-b and vit-l on imagenet. arXiv preprint arXiv:2212.06138"},{"key":"2204_CR19","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Zhang, T., Chen, D., Zhang, W., Yuan, L., Chen, D., Wen, F., & Yu, N. (2022). Bootstrapped masked autoencoders for vision bert pretraining. In Proceedings of European conference on computer vision (pp. 247\u2013264). Springer.","DOI":"10.1007\/978-3-031-20056-4_15"},{"issue":"1","key":"2204_CR20","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1609\/aaai.v37i1.25130","volume":"37","author":"X Dong","year":"2023","unstructured":"Dong, X., Bao, J., Zhang, T., Chen, D., Zhang, W., Yuan, L., Chen, D., Wen, F., Yu, N., & Guo, B. (2023). Peco: Perceptual codebook for bert pre-training of vision transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 552\u2013560.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2204_CR21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"2204_CR22","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., & Grave, E. (2021). Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740"},{"key":"2204_CR23","unstructured":"Fang, Y., Dong, L., Bao, H., Wang, X., & Wei, F. (2022). Corrupted image modeling for self-supervised visual pre-training. arXiv preprint arXiv:2202.03382"},{"key":"2204_CR24","doi-asserted-by":"crossref","unstructured":"Fang, Y., Wang, W., Xie, B., Sun, Q., Wu, L., Wang, X., Huang, T., Wang, X., & Cao, Y. (2023). Eva: Exploring the limits of masked visual representation learning at scale. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 19358\u201319369).","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"2204_CR25","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 178\u2013178). IEEE.","DOI":"10.1109\/CVPR.2004.383"},{"key":"2204_CR26","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Y. (2021). Clip-adapter: Better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544"},{"key":"2204_CR27","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings (pp. 249\u2013256)."},{"key":"2204_CR28","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/s11263-017-1048-0","volume":"126","author":"A Gonzalez-Garcia","year":"2018","unstructured":"Gonzalez-Garcia, A., Modolo, D., & Ferrari, V. (2018). Do semantic parts emerge in convolutional neural networks? International Journal of Computer Vision, 126, 476\u2013494.","journal-title":"International Journal of Computer Vision"},{"key":"2204_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., & Girshick, R. (2019). Lvis: A dataset for large vocabulary instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5356\u20135364).","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2204_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"7","key":"2204_CR31","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019). Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7), 2217\u20132226.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2204_CR32","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., & Guo, M. (2021). The many faces of robustness: A critical analysis of out-of-distribution generalization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8340\u20138349).","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"2204_CR33","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021). Natural adversarial examples. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 15262\u201315271).","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"2204_CR34","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K.\u00a0Q. (2016). Deep networks with stochastic depth. In Proceedings of European conference on computer vision (pp. 646\u2013661). Springer.","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"2204_CR35","unstructured":"Ilharco, G., Wortsman, M., Gadre, S.\u00a0Y., Song, S., Hajishirzi, H., Kornblith, S., Farhadi, A., & Schmidt, L. (2022). Patching open-vocabulary models by interpolating weights. arXiv preprint arXiv:2208.05592"},{"key":"2204_CR36","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.-C., Cardie, C., Belongie, S., Hariharan, B., & Lim, S.-N. (2022). Visual prompt tuning. In Proceedings of European conference on computer vision (pp. 709\u2013727). Springer.","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2204_CR37","doi-asserted-by":"crossref","unstructured":"Khattak, M.\u00a0U., Rasheed, H., Maaz, M., Khan, S., & Khan, F.\u00a0S. (2023). Maple: Multi-modal prompt learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 19113\u201319122).","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"2204_CR38","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei L. (2013). 3d object representations for fine-grained categorization. In Proceedings of the IEEE international conference on computer vision workshops (pp. 554\u2013561).","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2204_CR39","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images."},{"key":"2204_CR40","doi-asserted-by":"crossref","unstructured":"Li, X., Ge, Y., Yi, K., Hu, Z., Shan, Y., & Duan, L.-Y. (2022). mc-beit: Multi-choice discretization for image bert pre-training. In Proceedings of European conference on computer vision (pp. 231\u2013246). Springer.","DOI":"10.1007\/978-3-031-20056-4_14"},{"key":"2204_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao H., Girshick, R., & He, K. (2022). Exploring plain vision transformer backbones for object detection. In Proceedings of European conference on computer vision (pp. 280\u2013296). Springer.","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"2204_CR42","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"2204_CR43","unstructured":"Loshchilov, I., & Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983"},{"key":"2204_CR44","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"2204_CR45","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151"},{"key":"2204_CR46","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., & Zisserman, A. (2008). Automated flower classification over a large number of classes. In IEEE sixth Indian conference on computer vision, graphics & image processing (pp. 722\u2013729).","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2204_CR47","doi-asserted-by":"crossref","unstructured":"Parkhi, O.\u00a0M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012). Cats and dogs. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3498\u20133505). IEEE.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2204_CR48","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., & Wei, F. (2022). Beit v2: Masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366"},{"key":"2204_CR49","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., & Krueger, G. (2021). Learning transferable visual models from natural language supervision. In Proceedings of international conference on machine learning (pp. 8748\u20138763). PMLR."},{"issue":"8","key":"2204_CR50","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Blog, 1(8), 9.","journal-title":"OpenAI Blog"},{"issue":"140","key":"2204_CR51","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1\u201367.","journal-title":"Journal of Machine Learning Research"},{"key":"2204_CR52","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? In Proceedings of international conference on machine learning (pp. 5389\u20135400). PMLR."},{"key":"2204_CR53","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.\u00a0R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision (pp. 618\u2013626).","DOI":"10.1109\/ICCV.2017.74"},{"key":"2204_CR54","doi-asserted-by":"crossref","unstructured":"Simon, M., Rodner, E., & Denzler, J. (2015). Part detector discovery in deep convolutional neural networks. In Proceedings of Asian conference on computer vision (pp. 162\u2013177). Springer.","DOI":"10.1007\/978-3-319-16808-1_12"},{"key":"2204_CR55","unstructured":"Simonyan, K., Vedaldi, A., & Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034"},{"key":"2204_CR56","unstructured":"Soomro, K., Zamir, A.\u00a0R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"key":"2204_CR57","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"2204_CR58","unstructured":"Wang, H., Ge, S., Lipton, Z., & Xing, E.\u00a0P. (2019). Learning robust global representations by penalizing local predictive power. In Proceedings of advances in neural information processing systems (vol.\u00a032)."},{"key":"2204_CR59","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2022). Masked feature prediction for self-supervised visual pre-training. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 14668\u201314678).","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"2204_CR60","unstructured":"Wei, Y., Hu, H., Xie, Z., Zhang, Z., Cao, Y., Bao, J., Chen, D., & Guo, B. (2022). Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141"},{"key":"2204_CR61","doi-asserted-by":"crossref","unstructured":"Wei, L., Xie, L., Zhou, W., Li, H., & Tian, Q. (2022). Mvp: Multimodality-guided visual pre-training. In Proceedings of European conference on computer vision (pp. 337\u2013353). Springer.","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"2204_CR62","unstructured":"Wightman, R. (2019). Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"2204_CR63","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ilharco, G., Kim, J.\u00a0W., Li, M., Kornblith, S., Roelofs, R., Lopes, R.\u00a0G., Hajishirzi, H., Farhadi, A., Namkoong, H., & Schmidt. (2022). Robust fine-tuning of zero-shot models. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7959\u20137971).","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"2204_CR64","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., & Girshick, R. (2019). Detectron2. https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"2204_CR65","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.\u00a0A., Oliva, A., & Torralba, A. (2010). Sun database: Large-scale scene recognition from abbey to zoo. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3485\u20133492). IEEE.","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"2204_CR66","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In Proceedings of European conference on computer vision (pp. 418\u2013434).","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"2204_CR67","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2022). Simmim: A simple framework for masked image modeling. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9653\u20139663).","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2204_CR68","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.\u00a0J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE international conference on computer vision (pp. 6023\u20136032).","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2204_CR69","doi-asserted-by":"crossref","unstructured":"Zeiler, M.\u00a0D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Proceedings of European conference on computer vision (pp. 818\u2013833). Springer.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"2204_CR70","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.\u00a0N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"2204_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yang, J., & Schiele, B. (2018). Occluded pedestrian detection through guided attention in cnns. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6995\u20137003).","DOI":"10.1109\/CVPR.2018.00731"},{"key":"2204_CR72","unstructured":"Zhiliang, P., Li, D., Hangbo, B., Qixiang, Y., & Furu, W. (2022). A unified view of masked image modeling. arXiv preprint arXiv:2210.10615"},{"key":"2204_CR73","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., & Kong, T. (2021). ibot: Image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832"},{"key":"2204_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.\u00a0C., & Liu, Z. (2022a). Conditional prompt learning for vision-language models. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 16816\u201316825).","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2204_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022b). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"},{"key":"2204_CR76","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127, 302\u2013321.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02204-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02204-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02204-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:40:50Z","timestamp":1737528050000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02204-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":76,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2204"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02204-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"assertion":[{"value":"26 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}