{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:53:50Z","timestamp":1784300030458,"version":"3.55.0"},"reference-count":112,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"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":[[2024,11]]},"DOI":"10.1007\/s11263-024-02106-7","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T14:04:26Z","timestamp":1716818666000},"page":"4823-4849","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Learning Hierarchical Visual Transformation for Domain Generalizable Visual Matching and Recognition"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,27]]},"reference":[{"key":"2106_CR1","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019). Invariant risk minimization. arXiv:1907.02893"},{"key":"2106_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Y., Jiao, J., Ce, W., Liu, J., Lou, Y., Feng, X., & Duan, L. Y. (2021). Person30k: A dual-meta generalization network for person re-identification. In CVPR (pp. 2123\u20132132).","DOI":"10.1109\/CVPR46437.2021.00216"},{"key":"2106_CR3","doi-asserted-by":"crossref","unstructured":"Beery, S., Van\u00a0Horn, G., & Perona, P. (2018). Recognition in terra incognita. In ECCV (pp. 456\u2013473).","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"2106_CR4","unstructured":"Biswas, J., & Veloso, M. (2011). Depth camera based localization and navigation for indoor mobile robots. In RGB-D Workshop at RSS, Vol. 2011."},{"key":"2106_CR5","doi-asserted-by":"crossref","unstructured":"Cai, C., Poggi, M., Mattoccia, S., & Mordohai, P. (2020). Matching-space stereo networks for cross-domain generalization. In 3DV (pp. 364\u2013373). IEEE.","DOI":"10.1109\/3DV50981.2020.00046"},{"key":"2106_CR6","doi-asserted-by":"crossref","unstructured":"Chang, J. R., & Chen, Y. S. (2018). Pyramid stereo matching network. In CVPR (pp. 5410\u20135418).","DOI":"10.1109\/CVPR.2018.00567"},{"key":"2106_CR7","doi-asserted-by":"crossref","unstructured":"Chang, T., Yang, X., Luo, X., Ji, W., & Wang, M. (2023a). Learning style-invariant robust representation for generalizable visual instance retrieval. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 6171\u20136180).","DOI":"10.1145\/3581783.3611949"},{"key":"2106_CR8","doi-asserted-by":"crossref","unstructured":"Chang, T., Yang, X., Zhang, T., & Wang, M. (2023b). Domain generalized stereo matching via hierarchical visual transformation. In CVPR (pp. 9559\u20139568).","DOI":"10.1109\/CVPR52729.2023.00922"},{"key":"2106_CR9","unstructured":"Chang, S., Zhang, Y., Yu, M., & Jaakkola, T. (2020). Invariant rationalization. In ICML (pp. 1448\u20131458). PMLR."},{"key":"2106_CR10","doi-asserted-by":"crossref","unstructured":"Chen, C., Li, Z., Ouyang, C., Sinclair, M., Bai, W., & Rueckert, D. (2022). Maxstyle: Adversarial style composition for robust medical image segmentation. In MICCAI (pp. 151\u2013161). Springer.","DOI":"10.1007\/978-3-031-16443-9_15"},{"issue":"4","key":"2106_CR11","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2106_CR12","doi-asserted-by":"crossref","unstructured":"Choi, S., Jung, S., Yun, H., Kim, J. T., Kim, S., & Choo, J. (2021a). Robustnet: Improving domain generalization in urban-scene segmentation via instance selective whitening. In CVPR (pp. 11580\u201311590).","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"2106_CR13","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, T., Jeong, M., Park, H., & Kim, C. (2021b). Meta batch-instance normalization for generalizable person re-identification. In CVPR (pp. 3425\u20133435).","DOI":"10.1109\/CVPR46437.2021.00343"},{"key":"2106_CR14","doi-asserted-by":"crossref","unstructured":"Chuah, W., Tennakoon, R., Hoseinnezhad, R., Bab-Hadiashar, A., & Suter, D. (2022). Itsa: An information-theoretic approach to automatic shortcut avoidance and domain generalization in stereo matching networks. In CVPR (pp. 13022\u201313032).","DOI":"10.1109\/CVPR52688.2022.01268"},{"key":"2106_CR15","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR (pp. 3213\u20133223).","DOI":"10.1109\/CVPR.2016.350"},{"key":"2106_CR16","doi-asserted-by":"crossref","unstructured":"Cui, Y., Tao, Y., Ren, W., & Knoll, A. (2023). Dual-domain attention for image deblurring. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol.\u00a037, pp. 479\u2013487).","DOI":"10.1609\/aaai.v37i1.25122"},{"key":"2106_CR17","unstructured":"Dai, R., Shen, L., He, F., Tian, X., & Tao, D. (2022). Dispfl: Towards communication-efficient personalized federated learning via decentralized sparse training. In ICML (pp. 4587\u20134604). PMLR."},{"issue":"8","key":"2106_CR18","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., Li, X., Xu, C., Yang, X., Yang, G., Wang, X., & Wang, M. (2021). Dual encoding for video retrieval by text. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8), 4065\u20134080.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2106_CR19","doi-asserted-by":"crossref","unstructured":"Fathy, M. E., Tran, Q. H., Zia, M. Z., Vernaza, P., & Chandraker, M. (2018). Hierarchical metric learning and matching for 2d and 3d geometric correspondences. In ECCV (pp. 803\u2013819).","DOI":"10.1007\/978-3-030-01267-0_49"},{"key":"2106_CR20","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The Kitti vision benchmark suite. In CVPR (pp. 3354\u20133361). IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2106_CR21","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., & Tan, P. (2020). Cascade cost volume for high-resolution multi-view stereo and stereo matching. In CVPR (pp. 2495\u20132504).","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"2106_CR22","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., & Li, H. (2019). Group-wise correlation stereo network. In CVPR (pp. 3273\u20133282).","DOI":"10.1109\/CVPR.2019.00339"},{"key":"2106_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2106_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, H., Xing, E.P., & Huang, D. (2020). Self-challenging improves cross-domain generalization. In: ECCV (pp. 124\u2013140). Springer.","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"2106_CR25","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhou, Y., Zhu, F., Liu, L., & Shao, L. (2019). Iterative normalization: Beyond standardization towards efficient whitening. In CVPR (pp. 4874\u20134883).","DOI":"10.1109\/CVPR.2019.00501"},{"key":"2106_CR26","first-page":"915","volume":"35","author":"BW Huang","year":"2022","unstructured":"Huang, B. W., Liao, K. T., Kao, C. S., & Lin, S. D. (2022). Environment diversification with multi-head neural network for invariant learning. NeurIPS, 35, 915\u2013927.","journal-title":"NeurIPS"},{"issue":"2","key":"2106_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3181974","volume":"37","author":"Y Hu","year":"2018","unstructured":"Hu, Y., He, H., Xu, C., Wang, B., & Lin, S. (2018). Exposure: A white-box photo post-processing framework. ACM Transactions on Graphics (TOG), 37(2), 1\u201317.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2106_CR28","doi-asserted-by":"publisher","first-page":"3218","DOI":"10.1109\/TMM.2021.3095789","volume":"24","author":"B Jiang","year":"2021","unstructured":"Jiang, B., Wang, X., Zheng, A., Tang, J., & Luo, B. (2021). Ph-gcn: Person retrieval with part-based hierarchical graph convolutional network. IEEE Transactions on Multimedia, 24, 3218\u20133228.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2106_CR29","doi-asserted-by":"crossref","unstructured":"Jiao, B., Liu, L., Gao, L., Lin, G., Yang, L., Zhang, S., Wang, P., & Zhang, Y. (2022). Dynamically transformed instance normalization network for generalizable person re-identification. In ECCV (pp. 285\u2013301). Springer.","DOI":"10.1007\/978-3-031-19781-9_17"},{"key":"2106_CR30","doi-asserted-by":"crossref","unstructured":"Jin, X., Lan, C., Zeng, W., Chen, Z., & Zhang, L. (2020). Style normalization and restitution for generalizable person re-identification. In CVPR (pp. 3143\u20133152).","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"2106_CR31","unstructured":"Kamath, P., Tangella, A., Sutherland, D., & Srebro, N. (2021). Does invariant risk minimization capture invariance? In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research (Vol. 130, pp. 4069\u20134077). PMLR."},{"key":"2106_CR32","doi-asserted-by":"crossref","unstructured":"Kang, G., Jiang, L., Yang, Y., & Hauptmann, A. G. (2019). Contrastive adaptation network for unsupervised domain adaptation. In CVPR (pp. 4893\u20134902).","DOI":"10.1109\/CVPR.2019.00503"},{"key":"2106_CR33","doi-asserted-by":"crossref","unstructured":"Kang, J., Lee, S., Kim, N., & Kwak, S. (2022). Style neophile: Constantly seeking novel styles for domain generalization. In CVPR (pp. 7130\u20137140).","DOI":"10.1109\/CVPR52688.2022.00699"},{"key":"2106_CR34","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., & Bry, A. (2017). End-to-end learning of geometry and context for deep stereo regression. In ICCV (pp. 66\u201375).","DOI":"10.1109\/ICCV.2017.17"},{"key":"2106_CR35","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. NeurIPS 25."},{"key":"2106_CR36","unstructured":"Krueger, D., Caballero, E., Jacobsen, J.H., Zhang, A., Binas, J., Zhang, D., Le\u00a0Priol, R., & Courville, A. (2021). Out-of-distribution generalization via risk extrapolation (rex). In International Conference on Machine Learning (pp. 5815\u20135826). PMLR."},{"key":"2106_CR37","unstructured":"Li, X., Dai, Y., Ge, Y., Liu, J., Shan, Y., & Duan, L. Y. (2022). Uncertainty modeling for out-of-distribution generalization. arXiv:2202.03958"},{"key":"2106_CR38","unstructured":"Li, X., Lu, Y., Liu, B., Hou, Y., Liu, Y., Chu, Q., Ouyang, W., & Yu, N. (2023). Clothes-invariant feature learning by causal intervention for clothes-changing person re-identification. arXiv:2305.06145"},{"key":"2106_CR39","doi-asserted-by":"crossref","unstructured":"Li, H., Pan, S. J., Wang, S., & Kot, A. C. (2018). Domain generalization with adversarial feature learning. In CVPR (pp. 5400\u20135409).","DOI":"10.1109\/CVPR.2018.00566"},{"key":"2106_CR40","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y. Z., & Hospedales, T. M. (2017). Deeper, broader and artier domain generalization. In ICCV (pp. 5542\u20135550).","DOI":"10.1109\/ICCV.2017.591"},{"key":"2106_CR41","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., & Wang, X. (2014). Deepreid: Deep filter pairing neural network for person re-identification. In CVPR (pp. 152\u2013159).","DOI":"10.1109\/CVPR.2014.27"},{"key":"2106_CR42","doi-asserted-by":"crossref","unstructured":"Liao, S., & Shao, L. (2020). Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In ECCV (pp. 456\u2013474). Springer.","DOI":"10.1007\/978-3-030-58621-8_27"},{"key":"2106_CR43","doi-asserted-by":"crossref","unstructured":"Liao, S., & Shao, L. (2022). Graph sampling based deep metric learning for generalizable person re-identification. In CVPR (pp. 7359\u20137368).","DOI":"10.1109\/CVPR52688.2022.00721"},{"key":"2106_CR44","first-page":"1992","volume":"34","author":"S Liao","year":"2021","unstructured":"Liao, S., & Shao, L. (2021). Transmatcher: Deep image matching through transformers for generalizable person re-identification. NeurIPS, 34, 1992\u20132003.","journal-title":"NeurIPS"},{"key":"2106_CR45","unstructured":"Lin, Y., Lian, Q., & Zhang, T. (2021). An empirical study of invariant risk minimization on deep models. In ICML Workshop on Uncertainty and Robustness in Deep Learning (Vol.\u00a01, p.\u00a07)."},{"key":"2106_CR46","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., & Deng, J. (2021). Raft-stereo: Multilevel recurrent field transforms for stereo matching. In 3DV (pp. 218\u2013227). IEEE.","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"2106_CR47","doi-asserted-by":"crossref","unstructured":"Liu, B., Yu, H., & Qi, G. (2022). Graftnet: Towards domain generalized stereo matching with a broad-spectrum and task-oriented feature. In CVPR (pp. 13012\u201313021).","DOI":"10.1109\/CVPR52688.2022.01267"},{"key":"2106_CR48","first-page":"1","volume":"11","author":"X Liu","year":"2020","unstructured":"Liu, X., Yang, X., Wang, M., & Hong, R. (2020). Deep neighborhood component analysis for visual similarity modeling. ACM Transactions on Intelligent Systems and Technology (TIST), 11, 1\u201315.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"2106_CR49","doi-asserted-by":"crossref","unstructured":"Lv, F., Liang, J., Li, S., Zang, B., Liu, C.H., Wang, Z., & Liu, D. (2022). Causality inspired representation learning for domain generalization. In CVPR (pp. 8046\u20138056).","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"2106_CR50","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In CVPR (pp. 4040\u20134048).","DOI":"10.1109\/CVPR.2016.438"},{"key":"2106_CR51","doi-asserted-by":"crossref","unstructured":"Menze, M., & Geiger, A. (2015). Object scene flow for autonomous vehicles. In CVPR (pp. 3061\u20133070).","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"2106_CR52","unstructured":"Mu, J., Li, Y., Li, J., & Yang, J. (2022). Learning clothes-irrelevant cues for clothes-changing person re-identification. In BMVC."},{"key":"2106_CR53","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Rota\u00a0Bulo, S., & Kontschieder, P. (2017). The mapillary vistas dataset for semantic understanding of street scenes. In ICCV (pp. 4990\u20134999).","DOI":"10.1109\/ICCV.2017.534"},{"key":"2106_CR54","doi-asserted-by":"crossref","unstructured":"Ni, H., Song, J., Luo, X., Zheng, F., Li, W., & Shen, H. T. (2022). Meta distribution alignment for generalizable person re-identification. In CVPR (pp. 2487\u20132496).","DOI":"10.1109\/CVPR52688.2022.00252"},{"key":"2106_CR55","doi-asserted-by":"crossref","unstructured":"Pan, X., Luo, P., Shi, J., & Tang, X. (2018). Two at once: Enhancing learning and generalization capacities via ibn-net. In ECCV (pp. 464\u2013479).","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"2106_CR56","doi-asserted-by":"crossref","unstructured":"Pan, X., Zhan, X., Shi, J., Tang, X., & Luo, P. (2019). Switchable whitening for deep representation learning. In ICCV (pp. 1863\u20131871).","DOI":"10.1109\/ICCV.2019.00195"},{"key":"2106_CR57","doi-asserted-by":"crossref","unstructured":"Peng, D., Lei, Y., Hayat, M., Guo, Y., & Li, W. (2022). Semantic-aware domain generalized segmentation. In CVPR (pp. 2594\u20132605).","DOI":"10.1109\/CVPR52688.2022.00262"},{"key":"2106_CR58","doi-asserted-by":"publisher","first-page":"6594","DOI":"10.1109\/TIP.2021.3096334","volume":"30","author":"D Peng","year":"2021","unstructured":"Peng, D., Lei, Y., Liu, L., Zhang, P., & Liu, J. (2021). Global and local texture randomization for synthetic-to-real semantic segmentation. IEEE Transactions on Image Processing, 30, 6594\u20136608.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2106_CR59","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2018). Revisiting oxford and paris: Large-scale image retrieval benchmarking. In CVPR (pp. 5706\u20135715).","DOI":"10.1109\/CVPR.2018.00598"},{"key":"2106_CR60","doi-asserted-by":"crossref","unstructured":"Richter, S. R., Vineet, V., Roth, S., & Koltun, V. (2016). Playing for data: Ground truth from computer games. In ECCV (pp. 102\u2013118). Springer.","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"2106_CR61","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016). The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In CVPR (pp. 3234\u20133243).","DOI":"10.1109\/CVPR.2016.352"},{"key":"2106_CR62","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., & Harada, T. (2018). Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR (pp. 3723\u20133732).","DOI":"10.1109\/CVPR.2018.00392"},{"key":"2106_CR63","doi-asserted-by":"crossref","unstructured":"Scharstein, D., Hirschm\u00fcller, H., Kitajima, Y., Krathwohl, G., Ne\u0161i\u0107, N., Wang, X., & Westling, P. (2014). High-resolution stereo datasets with subpixel-accurate ground truth. In German conference on pattern recognition (pp. 31\u201342). Springer.","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"2106_CR64","doi-asserted-by":"crossref","unstructured":"Schops, T., Schonberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., & Geiger, A. (2017). A multi-view stereo benchmark with high-resolution images and multi-camera videos. In CVPR (pp. 3260\u20133269).","DOI":"10.1109\/CVPR.2017.272"},{"key":"2106_CR65","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., & Rao, Z. (2021). Cfnet: Cascade and fused cost volume for robust stereo matching. In CVPR (pp. 13906\u201313915).","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"2106_CR66","doi-asserted-by":"crossref","unstructured":"Song, P., Guo, D., Yang, X., Tang, S., & Wang, M. (2024). Emotional video captioning with vision-based emotion interpretation network. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2024.3359045"},{"key":"2106_CR67","unstructured":"Sun, C., Vianney, J. M. U., & Cao, D. (2019). Affordance learning in direct perception for autonomous driving. arXiv:1903.08746"},{"key":"2106_CR68","unstructured":"Sun, X., Yao, Y., Wang, S., Li, H., & Zheng, L. (2023). Alice benchmarks: Connecting real world object re-identification with the synthetic. arXiv:2310.04416"},{"key":"2106_CR69","doi-asserted-by":"crossref","unstructured":"Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017). Deep hashing network for unsupervised domain adaptation. In CVPR (pp. 5018\u20135027).","DOI":"10.1109\/CVPR.2017.572"},{"key":"2106_CR70","doi-asserted-by":"crossref","unstructured":"Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Chen, Y., Zeng, W., & Yu, P. (2022a). Generalizing to unseen domains: A survey on domain generalization. IEEE Transactions on Knowledge and Data Engineering.","DOI":"10.1109\/TKDE.2022.3178128"},{"key":"2106_CR71","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liao, S., & Shao, L. (2020). Surpassing real-world source training data: Random 3d characters for generalizable person re-identification. In ACM MM (pp. 3422\u20133430).","DOI":"10.1145\/3394171.3413815"},{"key":"2106_CR72","doi-asserted-by":"crossref","unstructured":"Wang, Z., Luo, Y., Qiu, R., Huang, Z., & Baktashmotlagh, M. (2021). Learning to diversify for single domain generalization. In ICCV (pp. 834\u2013843).","DOI":"10.1109\/ICCV48922.2021.00087"},{"key":"2106_CR73","doi-asserted-by":"crossref","unstructured":"Wang, R., Yi, M., Chen, Z., & Zhu, S. (2022b). Out-of-distribution generalization with causal invariant transformations. In CVPR (pp. 375\u2013385).","DOI":"10.1109\/CVPR52688.2022.00047"},{"key":"2106_CR74","doi-asserted-by":"crossref","unstructured":"Wei, L., Zhang, S., Gao, W., & Tian, Q. (2018). Person transfer gan to bridge domain gap for person re-identification. In CVPR (pp. 79\u201388).","DOI":"10.1109\/CVPR.2018.00016"},{"key":"2106_CR75","unstructured":"Xie, C., Ye, H., Chen, F., Liu, Y., Sun, R., & Li, Z. (2020). Risk variance penalization. arXiv:2006.07544"},{"key":"2106_CR76","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhang, R., Zhang, Y., Wang, Y., & Tian, Q. (2021). A fourier-based framework for domain generalization. In CVPR (pp. 14383\u201314392).","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"2106_CR77","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., Wang, M., & Chua, T. S. (2021). Deconfounded video moment retrieval with causal intervention. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.","DOI":"10.1145\/3404835.3462823"},{"key":"2106_CR78","doi-asserted-by":"crossref","unstructured":"Yang, G., Song, X., Huang, C., Deng, Z., Shi, J., & Zhou, B. (2019). Drivingstereo: A large-scale dataset for stereo matching in autonomous driving scenarios. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 899\u2013908).","DOI":"10.1109\/CVPR.2019.00099"},{"issue":"4","key":"2106_CR79","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1109\/TPAMI.2020.2975798","volume":"43","author":"C Yan","year":"2020","unstructured":"Yan, C., Gong, B., Wei, Y., & Gao, Y. (2020). Deep multi-view enhancement hashing for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(4), 1445\u20131451.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2106_CR80","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/TIP.2022.3140611","volume":"31","author":"X Yang","year":"2022","unstructured":"Yang, X., Wang, S., Dong, J., Dong, J., Wang, M., & Chua, T. S. (2022). Video moment retrieval with cross-modal neural architecture search. IEEE Transactions on Image Processing, 31, 1204\u20131216.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"2106_CR81","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1109\/TNNLS.2018.2861991","volume":"30","author":"X Yang","year":"2018","unstructured":"Yang, X., Zhou, P., & Wang, M. (2018). Person reidentification via structural deep metric learning. IEEE Transactions on Neural Networks and Learning Systems, 30(10), 2987\u20132998.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"10","key":"2106_CR82","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1109\/TNNLS.2018.2861991","volume":"30","author":"X Yang","year":"2019","unstructured":"Yang, X., Zhou, P., & Wang, M. (2019). Person reidentification via structural deep metric learning. IEEE Transactions on Neural Networks and Learning Systems, 30(10), 2987\u20132998.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2106_CR83","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1109\/TMM.2021.3069562","volume":"24","author":"C Yan","year":"2021","unstructured":"Yan, C., Pang, G., Bai, X., Liu, C., Ning, X., Gu, L., & Zhou, J. (2021). Beyond triplet loss: Person re-identification with fine-grained difference-aware pairwise loss. IEEE Transactions on Multimedia, 24, 1665\u20131677.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2106_CR84","doi-asserted-by":"crossref","unstructured":"Yao, C., Jia, Y., Di, H., Li, P., & Wu, Y. (2021). A decomposition model for stereo matching. In CVPR (pp. 6091\u20136100).","DOI":"10.1109\/CVPR46437.2021.00603"},{"key":"2106_CR85","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In CVPR (pp. 2636\u20132645).","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"2106_CR86","unstructured":"Yu, Y., Khadivi, S., & Xu, J. (2022). Can data diversity enhance learning generalization? In Proceedings of the 29th International Conference on Computational Linguistics (pp. 4933\u20134945)."},{"key":"2106_CR87","doi-asserted-by":"crossref","unstructured":"Yue, X., Zhang, Y., Zhao, S., Sangiovanni-Vincentelli, A., Keutzer, K., & Gong, B. (2019). Domain randomization and pyramid consistency: Simulation-to-real generalization without accessing target domain data. In ICCV (pp. 2100\u20132110).","DOI":"10.1109\/ICCV.2019.00219"},{"key":"2106_CR88","doi-asserted-by":"crossref","unstructured":"Zbontar, J., & LeCun, Y. (2015). Computing the stereo matching cost with a convolutional neural network. In CVPR (pp. 1592\u20131599).","DOI":"10.1109\/CVPR.2015.7298767"},{"key":"2106_CR89","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization. In International Conference on Learning Representations."},{"key":"2106_CR90","unstructured":"Zhang, Y., Deng, B., Li, R., Jia, K., & Zhang, L. (2023). Adversarial style augmentation for domain generalization. arXiv:2301.12643"},{"key":"2106_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, P., Dou, H., Yu, Y., & Li, X. (2022b). Adaptive cross-domain learning for generalizable person re-identification. In ECCV (pp. 215\u2013232). Springer.","DOI":"10.1007\/978-3-031-19781-9_13"},{"key":"2106_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, M., Li, R., Jia, K., & Zhang, L. (2022c). Exact feature distribution matching for arbitrary style transfer and domain generalization. In CVPR (pp. 8035\u20138045).","DOI":"10.1109\/CVPR52688.2022.00787"},{"key":"2106_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., & Torr, P.H. (2019). Ga-net: Guided aggregation net for end-to-end stereo matching. In CVPR (pp. 185\u2013194).","DOI":"10.1109\/CVPR.2019.00027"},{"key":"2106_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, F., Qi, X., Yang, R., Prisacariu, V., Wah, B., & Torr, P. (2020). Domain-invariant stereo matching networks. In ECCV (pp. 420\u2013439). Springer.","DOI":"10.1007\/978-3-030-58536-5_25"},{"key":"2106_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, A., Ren, W., Liu, Y., & Cao, X. (2023). Lightweight image super-resolution with superpixel token interaction. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 12728\u201312737).","DOI":"10.1109\/ICCV51070.2023.01169"},{"key":"2106_CR96","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Bai, X., Wang, C., Huang, L., Chen, Y., Gu, L., Zhou, J., Harada, T., & Hancock, E. R. (2022a). Revisiting domain generalized stereo matching networks from a feature consistency perspective. In CVPR (pp. 13001\u201313011).","DOI":"10.1109\/CVPR52688.2022.01266"},{"issue":"2","key":"2106_CR97","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1109\/TIP.2017.2752370","volume":"27","author":"F Zhang","year":"2017","unstructured":"Zhang, F., & Wah, B. W. (2017). Fundamental principles on learning new features for effective dense matching. IEEE Transactions on Image Processing, 27(2), 822\u2013836.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2106_CR98","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhong, Z., Yang, F., Luo, Z., Lin, Y., Li, S., & Sebe, N. (2021). Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In CVPR (pp. 6277\u20136286).","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"2106_CR99","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhong, Z., Zhao, N., Sebe, N., & Lee, G.H. (2022). Style-hallucinated dual consistency learning for domain generalized semantic segmentation. In ECCV (pp. 535\u2013552). Springer.","DOI":"10.1007\/978-3-031-19815-1_31"},{"issue":"3","key":"2106_CR100","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s11263-023-01911-w","volume":"132","author":"Y Zhao","year":"2024","unstructured":"Zhao, Y., Zhong, Z., Zhao, N., Sebe, N., & Lee, G. H. (2024). Style-hallucinated dual consistency learning: A unified framework for visual domain generalization. International Journal of Computer Vision, 132(3), 837\u2013853.","journal-title":"International Journal of Computer Vision"},{"key":"2106_CR101","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In ICCV (pp. 1116\u20131124).","DOI":"10.1109\/ICCV.2015.133"},{"key":"2106_CR102","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Cao, D., & Li, S. (2017). Re-ranking person re-identification with k-reciprocal encoding. In CVPR (pp. 1318\u20131327).","DOI":"10.1109\/CVPR.2017.389"},{"key":"2106_CR103","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020a). Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence (Vol.\u00a034, pp. 13001\u201313008).","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2106_CR104","first-page":"338","volume":"35","author":"Z Zhong","year":"2022","unstructured":"Zhong, Z., Zhao, Y., Lee, G. H., & Sebe, N. (2022). Adversarial style augmentation for domain generalized urban-scene segmentation. NeurIPS, 35, 338\u2013350.","journal-title":"NeurIPS"},{"issue":"8","key":"2106_CR105","first-page":"2723","volume":"43","author":"Z Zhong","year":"2020","unstructured":"Zhong, Z., Zheng, L., Luo, Z., Li, S., & Yang, Y. (2020b). Learning to adapt invariance in memory for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8), 2723\u20132738.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"2106_CR106","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1109\/TIP.2018.2874313","volume":"28","author":"Z Zhong","year":"2018","unstructured":"Zhong, Z., Zheng, L., Zheng, Z., Li, S., & Yang, Y. (2018). Camstyle: A novel data augmentation method for person re-identification. IEEE Transactions on Image Processing, 28(3), 1176\u20131190.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2106_CR107","doi-asserted-by":"crossref","unstructured":"Zhou, S., Guo, D., Li, J., Yang, X., & Wang, M. (2023). Exploring sparse spatial relation in graph inference for text-based vqa. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2023.3310332"},{"key":"2106_CR108","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Hospedales, T., & Xiang, T. (2020). Learning to generate novel domains for domain generalization. In ECCV (pp. 561\u2013578). Springer.","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"2106_CR109","unstructured":"Zhou, K., Yang, Y., Qiao, Y., & Xiang, T. (2021b). Domain generalization with mixstyle. arXiv:2104.02008"},{"issue":"4","key":"2106_CR110","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3634918","volume":"20","author":"S Zhou","year":"2024","unstructured":"Zhou, S., Guo, D., Yang, X., Dong, J., & Wang, M. (2024). Graph pooling inference network for text-based vqa. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(4), 1\u201321.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"9","key":"2106_CR111","first-page":"5056","volume":"44","author":"K Zhou","year":"2021","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., & Xiang, T. (2021a). Learning generalisable omni-scale representations for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5056\u20135069.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2106_CR112","doi-asserted-by":"crossref","unstructured":"Zhuang, Z., Wei, L., Xie, L., Zhang, T., Zhang, H., Wu, H., Ai, H., & Tian, Q. (2020). Rethinking the distribution gap of person re-identification with camera-based batch normalization. In ECCV (pp. 140\u2013157). Springer.","DOI":"10.1007\/978-3-030-58610-2_9"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02106-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02106-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02106-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T05:04:56Z","timestamp":1729919096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02106-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":112,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["2106"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02106-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,27]]},"assertion":[{"value":"16 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}