{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:46:56Z","timestamp":1770338816822,"version":"3.49.0"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200557","type":"print"},{"value":"9783031200564","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20056-4_8","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:31:54Z","timestamp":1667417514000},"page":"125-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Demystifying Unsupervised Semantic Correspondence Estimation"],"prefix":"10.1007","author":[{"given":"Mehmet","family":"Ayg\u00fcn","sequence":"first","affiliation":[]},{"given":"Oisin","family":"Mac Aodha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"8_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-030-01219-9_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Alwassel","year":"2018","unstructured":"Alwassel, H., Caba Heilbron, F., Escorcia, V., Ghanem, B.: Diagnosing error in temporal action detectors. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 264\u2013280. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_16"},{"key":"8_CR2","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep ViT features as dense visual descriptors. arXiv:2112.05814 (2021)"},{"key":"8_CR3","unstructured":"Araslanov, N., Schaub-Meyer, S., Roth, S.: Dense unsupervised learning for video segmentation. In: NeurIPS (2021)"},{"key":"8_CR4","unstructured":"Banik, P., Li, L., Dong, X.: A novel dataset for keypoint detection of quadruped animals from images. arXiv:2108.13958 (2021)"},{"key":"8_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-030-58621-8_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Biggs","year":"2020","unstructured":"Biggs, B., Boyne, O., Charles, J., Fitzgibbon, A., Cipolla, R.: Who left the dogs out? 3D animal reconstruction with expectation maximization in the loop. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 195\u2013211. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_12"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Bristow, H., Valmadre, J., Lucey, S.: Dense semantic correspondence where every pixel is a classifier. In: ICCV, pp. 4024\u20134031 (2015)","DOI":"10.1109\/ICCV.2015.458"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"8_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"8_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv:2003.04297 (2020)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv:2104.02057 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Su, J.C., Maji, S.: On equivariant and invariant learning of object landmark representations. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00975"},{"key":"8_CR12","unstructured":"Cho, S., Hong, S., Jeon, S., Lee, Y., Sohn, K., Kim, S.: CATs: cost aggregation transformers for visual correspondence. In: NeurIPS (2021)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Choe, J., Oh, S.J., Lee, S., Chun, S., Akata, Z., Shim, H.: Evaluating weakly supervised object localization methods right. In: CVPR, pp. 3133\u20133142 (2020)","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"8_CR14","unstructured":"Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: NeurIPS (2016)"},{"key":"8_CR15","unstructured":"David, M.: The correspondence theory of truth. In: The Oxford Handbook of Truth (2016)"},{"key":"8_CR16","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.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"IJCV"},{"issue":"5","key":"8_CR17","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/s11263-017-1048-0","volume":"126","author":"A Gonzalez-Garcia","year":"2017","unstructured":"Gonzalez-Garcia, A., Modolo, D., Ferrari, V.: Do semantic parts emerge in convolutional neural networks? IJCV 126(5), 476\u2013494 (2017). https:\/\/doi.org\/10.1007\/s11263-017-1048-0","journal-title":"IJCV"},{"key":"8_CR18","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.378"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: SCNet: learning semantic correspondence. In: ICCV, pp. 1831\u20131840 (2017)","DOI":"10.1109\/ICCV.2017.203"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 340\u2013353. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_25"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, Q., Zhang, S., Yan, S., He, X.: Dynamic context correspondence network for semantic alignment. In: ICCV, pp. 2010\u20132019 (2019)","DOI":"10.1109\/ICCV.2019.00210"},{"key":"8_CR25","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: NeurIPS (2018)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Self-supervised learning of interpretable keypoints from unlabelled videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. In: ICCV, pp. 6207\u20136217 (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Jacobs, D.W., Chandraker, M.: WarpNet: weakly supervised matching for single-view reconstruction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.354"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Karmali, T., Atrishi, A., Harsha, S.S., Agrawal, S., Jampani, V., Babu, R.V.: LEAD: self-supervised landmark estimation by aligning distributions of feature similarity. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00310"},{"key":"8_CR30","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: stanford dogs. In: CVPR Workshop on Fine-Grained Visual Categorization (2011)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Kim, J., Liu, C., Sha, F., Grauman, K.: Deformable spatial pyramid matching for fast dense correspondences. In: CVPR, pp. 2307\u20132314 (2013)","DOI":"10.1109\/CVPR.2013.299"},{"key":"8_CR32","unstructured":"Kim, S., Lin, S., Jeon, S.R., Min, D., Sohn, K.: Recurrent transformer networks for semantic correspondence. In: NeurIPS (2018)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Ham, B., Jeon, S., Lin, S., Sohn, K.: FCSS: fully convolutional self-similarity for dense semantic correspondence. In: CVPR, pp. 6560\u20136569 (2017)","DOI":"10.1109\/CVPR.2017.73"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: ICCV Workshops (2011)","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"8_CR35","unstructured":"Kolesnikov, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"8_CR36","unstructured":"Kulkarni, T.D., et al.: Unsupervised learning of object keypoints for perception and control. In: NeurIPS (2019)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Lee, J.Y., DeGol, J., Fragoso, V., Sinha, S.N.: Patchmatch-based neighborhood consensus for semantic correspondence. In: CVPR, pp. 13153\u201313163 (2021)","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNet: learning object-aware semantic correspondence. In: CVPR, pp. 2278\u20132287 (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Li, S., Han, K., Costain, T.W., Howard-Jenkins, H., Prisacariu, V.: Correspondence networks with adaptive neighbourhood consensus. In: CVPR, pp. 10196\u201310205 (2020)","DOI":"10.1109\/CVPR42600.2020.01021"},{"issue":"5","key":"8_CR40","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2010","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. PAMI 33(5), 978\u2013994 (2010)","journal-title":"PAMI"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., Yang, Y.: Semantic correspondence as an optimal transport problem. In: CVPR, pp. 4463\u20134472 (2020)","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"8_CR43","unstructured":"Long, J.L., Zhang, N., Darrell, T.: Do convnets learn correspondence? In: NeurIPS (2014)"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Min, J., Cho, M.: Convolutional hough matching networks. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Hyperpixel flow: semantic correspondence with multi-layer neural features. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00349"},{"key":"8_CR46","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: SPair-71k: a large-scale benchmark for semantic correspondence. arXiv:1908.10543 (2019)"},{"key":"8_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58555-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Min","year":"2020","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Learning to compose hypercolumns for visual correspondence. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 346\u2013363. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_21"},{"key":"8_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/978-3-030-58595-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Musgrave","year":"2020","unstructured":"Musgrave, K., Belongie, S., Lim, S.-N.: A metric learning reality check. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 681\u2013699. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_41"},{"key":"8_CR49","unstructured":"Pinheiro, P.O.O., Almahairi, A., Benmalek, R., Golemo, F., Courville, A.C.: Unsupervised learning of dense visual representations. In: NeurIPS (2020)"},{"key":"8_CR50","unstructured":"Van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv:1807.03748 (2018)"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: CVPR, pp. 6148\u20136157 (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"8_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-58545-7_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"I Rocco","year":"2020","unstructured":"Rocco, I., Arandjelovi\u0107, R., Sivic, J.: Efficient neighbourhood consensus networks via submanifold sparse convolutions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 605\u2013621. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_35"},{"key":"8_CR53","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. In: NeurIPS (2018)"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Roh, B., Shin, W., Kim, I., Kim, S.: Spatially consistent representation learning. In: CVPR, pp. 1144\u20131153 (2021)","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Ruggero Ronchi, M., Perona, P.: Benchmarking and error diagnosis in multi-instance pose estimation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.48"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Huang, Z., Berg, A.C., Fei-Fei, L.: Detecting avocados to Zucchinis: what have we done, and where are we going? In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.258"},{"key":"8_CR57","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"IJCV"},{"key":"8_CR58","unstructured":"Ryou, S., Perona, P.: Weakly supervised keypoint discovery. arXiv:2109.13423 (2021)"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Russakovsky, O., Gupta, A.: What actions are needed for understanding human actions in videos? In: ICCV, pp. 2137\u20132146 (2017)","DOI":"10.1109\/ICCV.2017.235"},{"key":"8_CR61","doi-asserted-by":"crossref","unstructured":"Thewlis, J., Albanie, S., Bilen, H., Vedaldi, A.: Unsupervised learning of landmarks by descriptor vector exchange. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00646"},{"key":"8_CR62","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object frames by dense equivariant image labelling. In: NeurIPS (2017)"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Thewlis, J., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks by factorized spatial embeddings. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.348"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"Ufer, N., Ommer, B.: Deep semantic feature matching. In: CVPR, pp. 6914\u20136923 (2017)","DOI":"10.1109\/CVPR.2017.628"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"8_CR66","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)"},{"key":"8_CR67","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: CVPR, pp. 3024\u20133033 (2021)","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Exploring set similarity for dense self-supervised representation learning. arXiv:2107.08712 (2021)","DOI":"10.1109\/CVPR52688.2022.01609"},{"key":"8_CR69","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S.: Aligning pretraining for detection via object-level contrastive learning. In: NeurIPS (2021)"},{"key":"8_CR70","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"issue":"9","key":"8_CR71","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. PAMI 41(9), 2251\u20132265 (2018)","journal-title":"PAMI"},{"key":"8_CR72","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"8_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Omran, M., Hosang, J., Schiele, B.: How far are we from solving pedestrian detection? In: CVPR, pp. 1259\u20131267 (2016)","DOI":"10.1109\/CVPR.2016.141"},{"key":"8_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Guo, Y., Jin, Y., Luo, Y., He, Z., Lee, H.: Unsupervised discovery of object landmarks as structural representations. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00285"},{"issue":"5","key":"8_CR75","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1109\/TPAMI.2015.2469286","volume":"38","author":"Z Zhang","year":"2015","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Learning deep representation for face alignment with auxiliary attributes. PAMI 38(5), 918\u2013930 (2015)","journal-title":"PAMI"},{"key":"8_CR76","doi-asserted-by":"crossref","unstructured":"Zhao, D., Song, Z., Ji, Z., Zhao, G., Ge, W., Yu, Y.: Multi-scale matching networks for semantic correspondence. In: ICCV, pp. 3354\u20133364 (2021)","DOI":"10.1109\/ICCV48922.2021.00334"},{"key":"8_CR77","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yuan, B., Wu, H., Yuan, Z., Peng, J., Wang, Y.X.: Pixel contrastive-consistent semi-supervised semantic segmentation. In: ICCV, pp. 7273\u20137282 (2021)","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"8_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20056-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T00:21:27Z","timestamp":1667607687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20056-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200557","9783031200564"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20056-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}