{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T22:12:52Z","timestamp":1774476772616,"version":"3.50.1"},"publisher-location":"Cham","reference-count":76,"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_16","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:31:54Z","timestamp":1667417514000},"page":"265-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Unsupervised Visual Representation Learning by\u00a0Synchronous Momentum Grouping"],"prefix":"10.1007","author":[{"given":"Bo","family":"Pang","sequence":"first","affiliation":[]},{"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yaoyi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jia","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., Malik, J.: Learning to see by moving. In: ICCV, pp. 37\u201345 (2015)","DOI":"10.1109\/ICCV.2015.13"},{"key":"16_CR2","unstructured":"Asano, Y.M., Patrick, M., Rupprecht, C., Vedaldi, A.: Labelling unlabelled videos from scratch with multi-modal self-supervision. arXiv preprint arXiv:2006.13662 (2020)"},{"key":"16_CR3","unstructured":"Asano, Y.M., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. arXiv preprint arXiv:1911.05371 (2019)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., Pereira, F., et al.: Analysis of representations for domain adaptation. In: NeurIPS, vol. 19, p. 137 (2007)","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"16_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"16_CR6","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. arXiv preprint arXiv:2104.14294 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"16_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR (2020)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: CVPR, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised visual transformers. arXiv e-prints, p. arXiv\u20132104 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"16_CR12","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. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Doersch, C., Zisserman, A.: Multi-task self-supervised visual learning. In: ICCV, pp. 2051\u20132060 (2017)","DOI":"10.1109\/ICCV.2017.226"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: With a little help from my friends: nearest-neighbor contrastive learning of visual representations. arXiv preprint arXiv:2104.14548 (2021)","DOI":"10.1109\/ICCV48922.2021.00945"},{"issue":"2","key":"16_CR16","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., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"16_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1007\/978-3-030-01225-0_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Fabbri","year":"2018","unstructured":"Fabbri, M., Lanzi, F., Calderara, S., Palazzi, A., Vezzani, R., Cucchiara, R.: Learning to detect and track visible and occluded body joints in a virtual world. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 450\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_27"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Sun, J., Wang, R., Gou, M., Li, Y.L., Lu, C.: InstaBoost: boosting instance segmentation via probability map guided copy-pasting. In: ICCV, pp. 682\u2013691 (2019)","DOI":"10.1109\/ICCV.2019.00077"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: CVPR, pp. 3636\u20133645 (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"16_CR20","unstructured":"Ge, C., Liang, Y., Song, Y., Jiao, J., Wang, J., Luo, P.: Revitalizing CNN attentions via transformers in self-supervised visual representation learning. arXiv preprint arXiv:2110.05340 (2021)"},{"key":"16_CR21","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)"},{"key":"16_CR22","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR26","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"16_CR27","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"16_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448\u2013456. PMLR (2015)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: ICCV, pp. 1413\u20131421 (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"16_CR30","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: CVPR, pp. 1920\u20131929 (2019)","DOI":"10.1109\/CVPR.2019.00202"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: CVPR, pp. 6874\u20136883 (2017)","DOI":"10.1109\/CVPR.2017.96"},{"issue":"7553","key":"16_CR33","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"16_CR35","unstructured":"Li, C., et al.: Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)"},{"key":"16_CR36","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.C.: Prototypical contrastive learning of unsupervised representations. arXiv preprint arXiv:2005.04966 (2020)"},{"key":"16_CR37","unstructured":"Li, Y., Pogodin, R., Sutherland, D.J., Gretton, A.: Self-supervised learning with kernel dependence maximization. arXiv preprint arXiv:2106.08320 (2021)"},{"key":"16_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"16_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01234-2_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Liu","year":"2018","unstructured":"Liu, S., et al.: Switchable temporal propagation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 89\u2013104. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_6"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"16_CR42","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam (2018)"},{"key":"16_CR43","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv preprint arXiv:1605.08104 (2016)"},{"key":"16_CR44","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440 (2015)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Misra, I., Maaten, L.V.D.: Self-supervised learning of pretext-invariant representations. In: CVPR, pp. 6707\u20136717 (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"16_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-319-46448-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"I Misra","year":"2016","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32"},{"key":"16_CR47","unstructured":"Mitrovic, J., McWilliams, B., Walker, J., Buesing, L., Blundell, C.: Representation learning via invariant causal mechanisms. arXiv preprint arXiv:2010.07922 (2020)"},{"key":"16_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Vinjimoor, A., Favaro, P., Pirsiavash, H.: Boosting self-supervised learning via knowledge transfer. In: CVPR, pp. 9359\u20139367 (2018)","DOI":"10.1109\/CVPR.2018.00975"},{"key":"16_CR50","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"2","key":"16_CR51","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199\u2013210 (2010)","journal-title":"IEEE Trans. Neural Netw."},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Pang, B., et al.: Unsupervised representation for semantic segmentation by implicit cycle-attention contrastive learning. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20100"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Qian, Q., Xu, Y., Hu, J., Li, H., Jin, R.: Unsupervised visual representation learning by online constrained k-means. arXiv preprint arXiv:2105.11527 (2021)","DOI":"10.1109\/CVPR52688.2022.01614"},{"key":"16_CR55","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and variational inference in deep latent gaussian models. In: ICML, vol. 2, p. 2. Citeseer (2014)"},{"key":"16_CR56","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML, pp. 843\u2013852. PMLR (2015)"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Sun, J., Fang, H.S., Zhu, X., Li, J., Lu, C.: Correlation field for boosting 3D object detection in structured scenes. In: Proceedings of the AAAI conference on artificial intelligence, vol. 36, no. 1 (2022)","DOI":"10.1609\/aaai.v36i2.20128"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Sun, J., Li, Y., Chai, L., Fang, H.S., Li, Y.L., Lu, C.: Human trajectory prediction with momentary observation. In: CVPR, pp. 6467\u20136476 (2022)","DOI":"10.1109\/CVPR52688.2022.00636"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Tao, C., et al.: Exploring the equivalence of siamese self-supervised learning via a unified gradient framework. arXiv preprint arXiv:2112.05141 (2021)","DOI":"10.1109\/CVPR52688.2022.01403"},{"key":"16_CR60","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? arXiv preprint arXiv:2005.10243 (2020)"},{"key":"16_CR61","unstructured":"Tung, H.F., Tung, H., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. CoRR (2017)"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: ICML, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: CVPR, pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"16_CR64","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. arXiv preprint arXiv:1609.02612 (2016)"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, Z., Yu, S.X.: Unsupervised feature learning by cross-level instance-group discrimination. In: CVPR, pp. 12586\u201312595 (2021)","DOI":"10.1109\/CVPR46437.2021.01240"},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Wei, D., Lim, J.J., Zisserman, A., Freeman, W.T.: Learning and using the arrow of time. In: CVPR, pp. 8052\u20138060 (2018)","DOI":"10.1109\/CVPR.2018.00840"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"16_CR68","unstructured":"Xie, Zet al.: Self-supervised learning with swin transformers. arXiv preprint arXiv:2105.04553 (2021)"},{"key":"16_CR69","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Scaling SGD batch size to 32k for ImageNet training. arXiv preprint arXiv:1708.03888, 6, 12 (2017)"},{"key":"16_CR70","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230 (2021)"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Zhan, X., Xie, J., Liu, Z., Ong, Y.S., Loy, C.C.: Online deep clustering for unsupervised representation learning. In: CVPR, pp. 6688\u20136697 (2020)","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"16_CR72","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. ICLR (2018)"},{"key":"16_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"16_CR74","unstructured":"Zheng, M., et al.: ReSSL: relational self-supervised learning with weak augmentation. arXiv preprint arXiv:2107.09282 (2021)"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Zhai, A.L., Yamins, D.: Local aggregation for unsupervised learning of visual embeddings. In: ICCV, pp. 6002\u20136012 (2019)","DOI":"10.1109\/ICCV.2019.00610"}],"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_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T23:39:39Z","timestamp":1701301179000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20056-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200557","9783031200564"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20056-4_16","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)"}}]}}