{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:20:29Z","timestamp":1776266429119,"version":"3.50.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198083","type":"print"},{"value":"9783031198090","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\/978-3-031-19809-0_11","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T07:03:04Z","timestamp":1667199784000},"page":"185-202","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Hierarchically Self-supervised Transformer for\u00a0Human Skeleton Representation Learning"],"prefix":"10.1007","author":[{"given":"Yuxiao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Long","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jianbo","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Zhaoyang","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Shijie","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Ligong","family":"Han","sequence":"additional","affiliation":[]},{"given":"Dimitris N.","family":"Metaxas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via gan. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 1418\u20131427 (2018)","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"11_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: A unified 3D human motion synthesis model via conditional variational auto-encoder. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11645\u201311655 (2021)","DOI":"10.1109\/ICCV48922.2021.01144"},{"key":"11_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"11_CR5","unstructured":"Chen, Y., Zhao, L., Peng, X., Yuan, J., Metaxas, D.N.: Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. In: BMVC (2019)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Y.B., Chen, X., Chen, J., Wei, P., Zhang, D., Lin, L.: Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428459"},{"key":"11_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"11_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4346\u20134354 (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"11_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1007\/978-3-030-01225-0_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-Y Gui","year":"2018","unstructured":"Gui, L.-Y., Wang, Y.-X., Liang, X., Moura, J.M.F.: Adversarial geometry-aware human motion prediction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 823\u2013842. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_48"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Video representation learning by dense predictive coding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"11_CR14","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"11_CR15","unstructured":"Hussein, M.E., Torki, M., Gowayyed, M.A., El-Saban, M.: Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. In: Twenty-Third International Joint Conference on Artificial Intelligence (2013)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Kim, T.S., Reiter, A.: Interpretable 3D human action analysis with temporal convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1623\u20131631. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"11_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Uppala, P.K., Radhakrishnan, V.B.: Unsupervised feature learning of human actions as trajectories in pose embedding manifold. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1459\u20131467. IEEE (2019)","DOI":"10.1109\/WACV.2019.00160"},{"key":"11_CR20","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Skeleton-based action recognition with convolutional neural networks. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 597\u2013600. IEEE (2017)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. arXiv preprint arXiv:1804.06055 (2018)","DOI":"10.24963\/ijcai.2018\/109"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, M., Ni, B., Wang, H., Yang, J., Zhang, W.: 3D human action representation learning via cross-view consistency pursuit. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4741\u20134750 (2021)","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"11_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/978-3-319-46478-7_13","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Li","year":"2016","unstructured":"Li, Y., Lan, C., Xing, J., Zeng, W., Yuan, C., Liu, J.: Online human action detection using joint classification-regression recurrent neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 203\u2013220. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_13"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Lin, L., Song, S., Yang, W., Liu, J.: MS2L: multi-task self-supervised learning for skeleton based action recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2490\u20132498 (2020)","DOI":"10.1145\/3394171.3413548"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., Liu, J.: PKU-MMD: a large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017)","DOI":"10.1145\/3132734.3132739"},{"issue":"10","key":"11_CR26","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB + D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M.: Generating smooth pose sequences for diverse human motion prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13309\u201313318 (2021)","DOI":"10.1109\/ICCV48922.2021.01306"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2891\u20132900 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"11_CR29","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":"11_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-030-58529-7_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Nie","year":"2020","unstructured":"Nie, Q., Liu, Z., Liu, Y.: Unsupervised 3D human pose representation with viewpoint and pose disentanglement. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 102\u2013118. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_7"},{"key":"11_CR31","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":"11_CR32","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"11_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-030-68796-0_50","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"C Plizzari","year":"2021","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Spatial temporal transformer network for skeleton-based action recognition. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12663, pp. 694\u2013701. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68796-0_50"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"11_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58571-6_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Si","year":"2020","unstructured":"Si, C., Nie, X., Wang, W., Wang, L., Tan, T., Feng, J.: Adversarial self-supervised learning for semi-supervised 3D action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 35\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_3"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"issue":"7","key":"11_CR41","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: Spatio-temporal attention-based LSTM networks for 3D action recognition and detection. IEEE Trans. Image Process. 27(7), 3459\u20133471 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Su, K., Liu, X., Shlizerman, E.: Predict & cluster: Unsupervised skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9631\u20139640 (2020)","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., Wu, Q.: Self-supervised 3D skeleton action representation learning with motion consistency and continuity. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13328\u201313338 (2021)","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"11_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2014)","DOI":"10.1109\/CVPR.2014.82"},{"issue":"4","key":"11_CR47","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/THMS.2015.2504550","volume":"46","author":"P Wang","year":"2015","unstructured":"Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., Ogunbona, P.O.: Action recognition from depth maps using deep convolutional neural networks. IEEE Trans. Human-Mach. Syst. 46(4), 498\u2013509 (2015)","journal-title":"IEEE Trans. Human-Mach. Syst."},{"key":"11_CR48","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.ins.2018.12.050","volume":"480","author":"Y Xiao","year":"2019","unstructured":"Xiao, Y., Chen, J., Wang, Y., Cao, Z., Zhou, J.T., Bai, X.: Action recognition for depth video using multi-view dynamic images. Inf. Sci. 480, 287\u2013304 (2019)","journal-title":"Inf. Sci."},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lu, S., Er, M.H., Kot, A.C.: Skeleton cloud colorization for unsupervised 3d action representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13423\u201313433 (2021)","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2117\u20132126 (2017)","DOI":"10.1109\/ICCV.2017.233"},{"key":"11_CR53","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":"11_CR54","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., Gong, Z.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10451"}],"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\/978-3-031-19809-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:10:17Z","timestamp":1667434217000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19809-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198083","9783031198090"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19809-0_11","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":"1 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)"}}]}}