{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:02:44Z","timestamp":1776092564149,"version":"3.50.1"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585440","type":"print"},{"value":"9783030585457","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58545-7_11","type":"book-chapter","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T10:04:51Z","timestamp":1604484291000},"page":"177-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos"],"prefix":"10.1007","author":[{"given":"Mahsa","family":"Ehsanpour","sequence":"first","affiliation":[]},{"given":"Alireza","family":"Abedin","sequence":"additional","affiliation":[]},{"given":"Fatemeh","family":"Saleh","sequence":"additional","affiliation":[]},{"given":"Javen","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Reid","sequence":"additional","affiliation":[]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,5]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Xie, D., Zhao, M., Todorovic, S., Zhu, S.C.: Cost-sensitive top-down\/bottom-up inference for multiscale activity recognition. In: Proceedings of the European Conference on Computer Vision, pp. 187\u2013200 (2012)","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Lei, P., Todorovic, S.: Hirf: hierarchical random field for collective activity recognition in videos. In: Proceedings of the European Conference on Computer Vision, pp. 572\u2013585 (2014)","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Azar, S.M., Atigh, M.G., Nickabadi, A., Alahi, A.: Convolutional relational machine for group activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7892\u20137901 (2019)","DOI":"10.1109\/CVPR.2019.00808"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Bagautdinov, T., Alahi, A., Fleuret, F., Fua, P., Savarese, S.: Social scene understanding: end-to-end multi-person action localization and collective activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4315\u20134324 (2017)","DOI":"10.1109\/CVPR.2017.365"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y.W., Pantofaru, C., Savarese, S.: Discovering groups of people in images. In: Proceedings of the European Conference on Computer Vision, pp. 417\u2013433 (2014)","DOI":"10.1007\/978-3-319-10593-2_28"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: Proceedings of the European Conference on Computer Vision, pp. 215\u2013230 (2012)","DOI":"10.1007\/978-3-642-33765-9_16"},{"issue":"6","key":"11_CR9","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1109\/TPAMI.2013.220","volume":"36","author":"W Choi","year":"2013","unstructured":"Choi, W., Savarese, S.: Understanding collective activities of people from videos. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1242\u20131257 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: collective activity classification using spatio-temporal relationship among people. In: Proceedings of the IEEE 12th International Conference on Computer Vision Workshops, pp. 1282\u20131289 (2009)","DOI":"10.1109\/ICCVW.2009.5457461"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Choi, W., Shahid, K., Savarese, S.: Learning context for collective activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133280 (2011)","DOI":"10.1109\/CVPR.2011.5995707"},{"issue":"8","key":"11_CR12","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TPAMI.2000.868676","volume":"22","author":"RT Collins","year":"2000","unstructured":"Collins, R.T., Lipton, A.J., Kanade, T.: Introduction to the special section on video surveillance. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 745\u2013746 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Deng, Z., Vahdat, A., Hu, H., Mori, G.: Structure inference machines: recurrent neural networks for analyzing relations in group activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4772\u20134781 (2016)","DOI":"10.1109\/CVPR.2016.516"},{"key":"11_CR14","unstructured":"Deng, Z., et al.: Deep structured models for group activity recognition. arXiv preprint arXiv:1506.04191 (2015)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"issue":"2","key":"11_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. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems, pp. 3468\u20133476 (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"issue":"5","key":"11_CR20","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TPAMI.2011.176","volume":"34","author":"W Ge","year":"2012","unstructured":"Ge, W., Collins, R.T., Ruback, R.B.: Vision-based analysis of small groups in pedestrian crowds. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 1003\u20131016 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR21","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: A better baseline for ava. arXiv preprint arXiv:1807.10066 (2018)"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Hung, H., Kr\u00f6se, B.: Detecting f-formations as dominant sets. In: Proceedings of the 13th International Conference on Multimodal Interfaces, pp. 231\u2013238 (2011)","DOI":"10.1145\/2070481.2070525"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Mori, G.: Hierarchical relational networks for group activity recognition and retrieval. In: Proceedings of the European Conference on Computer Vision, pp. 721\u2013736 (2018)","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Muralidharan, S., Deng, Z., Vahdat, A., Mori, G.: A hierarchical deep temporal model for group activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1971\u20131980 (2016)","DOI":"10.1109\/CVPR.2016.217"},{"key":"11_CR28","unstructured":"The multiview extended video with activities (MEVA) dataset. https:\/\/mevadata.org\/"},{"key":"11_CR29","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"issue":"1","key":"11_CR30","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"11_CR31","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TPAMI.2017.2782743","volume":"41","author":"H Joo","year":"2017","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social interaction capture. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 190\u2013204 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR32","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"11_CR33","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"issue":"12","key":"11_CR34","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1016\/j.robot.2013.05.007","volume":"61","author":"T Kruse","year":"2013","unstructured":"Kruse, T., Pandey, A.K., Alami, R., Kirsch, A.: Human-aware robot navigation: a survey. Robot. Auton. Syst. 61(12), 1726\u20131743 (2013)","journal-title":"Robot. Auton. Syst."},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Lan, T., Sigal, L., Mori, G.: Social roles in hierarchical models for human activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1354\u20131361 (2012)","DOI":"10.1109\/CVPR.2012.6247821"},{"issue":"8","key":"11_CR37","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1109\/TPAMI.2011.228","volume":"34","author":"T Lan","year":"2011","unstructured":"Lan, T., Wang, Y., Yang, W., Robinovitch, S.N., Mori, G.: Discriminative latent models for recognizing contextual group activities. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1549\u20131562 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Li, D., Qiu, Z., Dai, Q., Yao, T., Mei, T.: Recurrent tubelet proposal and recognition networks for action detection. In: Proceedings of the European Conference on Computer Vision, pp. 303\u2013318 (2018)","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"11_CR39","unstructured":"Li, W., Chang, M.C., Lyu, S.: Who did what at where and when: simultaneous multi-person tracking and activity recognition. arXiv preprint arXiv:1807.01253 (2018)"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Li, X., Choo Chuah, M.: SBGAR: semantics based group activity recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2876\u20132885 (2017)","DOI":"10.1109\/ICCV.2017.313"},{"key":"11_CR41","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.: VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"11_CR42","unstructured":"Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Advances in Neural Information Processing Systems, pp. 849\u2013856 (2002)"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Patron-Perez, A., Marszalek, M., Zisserman, A., Reid, I.D.: High five: recognising human interactions in TV shows. In: BMVC, vol. 1, p. 33 (2010)","DOI":"10.5244\/C.24.50"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Qi, M., Qin, J., Li, A., Wang, Y., Luo, J., Van Gool, L.: stagNet: an attentive semantic RNN for group activity recognition. In: Proceedings of the European Conference on Computer Vision, pp. 101\u2013117 (2018)","DOI":"10.1007\/978-3-030-01249-6_7"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Huang, J., Abu-El-Haija, S., Gorban, A., Murphy, K., Fei-Fei, L.: Detecting events and key actors in multi-person videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3043\u20133053 (2016)","DOI":"10.1109\/CVPR.2016.332"},{"key":"11_CR46","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Setti, F., Lanz, O., Ferrario, R., Murino, V., Cristani, M.: Multi-scale f-formation discovery for group detection. In: Proceedings of the IEEE International Conference on Image Processing, pp. 3547\u20133551 (2013)","DOI":"10.1109\/ICIP.2013.6738732"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Shu, T., Todorovic, S., Zhu, S.C.: CERN: confidence-energy recurrent network for group activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5523\u20135531 (2017)","DOI":"10.1109\/CVPR.2017.453"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Shu, T., Xie, D., Rothrock, B., Todorovic, S., Chun Zhu, S.: Joint inference of groups, events and human roles in aerial videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4576\u20134584 (2015)","DOI":"10.1109\/CVPR.2015.7299088"},{"key":"11_CR50","unstructured":"Shu, X., Tang, J., Qi, G., Liu, W., Yang, J.: Hierarchical long short-term concurrent memory for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2019)"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Divvala, S., Farhadi, A., Gupta, A.: Asynchronous temporal fields for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 585\u2013594 (2017)","DOI":"10.1109\/CVPR.2017.599"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Proceedings of the European Conference on Computer Vision, pp. 510\u2013526 (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"11_CR53","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"11_CR54","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"11_CR55","doi-asserted-by":"publisher","first-page":"102799","DOI":"10.1016\/j.cviu.2019.102799","volume":"188","author":"A Stergiou","year":"2019","unstructured":"Stergiou, A., Poppe, R.: Analyzing human-human interactions: a survey. Comput. Vis. Image Underst. 188, 102799 (2019)","journal-title":"Comput. Vis. Image Underst."},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Proceedings of the European Conference on Computer Vision, pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Swofford, M., Peruzzi, J.C., V\u00e1zquez, M., Mart\u00edn-Mart\u00edn, R., Savarese, S.: DANTE: deep affinity network for clustering conversational interactants. arXiv preprint arXiv:1907.12910 (2019)","DOI":"10.1145\/3392824"},{"key":"11_CR58","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_CR59","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"11_CR60","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks (2017)"},{"key":"11_CR61","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the Proceedings of the European Conference on Computer Vision, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Wang, M., Ni, B., Yang, X.: Recurrent modeling of interaction context for collective activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3048\u20133056 (2017)","DOI":"10.1109\/CVPR.2017.783"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"11_CR64","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"11_CR65","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, L., Wang, L., Guo, J., Wu, G.: Learning actor relation graphs for group activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9964\u20139974 (2019)","DOI":"10.1109\/CVPR.2019.01020"},{"key":"11_CR66","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp. 478\u2013487 (2016)"},{"key":"11_CR67","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783\u20135792 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"11_CR68","unstructured":"Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: Advances in Neural Information Processing Systems, pp. 1601\u20131608 (2005)"},{"key":"11_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision, pp. 803\u2013818 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58545-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T01:08:53Z","timestamp":1730682533000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58545-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585440","9783030585457"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58545-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"5 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}