{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:10:00Z","timestamp":1774541400994,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030584511","type":"print"},{"value":"9783030584528","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\/978-3-030-58452-8_5","type":"book-chapter","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:34:03Z","timestamp":1604363643000},"page":"71-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Empowering Relational Network by Self-attention Augmented Conditional Random Fields for Group Activity Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-5167","authenticated-orcid":false,"given":"Rizard Renanda Adhi","family":"Pramono","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-1603","authenticated-orcid":false,"given":"Yie Tarng","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6402-2688","authenticated-orcid":false,"given":"Wen Hsien","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"5_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-01249-6_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Qi","year":"2018","unstructured":"Qi, M., Qin, J., Li, A., Wang, Y., Luo, J., Van Gool, L.: stagNet: an attentive semantic RNN for group activity recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 104\u2013120. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_7"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1007\/978-3-030-01219-9_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"MS Ibrahim","year":"2018","unstructured":"Ibrahim, M.S., Mori, G.: Hierarchical relational networks for group activity recognition and retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 742\u2013758. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_44"},{"key":"5_CR3","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":"5_CR4","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":"5_CR5","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":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-642-33765-9_16","volume-title":"Computer Vision \u2013 ECCV 2012","author":"W Choi","year":"2012","unstructured":"Choi, W., Savarese, S.: A unified framework for multi-target tracking and collective activity recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 215\u2013230. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_16"},{"key":"5_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-319-10599-4_37","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MR Amer","year":"2014","unstructured":"Amer, M.R., Lei, P., Todorovic, S.: HiRF: hierarchical random field for collective activity recognition in videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 572\u2013585. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_37"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Hajimirsadeghi, H., Yan, W., Vahdat, A., Mori, G.: Visual recognition by counting instances: a multi-instance cardinality potential kernel. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2596\u20132605 (2015)","DOI":"10.1109\/CVPR.2015.7298875"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Li, X., Chuah, M.C.: 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":"5_CR10","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":"5_CR11","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":"5_CR12","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":"5_CR13","doi-asserted-by":"crossref","unstructured":"Biswas, S., Gall, J.: Structural recurrent neural network (SRNN) for group activity analysis. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1625\u20131632 (2018)","DOI":"10.1109\/WACV.2018.00180"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Butepage, J., Black, M.J., Kragic, D., Kjellstrom, H.: Deep representation learning for human motion prediction and classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6158\u20136166 (2017)","DOI":"10.1109\/CVPR.2017.173"},{"key":"5_CR15","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":"5_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831\u20131840 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"5_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"5_CR19","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)"},{"issue":"1","key":"5_CR20","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1080\/0022250X.1973.9989826","volume":"3","author":"RD Alba","year":"1973","unstructured":"Alba, R.D.: A graph-theoretic definition of a sociometric clique. J. Math. Sociol. 3(1), 113\u2013126 (1973)","journal-title":"J. Math. Sociol."},{"key":"5_CR21","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J., Kaiser, \u0141.: Universal transformers. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"5_CR22","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"5_CR23","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"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 3468\u20133476 (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"5_CR25","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"},{"issue":"1","key":"5_CR26","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Wei, X., Yang, M., Kai, Yu.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR27","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":"5_CR28","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"5_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"5_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-030-01219-9_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Li","year":"2018","unstructured":"Li, X., Loy, C.C.: Video object segmentation with joint re-identification and attention-aware mask propagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 93\u2013110. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_6"},{"key":"5_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-01231-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Zhang","year":"2018","unstructured":"Zhang, G., Kan, M., Shan, S., Chen, X.: Generative adversarial network with spatial attention for face attribute editing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 422\u2013437. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_26"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, T., Wu, X.: Pyramid feature attention network for saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3085\u20133094 (2019)","DOI":"10.1109\/CVPR.2019.00320"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Loy, C.C., Xiang, T., Gong, S.: Modelling activity global temporal dependencies using time delayed probabilistic graphical model. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 120\u2013127 (2009)","DOI":"10.1109\/ICCV.2009.5459156"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Swears, E., Hoogs, A., Ji, Q., Boyer, K.: Complex activity recognition using granger constrained DBN (GCDBN) in sports and surveillance video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 788\u2013795 (2014)","DOI":"10.1109\/CVPR.2014.106"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Lu, Y., Lu, C., Tang, C.-K.: Online video object detection using association LSTM. In: Proceedings of The IEEE International Conference on Computer Vision, pp. 2344\u20132352 (2017)","DOI":"10.1109\/ICCV.2017.257"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: LSTM pose machines. In: Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, pp. 7852\u20137861 (2018)","DOI":"10.1109\/CVPR.2018.00546"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Perrett, T., Damen, D.: DDLSTM: dual-domain LSTM for cross-dataset action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5207\u20135215 (2019)","DOI":"10.1109\/CVPR.2019.00804"},{"key":"5_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSP.2019.2923918","volume":"26","author":"D Purwanto","year":"2019","unstructured":"Purwanto, D., Pramono, R.R.A., Chen, Y.-T., Fang, W.-H.: Three-stream network with bidirectional self-attention for action recognition in extreme low resolution videos. IEEE Signal Process. Lett. 26, 1 (2019)","journal-title":"IEEE Signal Process. Lett."},{"key":"5_CR40","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":"5_CR41","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. arXiv preprint arXiv:1904.01766 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"5_CR42","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":"5_CR43","doi-asserted-by":"crossref","unstructured":"Pramono, R.R.A., Chen, Y.-T., Fang, W.-H.: Hierarchical self-attention network for action localization in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 61\u201370 (2019)","DOI":"10.1109\/ICCV.2019.00015"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Morariu, V.I., Davis, L.S.: Multi-agent event recognition in structured scenarios. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133296 (2011)","DOI":"10.1109\/CVPR.2011.5995386"},{"issue":"3","key":"5_CR45","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1006\/cviu.2000.0896","volume":"81","author":"SS Intille","year":"2001","unstructured":"Intille, S.S., Bobick, A.F.: Recognizing planned, multiperson action. Comput. Vis. Image Underst. 81(3), 414\u2013445 (2001)","journal-title":"Comput. Vis. Image Underst."},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Xu, Y., Qin, L., Liu, X., Xie, J., Zhu, S.-C.: A causal and-or graph model for visibility fluent reasoning in tracking interacting objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2178\u20132187 (2018)","DOI":"10.1109\/CVPR.2018.00232"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Li, W.-H., Hong, F.-T., Zheng, W.-S.: Learning to learn relation for important people detection in still images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5003\u20135011 (2019)","DOI":"10.1109\/CVPR.2019.00514"},{"key":"5_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Xie, S., Tai, Y.-W., Lu, C.: RMPE: regional multi-person pose estimation, pp. 2334\u20132343 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"5_CR51","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the International Conference on Machine Learning (2001)"},{"key":"5_CR52","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 109\u2013117 (2011)"},{"key":"5_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-319-46475-6_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Arnab","year":"2016","unstructured":"Arnab, A., Jayasumana, S., Zheng, S., Torr, P.H.S.: Higher order conditional random fields in deep neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 524\u2013540. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_33"},{"key":"5_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-319-46466-4_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"B Liu","year":"2016","unstructured":"Liu, B., He, X.: Learning dynamic hierarchical models for anytime scene labeling. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 650\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_39"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: UPSNet: a unified panoptic segmentation network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8818\u20138826 (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"5_CR56","unstructured":"Graves, A.: Adaptive computation time for recurrent neural networks. arXiv preprint arXiv:1603.08983 (2016)"},{"key":"5_CR57","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 International Conference on Computer Vision Workshops, pp. 1282\u20131289 (2009)","DOI":"10.1109\/ICCVW.2009.5457461"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Proceedings of the Joint Pattern Recognition Symposium, pp. 214\u2013223 (2007)","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"5_CR59","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press, Cambridge (2016)"},{"issue":"8","key":"5_CR60","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."}],"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\/978-3-030-58452-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:04:29Z","timestamp":1730592269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58452-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030584511","9783030584528"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58452-8_5","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":"3 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.","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)"}}]}}