{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:30:48Z","timestamp":1788049848828,"version":"build-2784847793"},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Basic scientific research projects of Liaoning Provincial Department of Education of China","award":["LJKZ0146"],"award-info":[{"award-number":["LJKZ0146"]}]},{"name":"the Applied Basic Research Program of Liaoning Provincial Department of Science and Technology of China","award":["2022JH2\/101300245"],"award-info":[{"award-number":["2022JH2\/101300245"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03479-z","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T16:26:03Z","timestamp":1717086363000},"page":"1733-1755","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A comprehensive review of deep learning approaches for group activity analysis"],"prefix":"10.1007","volume":"41","author":[{"given":"Gang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao G.","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"3479_CR1","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/s00371-018-1499-5","volume":"35","author":"G Tripathi","year":"2018","unstructured":"Tripathi, G., Singh, K., Vishwakarma, D.K.: Convolutional neural networks for crowd behavior analysis: a survey. Vis. Comput.Comput. 35, 753\u2013776 (2018)","journal-title":"Vis. Comput.Comput."},{"key":"3479_CR2","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.neucom.2015.11.021","volume":"177","author":"VJ Kok","year":"2016","unstructured":"Kok, V.J., Lim, M.K., Chan, C.S.: Crowd behavior analysis: a review where physics meets biology. Neurocomputing 177, 342\u2013362 (2016)","journal-title":"Neurocomputing"},{"key":"3479_CR3","unstructured":"Sharif, M.H., Jiao, L., Omlin C.W.: Deep crowd anomaly detection: state-of-the-art, challenges, and future research directions. https:\/\/arxiv.org\/pdf\/2210.13927.pdf."},{"key":"3479_CR4","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TPAMI.2021.3107160","volume":"44","author":"P Koniusz","year":"2022","unstructured":"Koniusz, P., Wang, L., Cherian, A.: Tensor representations for action recognition. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 44, 648\u2013665 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0010047","volume":"5","author":"M Moussa\u00efd","year":"2010","unstructured":"Moussa\u00efd, M., Perozo, N., Garnier, S., et al.: The walking behaviour of pedestrian social groups and its impact on crowd dynamics. PLoS ONE 5, e10047 (2010)","journal-title":"PLoS ONE"},{"key":"3479_CR6","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TCSVT.2014.2358029","volume":"25","author":"T Li","year":"2015","unstructured":"Li, T., Chang, H., Wang, M., et al.: Crowded scene analysis: a survey. IEEE Trans. Circuits Syst. Video Technol. 25, 367\u2013386 (2015)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3479_CR7","doi-asserted-by":"crossref","unstructured":"Shu, T., Todorovic, S., Zhu, S.C.: CERN: confidence-energy recurrent network for group activity recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4255\u20134263 (2017)","DOI":"10.1109\/CVPR.2017.453"},{"key":"3479_CR8","first-page":"1","volume":"4","author":"M Bendali-Braham","year":"2021","unstructured":"Bendali-Braham, M., Weber, J., Forestier, G., et al.: Recent trends in crowd analysis: a review. Mach. Learn. Appl. 4, 1\u201330 (2021)","journal-title":"Mach. Learn. Appl."},{"key":"3479_CR9","doi-asserted-by":"crossref","unstructured":"Borja-Borja, L.F., Saval-Calvo, M., Azorin-Lopez, J.: Machine learning methods from group to crowd behaviour analysis. In: Rojas, I., Joya, G., Catala, A. (eds.) Advances in Computational Intelligence, pp. 294\u2013305 (2017)","DOI":"10.1007\/978-3-319-59147-6_26"},{"key":"3479_CR10","first-page":"2018","volume":"50","author":"HG Deng","year":"2022","unstructured":"Deng, H.G., Wang, C.X., Li, C.W., et al.: Summarization of group activity recognition algorithms based on deep learning frame. Acta Electron. Sin. Electron. Sin. 50, 2018\u20132036 (2022)","journal-title":"Acta Electron. Sin. Electron. Sin."},{"key":"3479_CR11","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/s11633-020-1258-8","volume":"18","author":"LF Wu","year":"2021","unstructured":"Wu, L.F., Wang, Q., Jian, M., et al.: A comprehensive review of group activity recognition in videos. Int. J. Autom. Comput.Autom. Comput. 18, 334\u2013350 (2021)","journal-title":"Int. J. Autom. Comput.Autom. Comput."},{"key":"3479_CR12","first-page":"964","volume":"34","author":"JC Wu","year":"2023","unstructured":"Wu, J.C., Wang, L.M., Wu, G.S.: Group activity recognition in videos: a survey. J. Softw. 34, 964\u2013984 (2023)","journal-title":"J. Softw."},{"key":"3479_CR13","doi-asserted-by":"publisher","first-page":"43947","DOI":"10.1007\/s11042-022-13227-x","volume":"81","author":"S Waqar","year":"2022","unstructured":"Waqar, S., Khan, U.G., Waseem, M.H., et al.: The utility of datasets in crowd modelling and analysis: a survey. Multimed. Tools Appl. 81, 43947\u201343978 (2022)","journal-title":"Multimed. Tools Appl."},{"key":"3479_CR14","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.1073\/pnas.0711437105","volume":"105","author":"M Ballerini","year":"2008","unstructured":"Ballerini, M., Cabibbo, N., Candelier, R., et al.: Interaction ruling animal collective behavior depends on topological rather than metric distance: evidence from a field study. Proc. Natl. Acad. Sci. U. S. A. 105, 1232\u20131237 (2008)","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"3479_CR15","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/TPAMI.2018.2875002","volume":"42","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Chen, M.L., Nie, F.P., et al.: Detecting coherent groups in crowd scenes by Multiview clustering. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 42, 46\u201358 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR16","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TPAMI.2011.176","volume":"34","author":"WN Ge","year":"2012","unstructured":"Ge, W.N., Collins, R.T., Ruback, R.B.: Vision-based analysis of small groups in pedestrian crowds. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 34, 1003\u20131016 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR17","volume-title":"Social Identity and Intergroup Relations","author":"JC Turner","year":"1982","unstructured":"Turner, J.C.: Towards a cognitive redefinition of the social group. In: Tajfel, H. (ed.) Social Identity and Intergroup Relations. Cambridge University Press, Cambridge, England (1982)"},{"key":"3479_CR18","doi-asserted-by":"publisher","first-page":"4283","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing, D., Moln\u00e1r, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51, 4283\u20134286 (1995)","journal-title":"Phys. Rev. E"},{"key":"3479_CR19","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1109\/TPAMI.2015.2470658","volume":"38","author":"F Solera","year":"2016","unstructured":"Solera, F., Calderara, S., Cucchiara, R.: Socially constrained structural learning for groups detection in crowd. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 38, 995\u20131008 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR20","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1023\/B:MACH.0000033116.57574.95","volume":"56","author":"N Bansal","year":"2004","unstructured":"Bansal, N., Blum, A., Chawla, S.: Correlation clustering. Mach. Learn. 56, 89\u2013113 (2004)","journal-title":"Mach. Learn."},{"key":"3479_CR21","doi-asserted-by":"publisher","first-page":"3624","DOI":"10.1109\/TIP.2015.2447836","volume":"24","author":"M Niknejad","year":"2015","unstructured":"Niknejad, M., Rabbani, H., Babaie-Zadeh, M.: Image restoration using Gaussian mixture models with spatially constrained patch clustering. IEEE Trans. Image Process. 24, 3624\u20133636 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"3479_CR22","doi-asserted-by":"publisher","first-page":"424","DOI":"10.2307\/1912791","volume":"37","author":"CWJ Granger","year":"1969","unstructured":"Granger, C.W.J.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37, 424\u2013438 (1969)","journal-title":"Econometrica"},{"key":"3479_CR23","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, pp. 359\u2013370 (1994)"},{"key":"3479_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Han, R., Yan, H., et al.: Self-supervised social relation representation for human group detection. In: Proceedings of European Conference on Computer Vision, pp. 142\u2013159 (2022)","DOI":"10.1007\/978-3-031-19833-5_9"},{"key":"3479_CR25","doi-asserted-by":"crossref","unstructured":"Artacho, B., Savakis, A.: UniPose: unified human pose estimation in single images and videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7033\u20137042 (2020)","DOI":"10.1109\/CVPR42600.2020.00706"},{"key":"3479_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, pp. 5999\u20136009 (2017)"},{"key":"3479_CR27","doi-asserted-by":"crossref","unstructured":"Zhan, X., Liu, Z., Yan, J., et al. Consensus-driven propagation in massive unlabeled data for face recognition. In: Proceedings of European Conference on Computer Vision, pp. 576\u2013592 (2018)","DOI":"10.1007\/978-3-030-01240-3_35"},{"key":"3479_CR28","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Qian, K., Elhoseiny, M., et al. Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 14412\u201314420 (2020)","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"3479_CR29","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., et al. Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 180\u2013189 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"3479_CR30","doi-asserted-by":"crossref","unstructured":"Mei, L., Lai, J.H., Chen, Z.Y., et al. Measuring crowd collectiveness via global motion correlation. In: Proceedings of IEEE\/CVF International Conference on Computer Vision Workshop, pp. 1222\u20131231 (2019)","DOI":"10.1109\/ICCVW.2019.00155"},{"key":"3479_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, Y.F.: Metal: minimum effort temporal activity localization in untrimmed videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3881\u20133891 (2020)","DOI":"10.1109\/CVPR42600.2020.00394"},{"key":"3479_CR32","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: Adversarial background-aware loss for weakly-supervised temporal activity localization. In: Proceedings of European Conference on Computer Vision, pp. 283\u2013299 (2020)","DOI":"10.1007\/978-3-030-58568-6_17"},{"issue":"10","key":"3479_CR33","doi-asserted-by":"publisher","first-page":"6209","DOI":"10.1109\/TPAMI.2021.3090167","volume":"44","author":"RH Zeng","year":"2022","unstructured":"Zeng, R.H., Huang, W.B., Tan, M.K., et al.: Graph convolutional module for temporal action localization in videos. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 44(10), 6209\u20136223 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR34","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"3479_CR35","unstructured":"Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1025\u20131035 (2017)"},{"key":"3479_CR36","first-page":"3019","volume":"45","author":"T Zhao","year":"2023","unstructured":"Zhao, T., Han, J., Yang, L., et al.: Equivalent classification mapping for weakly supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 45, 3019\u20133031 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR37","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"SQ Ren","year":"2017","unstructured":"Ren, S.Q., He, K.M., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 39, 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR38","doi-asserted-by":"publisher","first-page":"4477","DOI":"10.1109\/TPAMI.2020.2997860","volume":"43","author":"R Su","year":"2021","unstructured":"Su, R., Xu, D., Zhou, L.P., et al.: Progressive cross-stream cooperation in spatial and temporal domain for action localization. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 43, 4477\u20134490 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR39","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1109\/TETCI.2019.2897815","volume":"5","author":"M Tzelepi","year":"2021","unstructured":"Tzelepi, M., Tefas, A.: Graph embedded convolutional neural networks in human crowd detection for drone flight safety. IEEE Trans. Emerg. Top. Comput. Intell. 5, 191\u2013204 (2021)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"3479_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Dang, K., Lai, J.H., et al: Modeling 3d layout for group re-identification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7502\u20137510 (2022)","DOI":"10.1109\/CVPR52688.2022.00736"},{"key":"3479_CR41","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/TPAMI.2017.2687462","volume":"40","author":"A Dehghan","year":"2018","unstructured":"Dehghan, A., Shah, M.: Binary quadratic programing for online tracking of hundreds of people in extremely crowded scenes. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 40, 568\u2013581 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR42","doi-asserted-by":"publisher","first-page":"5571","DOI":"10.1109\/TIP.2020.2985284","volume":"29","author":"XL Li","year":"2020","unstructured":"Li, X.L., Chen, M.L., Wang, Q.: Quantifying and detecting collective motion in crowd scenes. IEEE Trans. Image Process. 29, 5571\u20135583 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3479_CR43","doi-asserted-by":"publisher","first-page":"7574","DOI":"10.1109\/TNNLS.2021.3085567","volume":"33","author":"R Yan","year":"2022","unstructured":"Yan, R., Shu, X.B., Yuan, C.C., et al.: Position-aware participation-contributed temporal dynamic model for group activity recognition. IEEE Trans. Neural Netw. Learn. Syst. 33, 7574\u20137588 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3479_CR44","doi-asserted-by":"crossref","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Proceedings of European Conference on Computer Vision, pp. 744\u2013759 (2016)","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"3479_CR45","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding?. In: Proceedings of International Conference on Machine Learning, pp. 1\u201313 (2021)"},{"key":"3479_CR46","unstructured":"Duta, I., Nicolicioiu, A., Leordeanu, M.: Discovering dynamic salient regions for spatio-temporal graph neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 7111\u20137125 (2021)"},{"issue":"6","key":"3479_CR47","doi-asserted-by":"publisher","first-page":"9280","DOI":"10.1109\/JIOT.2019.2911669","volume":"6","author":"Z Gao","year":"2019","unstructured":"Gao, Z., Xuan, H.Z., Zhang, H., et al.: Adaptive fusion and category-level dictionary learning model for multiview human action recognition. IEEE Internet Things J. 6(6), 9280\u20139293 (2019)","journal-title":"IEEE Internet Things J."},{"key":"3479_CR48","doi-asserted-by":"crossref","unstructured":"Ehsanpour, M., Abedin, A., Saleh, F., et al.: Joint learning of social groups, individuals action and sub-group activities in videos. In: Proceedings of European Conference on Computer Vision, pp. 177\u2013195 (2020)","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"3479_CR49","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"3479_CR50","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., et al.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"3479_CR51","unstructured":"Kay, W., Carreira, J., Simonyan, K., et al.: The Kinetics Human Action Video Dataset. https:\/\/arxiv.org\/pdf\/1705.06950.pdf."},{"key":"3479_CR52","unstructured":"Yan, R., Xie, L., Tang, J., et al.: HiGCIN: hierarchical graph-based cross inference network for group activity recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"3479_CR53","doi-asserted-by":"crossref","unstructured":"Yuan, H., Ni, D., Wang, M.: Spatio-temporal dynamic inference network for group activity recognition. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp. 7456\u20137465 (2021)","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"3479_CR54","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1109\/TNNLS.2020.2978942","volume":"32","author":"XB Shu","year":"2021","unstructured":"Shu, X.B., Zhang, L.Y., Sun, Y.L., et al.: Host-parasite: graph LSTM-in-LSTM for group activity recognition. IEEE Trans. Neural Netw. Learn. Syst. 32, 663\u2013674 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3479_CR55","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1109\/TPAMI.2019.2928540","volume":"44","author":"JH Tang","year":"2022","unstructured":"Tang, J.H., Shu, X.B., Yan, R., et al.: Coherence constrained graph LSTM for group activity recognition. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 44, 636\u2013647 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR56","doi-asserted-by":"crossref","unstructured":"Deng, Z., Vahdat, A., Hu, H., et al.: Structure inference machines: recurrent neural networks for analyzing relations in group activity recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4772\u20134781 (2016)","DOI":"10.1109\/CVPR.2016.516"},{"key":"3479_CR57","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, L., Wang, L., et al. Learning actor relation graphs for group activity recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 9956\u20139966 (2019)","DOI":"10.1109\/CVPR.2019.01020"},{"key":"3479_CR58","doi-asserted-by":"crossref","unstructured":"Han, R., Yan, H., Li, J., et al.: Panoramic human activity recognition. In: Proceedings of European Conference on Computer Vision, pp. 244\u2013261 (2022)","DOI":"10.1007\/978-3-031-19772-7_15"},{"key":"3479_CR59","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 39, 640\u2013651 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR60","doi-asserted-by":"crossref","unstructured":"Han, M., Zhang, D.J., Wang, Y., et al.: Dual-ai: dual-path actor interaction learning for group activity recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2980\u20132989 (2022)","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"3479_CR61","doi-asserted-by":"crossref","unstructured":"Kwon, H., Kim, M., Kwak, S., et al.: Motionsqueeze: neural motion feature learning for video understanding. In: Proceedings of European Conference on Computer Vision, pp. 345\u2013362 (2020)","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"3479_CR62","doi-asserted-by":"crossref","unstructured":"Kim, D., Lee, J., Cho, M., et al.: Detector-free weakly supervised group activity recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20051\u201320061 (2022)","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"3479_CR63","doi-asserted-by":"crossref","unstructured":"Tamura, M., Vishwakarma, R., Vennelakanti, R.: Hunting group clues with transformers for social group activity recognition. In: Proceedings of the 17th European Conference on European Conference on Computer Vision, pp. 19\u201335 (2022)","DOI":"10.1007\/978-3-031-19772-7_2"},{"key":"3479_CR64","unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of the 9th International Conference on Learning Representations, pp. 1\u201316 (2021)"},{"key":"3479_CR65","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1002\/nav.20053","volume":"52","author":"HW Kuhn","year":"2005","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist.Logist. 52, 7\u201321 (2005)","journal-title":"Nav. Res. Logist.Logist."},{"key":"3479_CR66","doi-asserted-by":"crossref","unstructured":"Li, S., Cao, Q., Liu, L., et al.: GroupFormer: group activity recognition with clustered spatialtemporal transformer. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 13648\u201313657 (2021)","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"3479_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, R., Zhou, H., Gao, H., et al. Grouptron: dynamic multi-scale graph convolutional networks for group-aware dense crowd trajectory forecasting. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 805\u2013811 (2022)","DOI":"10.1109\/ICRA46639.2022.9811585"},{"key":"3479_CR68","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Muralidharan, S., Deng, Z., et al.: A hierarchical deep temporal model for group activity recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1971\u20131980 (2016)","DOI":"10.1109\/CVPR.2016.217"},{"key":"3479_CR69","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TKDE.2020.3008774","volume":"34","author":"JK Sun","year":"2022","unstructured":"Sun, J.K., Zhang, J.B., Li, Q.F., et al.: Predicting citywide crowd flows in irregular regions using multi-view graph convolutional networks. IEEE Trans. Knowl. Data Eng.ta Eng. 34, 2348\u20132359 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng.ta Eng."},{"key":"3479_CR70","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., et al.: Social LSTM: human trajectory prediction in crowded spaces. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013971 (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"3479_CR71","unstructured":"Graves, A.: Generating sequences with recurrent neural networks (2014). https:\/\/arxiv.org\/pdf\/1308.0850.pdf."},{"key":"3479_CR72","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Li, F.F., et al.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2255\u20132264 (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"3479_CR73","unstructured":"Qi, C.R., Su, H., Mo, K., et al.: PointNet: deep learning on point sets for 3d classification and segmentation (2017). https:\/\/arxiv.org\/pdf\/1612.00593.pdf."},{"key":"3479_CR74","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.: A point set generation network for 3D object reconstruction from a single image (2016). https:\/\/arxiv.org\/pdf\/1612.00603.pdf.","DOI":"10.1109\/CVPR.2017.264"},{"key":"3479_CR75","doi-asserted-by":"crossref","unstructured":"Bae, I., Park, J.H., Jeon, H.G.: Learning pedestrian group representations for multi-modal trajectory prediction. In: Proceedings of European Conference on Computer Vision, pp. 270\u2013289 (2022)","DOI":"10.1007\/978-3-031-20047-2_16"},{"key":"3479_CR76","doi-asserted-by":"crossref","unstructured":"Yu, C., Ma, X., Ren, J., et al.: Spatio-temporal graph transformer networks for pedestrian trajectory prediction. In: Proceedings of European Conference on Computer Vision, pp. 507\u2013523 (2020)","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"3479_CR77","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1109\/TMM.2019.2908350","volume":"21","author":"J Li","year":"2019","unstructured":"Li, J., Wei, L.S., Zhang, F.B., et al.: Joint deep and depth for object-level segmentation and stereo tracking in crowds. IEEE Trans. Multimed. 21, 2531\u20132544 (2019)","journal-title":"IEEE Trans. Multimed."},{"key":"3479_CR78","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2008","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 30, 328\u2013341 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR79","doi-asserted-by":"crossref","unstructured":"Dupont, C., Tob\u00edas, L., Luvison, B.: Crowd-11: a dataset for fine grained crowd behaviour analysis. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2184\u20132191 (2017)","DOI":"10.1109\/CVPRW.2017.271"},{"key":"3479_CR80","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s11263-020-01365-4","volume":"129","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Gao, J., Lin, W., et al.: Pixel-wise crowd understanding via synthetic data. Int. J. Comput. Vis.Comput. Vis. 129, 225\u2013245 (2021)","journal-title":"Int. J. Comput. Vis.Comput. Vis."},{"key":"3479_CR81","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, J., Lin, W., et al.: Learning from synthetic data for crowd counting in the wild. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 8190\u20138199 (2019)","DOI":"10.1109\/CVPR.2019.00839"},{"key":"3479_CR82","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TPAMI.2020.3043372","volume":"44","author":"LY Chai","year":"2022","unstructured":"Chai, L.Y., Liu, Y.T., Liu, W.X., et al.: CrowdGAN: identity-free interactive crowd video generation and beyond. IEEE Trans. Pattern Anal. Mach. Intell.Intell. 44, 2856\u20132871 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"3479_CR83","doi-asserted-by":"crossref","unstructured":"Shao, J., Kang, K., Loy, C.C., et al.: Deeply learned attributes for crowd scene understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4657\u20134666 (2015)","DOI":"10.1109\/CVPR.2015.7299097"},{"key":"3479_CR84","doi-asserted-by":"crossref","unstructured":"Shao, J., Loy, C.C., Wang X.: Scene-independent group profiling in crowd. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2227\u20132234 (2014)","DOI":"10.1109\/CVPR.2014.285"},{"key":"3479_CR85","doi-asserted-by":"crossref","unstructured":"Hassner, T., Itcher, Y., Kliper-Gross, O.: Violent flows: real-time detection of violent crowd behavior. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1\u20136 (2012)","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"3479_CR86","unstructured":"Zhang, C., Li, H., Wang, X., et al.: Cross-scene crowd counting via deep convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 833\u2013841 (2015)"},{"key":"3479_CR87","unstructured":"Allain, P., Courty, N., Corpetti, T.: AGORASET: a dataset for crowd video analysis. In: Proceedings of International Workshop on Pattern Recognition and Crowd Analysis, pp. 1\u20136 (2012)"},{"key":"3479_CR88","doi-asserted-by":"crossref","unstructured":"Patino, L., Nawaz, T., Cane T., et al.: PETS 2017: dataset and challenge. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2126\u20132132 (2017)","DOI":"10.1109\/CVPRW.2017.264"},{"key":"3479_CR89","unstructured":"Unusual crowd activity dataset made available by the University of Minnesota. http:\/\/mha.cs.umn.edu."},{"key":"3479_CR90","doi-asserted-by":"crossref","unstructured":"Nievas, E.B., Suarez, O.D., Garc\u00eda, G.B., et al.: Violence detection in video using computer vision techniques. In: Proceedings of the 14th International Conference on Computer Analysis of Images and Patterns, pp. 332\u2013339 (2011)","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"3479_CR91","unstructured":"Mart\u00edn-Mart\u00edn, R., Patel, M., Rezatofighi, H., et al.: JRDB: a dataset and benchmark of egocentric robot visual perception of humans in built environments. IEEE Trans. Pattern Anal. Mach. Intell. (2021)"},{"key":"3479_CR92","unstructured":"Dendorfer, P., Rezatofighi, H., Milan, A., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. https:\/\/arxiv.org\/pdf\/2003.09003 v1.pdf."},{"key":"3479_CR93","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Zhu, Y., et al.: PANDA: a gigapixel-level human-centric video dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3265\u20133275 (2020)","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"3479_CR94","unstructured":"Choi, W., Shahid, K., Savarese, S.: What are they doing?: Collective activity classification using spatio-temporal relationship among people. In: Proceedings of IEEE International Conference on Computer Vision Workshops, pp. 1\u20138 (2009)"},{"key":"3479_CR95","doi-asserted-by":"crossref","unstructured":"Ehsanpour, M., Saleh, F., Savarese, S., et al.: JRDB-act: a large-scale dataset for spatio-temporal action, social group and activity detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20951\u201320960 (2022)","DOI":"10.1109\/CVPR52688.2022.02031"},{"key":"3479_CR96","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S.Z., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"3479_CR97","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2021","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimed. 23, 1330\u20131342 (2021)","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"3479_CR98","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"K Aouaidjia","year":"2021","unstructured":"Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-D joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51(5), 2774\u20132788 (2021)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03479-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03479-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03479-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T09:55:37Z","timestamp":1739354137000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03479-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":98,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3479"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03479-z","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"9 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}