{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T12:23:06Z","timestamp":1792066986533,"version":"4.4.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["20&ZD305"],"award-info":[{"award-number":["20&ZD305"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["20&ZD305"],"award-info":[{"award-number":["20&ZD305"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of Henan Key Laboratory of Oracle Bone Inscription Information Processing","award":["OIP2021H001"],"award-info":[{"award-number":["OIP2021H001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s00530-023-01093-y","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T10:03:11Z","timestamp":1682416991000},"page":"2153-2164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Weakly supervised anomaly detection with multi-level contextual modeling"],"prefix":"10.1007","volume":"29","author":[{"given":"Mengting","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinrui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongge","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"1093_CR1","doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A.K., Davis, L.S.: Learning temporal regularity in video sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 733\u2013742 (2016)","DOI":"10.1109\/CVPR.2016.86"},{"key":"1093_CR2","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S.: Future frame prediction for anomaly detection\u2013a new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6536\u20136545 (2018)","DOI":"10.1109\/CVPR.2018.00684"},{"issue":"5","key":"1093_CR3","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/TIFS.2018.2878538","volume":"14","author":"T Wang","year":"2018","unstructured":"Wang, T., Qiao, M., Lin, Z., Li, C., Snoussi, H., Liu, Z., Choi, C.: Generative neural networks for anomaly detection in crowded scenes. IEEE Trans. Inf. Forensics Secur. 14(5), 1390\u20131399 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"1093_CR4","doi-asserted-by":"crossref","unstructured":"Gong, D., Liu, L., Le, V., Saha, B., Mansour, M.R., Venkatesh, S., Hengel, A.v.d.: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1705\u20131714 (2019)","DOI":"10.1109\/ICCV.2019.00179"},{"key":"1093_CR5","doi-asserted-by":"crossref","unstructured":"Yu, G., Wang, S., Cai, Z., Zhu, E., Xu, C., Yin, J., Kloft, M.: Cloze test helps: Effective video anomaly detection via learning to complete video events. In: Proceedings of the ACM International Conference on Multimedia, pp. 583\u2013591 (2020)","DOI":"10.1145\/3394171.3413973"},{"key":"1093_CR6","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"1093_CR7","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"issue":"1\u20132","key":"1093_CR8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R.H., Lozano-P\u00e9rez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1\u20132), 31\u201371 (1997)","journal-title":"Artif. Intell."},{"key":"1093_CR9","unstructured":"Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS, vol. 2, p. 7 (2002)"},{"key":"1093_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, J., Qing, L., Miao, J.: Temporal convolutional network with complementary inner bag loss for weakly supervised anomaly detection. In: Proceedings of the IEEE International Conference on Image Processing, pp. 4030\u20134034 (2019)","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"1093_CR11","unstructured":"Zhu, Y., Newsam, S.: Motion-aware feature for improved video anomaly detection. arXiv preprint arXiv:1907.10211 (2019)"},{"key":"1093_CR12","doi-asserted-by":"crossref","unstructured":"Park, H., Noh, J., Ham, B.: Learning memory-guided normality for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14372\u201314381 (2020)","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"1093_CR13","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":"1093_CR14","doi-asserted-by":"crossref","unstructured":"Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: IEEE International Conference on Computer Vision, pp. 2720\u20132727 (2013)","DOI":"10.1109\/ICCV.2013.338"},{"issue":"3","key":"1093_CR15","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1109\/TPAMI.2007.70825","volume":"30","author":"A Adam","year":"2008","unstructured":"Adam, A., Rivlin, E., Shimshoni, I., Reinitz, D.: Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans. Pattern Anal. Mach. Intell. 30(3), 555\u2013560 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"1093_CR16","first-page":"18","volume":"36","author":"W Li","year":"2013","unstructured":"Li, W., Mahadevan, V., Vasconcelos, N.: Anomaly detection and localization in crowded scenes. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 18\u201332 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1093_CR17","doi-asserted-by":"crossref","unstructured":"Rabiee, H., Haddadnia, J., Mousavi, H., Kalantarzadeh, M., Nabi, M., Murino, V.: Novel dataset for fine-grained abnormal behavior understanding in crowd. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 95\u2013101 (2016). IEEE","DOI":"10.1109\/AVSS.2016.7738074"},{"key":"1093_CR18","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234\u2013241 (2015). Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1093_CR19","doi-asserted-by":"crossref","unstructured":"O\u2019Shea, T.J., Karra, K., Clancy, T.C.: Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention. In: 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp. 223\u2013228 (2016). IEEE","DOI":"10.1109\/ISSPIT.2016.7886039"},{"key":"1093_CR20","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.patrec.2019.11.024","volume":"129","author":"Y Tang","year":"2020","unstructured":"Tang, Y., Zhao, L., Zhang, S., Gong, C., Li, G., Yang, J.: Integrating prediction and reconstruction for anomaly detection. Pattern Recogn. Lett. 129, 123\u2013130 (2020)","journal-title":"Pattern Recogn. Lett."},{"issue":"1","key":"1093_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TCDS.2018.2883368","volume":"12","author":"S Yan","year":"2018","unstructured":"Yan, S., Smith, J.S., Lu, W., Zhang, B.: Abnormal event detection from videos using a two-stream recurrent variational autoencoder. IEEE Transactions on Cognitive and Developmental Systems 12(1), 30\u201342 (2018)","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"1093_CR22","unstructured":"Maron, O., Lozano-P\u00e9rez, T.: A framework for multiple-instance learning. Advances in neural information processing systems 10 (1997)"},{"key":"1093_CR23","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":"1093_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4975\u20134986 (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"1093_CR25","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, T., Ji, W., Wang, J., Cheng, L.: Exploring denoised cross-video contrast for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19914\u201319924 (2022)","DOI":"10.1109\/CVPR52688.2022.01929"},{"key":"1093_CR26","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.-W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"1093_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Song, J., Gao, L., Liu, X., Huang, W., He, X., Gan, C.: Beyond rnns: Positional self-attention with co-attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8658\u20138665 (2019)","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"1093_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: Actbert: Learning global-local video-text representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8746\u20138755 (2020)","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"1093_CR29","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervised spatio-temporal representation learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"1093_CR30","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of the European Conference on Computer Vision, pp. 399\u2013417 (2018)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"1093_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"1093_CR32","doi-asserted-by":"crossref","unstructured":"Purwanto, D., Chen, Y.-T., Fang, W.-H.: Dance with self-attention: A new look of conditional random fields on anomaly detection in videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 173\u2013183 (2021)","DOI":"10.1109\/ICCV48922.2021.00024"},{"key":"1093_CR33","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"1093_CR34","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"1093_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, J.-X., Li, N., Kong, W., Liu, S., Li, T.H., Li, G.: Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1237\u20131246 (2019)","DOI":"10.1109\/CVPR.2019.00133"},{"key":"1093_CR36","unstructured":"Hinton, G.E.: Rectified linear units improve restricted boltzmann machines vinod nair (2010)"},{"issue":"56","key":"1093_CR37","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1093_CR38","doi-asserted-by":"crossref","unstructured":"Liang, S., Huang, Z., Liang, M., Yang, H.: Instance enhancement batch normalization: An adaptive regulator of batch noise. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4819\u20134827 (2020)","DOI":"10.1609\/aaai.v34i04.5917"},{"key":"1093_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1093_CR40","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Li, Z., Zhao, P., Gao, S., et al.: Margin learning embedded prediction for video anomaly detection with a few anomalies. In: IJCAI, pp. 3023\u20133030 (2019)","DOI":"10.24963\/ijcai.2019\/419"},{"key":"1093_CR41","doi-asserted-by":"crossref","unstructured":"Luo, W., Liu, W., Gao, S.: A revisit of sparse coding based anomaly detection in stacked rnn framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 341\u2013349 (2017)","DOI":"10.1109\/ICCV.2017.45"},{"key":"1093_CR42","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":"1093_CR43","doi-asserted-by":"crossref","unstructured":"Wan, B., Fang, Y., Xia, X., Mei, J.: Weakly supervised video anomaly detection via center-guided discriminative learning. In: Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2020). IEEE","DOI":"10.1109\/ICME46284.2020.9102722"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01093-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01093-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01093-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T11:41:15Z","timestamp":1702294875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01093-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1093"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01093-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"21 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":3,"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"}}]}}