UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Open accessThe DOI matches its Crossref record; 72 of the 72 references it cites were found in a registry or an index.
Abstract
Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal and abnormal events. In this scenario, anomaly detection is an open-set problem. However, some studies assimilate anomaly detection to action recognition. This is a closed-set scenario that fails to test the capability of systems at detecting new anomaly types. To this end, we propose UBnormal, a new supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, we introduce abnormal events annotated at the pixel level at training time, for the first time enabling the use of fully-supervised learning methods for abnormal event detection. To preserve the typical open-set formulation, we make sure to include dis-joint sets of anomaly types in our training and test collections of videos. To our knowledge, UBnormal is the first video anomaly detection benchmark to allow a fair head-to-head comparison between one-class open-set models and supervised closed-set models, as shown in our experiments. Moreover, we provide empirical evidence showing that UB-normal can enhance the performance of a state-of-the-art anomaly detection framework on two prominent data sets, Avenue and ShanghaiTech. Our benchmark is freely available at https://github.com/lilygeorgescu/UBnormal.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 1×
“To detect the objects in Avenue and ShanghaiTech, we apply the pre-trained YOLOv3 [49] object detector, following [17].”
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593 · cited 2×
“[53] represented each video using features extracted by a pre-trained C3D [58] model.”
Real-World Anomaly Detection in Surveillance Videos
Sultani, W., Chen, C., & Shah, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00678 · Cited by 2,140
Self-citationGong, D., Liu, L., Le, V., Saha, B., Mansour, M. R., Venkatesh, S., & Van Den Hengel, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00179 · Cited by 1,930
Abnormal crowd behavior detection using social force model
Mehran, R., Oyama, A., & Shah, M. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206641 · Cited by 1,672 · cited 6×
“Most of the existing data sets contain anomalies related to human-interaction [1,33,37,38] or vehicles in pedestrian areas, but the anomalies are usually staged and lack variety.”
InfluentialSelf-citationIs Space-Time Attention All You Need for Video Understanding?
Bertasius, G., Wang, H., & Torresani, L. (2021) · arXiv · doi:10.48550/arxiv.2102.05095 · Cited by 1,663 · cited 19×
“Indeed, the empirical results show that the video sample rate of 1 / 32 is optimal for TimeSformer.”
InfluentialFuture Frame Prediction for Anomaly Detection - A New Baseline
Liu, W., Luo, W., Lian, D., & Gao, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00684 · Cited by 1,530
Anomaly detection in crowded scenes
Mahadevan, V., Li, W., Bhalodia, V., & Vasconcelos, N. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539872 · Cited by 1,512 · cited 8×
“For example, in UCSD Ped2 [37], each anomalous event is related to bicycles, skateboards or cars in a pedestrian area.”
InfluentialAbnormal Event Detection at 150 FPS in MATLAB
Lu, C., Shi, J., & Jia, J. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.338 · Cited by 1,436 · cited 10×
“The CUHK Avenue [33], Street Scene [43], Subway Entrance [1], Subway Exit [1] and UCSD Ped [37] data sets form the category of single-scene benchmarks [46], enabling the successful use of frame-level methods that learn very specific normality models (adapted to a particular scene).”
InfluentialLearning Temporal Regularity in Video Sequences
Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A. K., & Davis, L. S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.86 · Cited by 1,397 · cited 3×
“A large body of recent works [2–4,7,9–11,14,17,18,20, 21,23,25,27,27–30,32,33,35–38,41,43–45,47,48,50,51, 55, 56, 59–70] treats anomaly detection in video as a one-class classification (outlier detection) task, training models without having access to abnormal samples.”
Anomaly Detection and Localization in Crowded Scenes
Li, W., Mahadevan, V., & Vasconcelos, N. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.111 · Cited by 1,017
Recent Advances in Open Set Recognition: A Survey
Geng, C., Huang, S.-J., & Chen, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2981604 · Cited by 1,006 · cited 1×
“[16], in our setting, the normal classes are known known classes (KKC) and the abnormal classes used at test time are unknown unknown classes (UUC).”
Learning Memory-Guided Normality for Anomaly Detection
Park, H., Noh, J., & Ham, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01438 · Cited by 929
Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors
Adam, A., Rivlin, E., Shimshoni, I., & Reinitz, D. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70825 · Cited by 918 · cited 9×
“The CUHK Avenue [33], Street Scene [43], Subway Entrance [1], Subway Exit [1] and UCSD Ped [37] data sets form the category of single-scene benchmarks [46], enabling the successful use of frame-level methods that learn very specific normality models (adapted to a particular scene).”
InfluentialA Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
Luo, W., Liu, W., & Gao, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.45 · Cited by 895
Sparse reconstruction cost for abnormal event detection
Cong, Y., Yuan, J., & Liu, J. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995434 · Cited by 801
Kim, J., & Grauman, K. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206569 · Cited by 768
Zhong, J.-X., Li, N., Kong, W., Liu, S., Li, T. H., & Li, G. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00133 · Cited by 588
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J. W., & Carneiro, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00493 · Cited by 557
Online detection of unusual events in videos via dynamic sparse coding
Zhao, B., Fei-Fei, L., & Xing, E. P. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995524 · Cited by 532
Abnormal event detection in videos using generative adversarial nets
Ravanbakhsh, M., Nabi, M., Sangineto, E., Marcenaro, L., Regazzoni, C., & Sebe, N. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296547 · Cited by 515 · cited 3×
“A large body of recent works [2–4,7,9–11,14,17,18,20, 21,23,25,27,27–30,32,33,35–38,41,43–45,47,48,50,51, 55, 56, 59–70] treats anomaly detection in video as a one-class classification (outlier detection) task, training models without having access to abnormal samples.”
Detecting anomalous events in videos by learning deep representations of appearance and motion
Xu, D., Yan, Y., Ricci, E., & Sebe, N. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.10.010 · Cited by 474
Anomaly Detection in Video Sequence With Appearance-Motion Correspondence
Nguyen, T. N., & Meunier, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00136 · Cited by 459
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video
Ionescu, R. T., Khan, F. S., Georgescu, M.-I., & Shao, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00803 · Cited by 425
Self-citationSabokrou, M., Fayyaz, M., Fathy, M., & Klette, R. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2670780 · Cited by 386 · cited 3×
“A large body of recent works [2–4,7,9–11,14,17,18,20, 21,23,25,27,27–30,32,33,35–38,41,43–45,47,48,50,51, 55, 56, 59–70] treats anomaly detection in video as a one-class classification (outlier detection) task, training models without having access to abnormal samples.”
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
Feng, J.-C., Hong, F.-T., & Zheng, W.-S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01379 · Cited by 355 · cited 5×
“Another body of works [15, 42, 53, 57, 67, 71] treats anomaly detection as a weakly-supervised action recognition task.”
InfluentialAnomaly Detection in Video via Self-Supervised and Multi-Task Learning
Georgescu, M.-I., Barbalau, A., Ionescu, R. T., Shahbaz Khan, F., Popescu, M., & Shah, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01255 · Cited by 350 · cited 10×
“Further details about LT1 ,LT2 ,LT3 and LT4 are provided in [17].”
InfluentialSelf-citationAdversarial Reciprocal Points Learning for Open Set Recognition
Chen, G., Peng, P., Wang, X., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3106743 · Cited by 344 · cited 1×
“Hence, we consider works on open-set action recognition [5, 8] as very distantly related.”
Unmasking the Abnormal Events in Video
Ionescu, R. T., Smeureanu, S., Alexe, B., & Popescu, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.315 · Cited by 335 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Self-citationLiu, Z., Nie, Y., Long, C., Zhang, Q., & Li, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01333 · Cited by 328 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Integrating prediction and reconstruction for anomaly detection
Tang, Y., Zhao, L., Zhang, S., Gong, C., Li, G., & Yang, J. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.11.024 · Cited by 282 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
Pang, G., Yan, C., Shen, C., van den Hengel, A., & Bai, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01219 · Cited by 257
Cheng, K.-W., Chen, Y.-T., & Fang, W.-H. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298909 · Cited by 234 · cited 3×
“A large body of recent works [2–4,7,9–11,14,17,18,20, 21,23,25,27,27–30,32,33,35–38,41,43–45,47,48,50,51, 55, 56, 59–70] treats anomaly detection in video as a one-class classification (outlier detection) task, training models without having access to abnormal samples.”
Video anomaly detection with spatio-temporal dissociation
Chang, Y., Tu, Z., Xie, W., Luo, B., Zhang, S., Sui, H., & Yuan, J. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2021.108213 · Cited by 234
Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
Ravanbakhsh, M., Nabi, M., Mousavi, H., Sangineto, E., & Sebe, N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00188 · Cited by 216
Few-Shot Scene-Adaptive Anomaly Detection
Lu, Y., Yu, F., Reddy, M. K. K., & Wang, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58558-7_8 · Cited by 207
Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events
Yu, G., Wang, S., Cai, Z., Zhu, E., Xu, C., Yin, J., & Kloft, M. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413973 · Cited by 193 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
A Deep One-Class Neural Network for Anomalous Event Detection in Complex Scenes
Wu, P., Liu, J., & Shen, F. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2933554 · Cited by 191
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
Georgescu, M. I., Ionescu, R., Khan, F. S., Popescu, M., & Shah, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3074805 · Cited by 187 · cited 10×
“Legend: † – computed based on the tracks from [18]; ‡ – computed based on tracks from [43].”
InfluentialSelf-citationOld Is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm
Zaigham Zaheer, M., Lee, J.-H., Astrid, M., & Lee, S.-I. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01419 · Cited by 186 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Street Scene: A new dataset and evaluation protocol for video anomaly detection
Ramachandra, B., & Jones, M. J. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093457 · Cited by 180 · cited 9×
“The CUHK Avenue [33], Street Scene [43], Subway Entrance [1], Subway Exit [1] and UCSD Ped [37] data sets form the category of single-scene benchmarks [46], enabling the successful use of frame-level methods that learn very specific normality models (adapted to a particular scene).”
InfluentialEvidential Deep Learning for Open Set Action Recognition
Bao, W., Yu, Q., & Kong, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01310 · Cited by 174
A Survey of Single-Scene Video Anomaly Detection
Ramachandra, B., Jones, M., & Vatsavai, R. R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3040591 · Cited by 173
BMAN: Bidirectional Multi-Scale Aggregation Networks for Abnormal Event Detection
Lee, S., Kim, H. G., & Ro, Y. M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2948286 · Cited by 170 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Video parsing for abnormality detection
Antic, B., & Ommer, B. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126525 · Cited by 164 · cited 3×
“A large body of recent works [2–4,7,9–11,14,17,18,20, 21,23,25,27,27–30,32,33,35–38,41,43–45,47,48,50,51, 55, 56, 59–70] treats anomaly detection in video as a one-class classification (outlier detection) task, training models without having access to abnormal samples.”
Zaheer, M. Z., Mahmood, A., Astrid, M., & Lee, S.-I. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58542-6_22 · Cited by 158
Deep Appearance Features for Abnormal Behavior Detection in Video
Smeureanu, S., Ionescu, R. T., Popescu, M., & Alexe, B. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68548-9_70 · Cited by 153
Self-citationDual Discriminator Generative Adversarial Network for Video Anomaly Detection
Dong, F., Zhang, Y., & Nie, X. (2020) · IEEE Access · doi:10.1109/access.2020.2993373 · Cited by 150
Detecting Abnormal Events in Video Using Narrowed Normality Clusters
Ionescu, R. T., Smeureanu, S., Popescu, M., & Alexe, B. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00212 · Cited by 137
Self-citationScene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos
Sun, C., Jia, Y., Hu, Y., & Wu, Y. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413887 · Cited by 134 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Continual Learning for Anomaly Detection in Surveillance Videos
Doshi, K., & Yilmaz, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00135 · Cited by 131 · cited 4×
“In Tables 3 and 4, we also report the results obtained on the ShanghaiTech [35] data set, comparing the approach based on UBnormal samples with other state-of-the-art methods [3,4,7,11–13,18,19,21,27,28,30,32,34,36,41,43,44 [21] 87 .”
InfluentialLearning a distance function with a Siamese network to localize anomalies in videos
Ramachandra, B., Jones, M., & Vatsavai, R. R. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093417 · Cited by 126 · cited 1×
“RBDC and TBDC scores (in %) of the state-of-the-art methods [18,21,30,43,44] versus an approach based on the framework proposed in [17], enhanced by us with the fifth proxy task (T5) to discriminate between normal and abnormal objects from the UBnormal data set.”
Any-Shot Sequential Anomaly Detection in Surveillance Videos
Doshi, K., & Yılmaz, Y. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00475 · Cited by 116
Abnormal Event Detection and Localization via Adversarial Event Prediction
Yu, J., Lee, Y., Yow, K., Jeon, M., & Pedrycz, W. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053563 · Cited by 116 · cited 1×
“[65] proposed a frame-level framework which employs the adversarial learning of past and future events to detect anomalies, instead of requiring complementary information such as optical flow or explicit abnormal samples during training.”
Classifier Two Sample Test for Video Anomaly Detections.
Liu, Y., Li, C., & Póczos, B. (2018) · British Machine Vision Conference (BMVC) · Cited by 115
Video anomaly detection based on locality sensitive hashing filters
Zhang, Y., Lu, H., Zhang, L., Ruan, X., & Sakai, S. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.11.018 · Cited by 112
Cluster Attention Contrast for Video Anomaly Detection
Wang, Z., Zou, Y., & Zhang, Z. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413529 · Cited by 109 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Robust Anomaly Detection in Videos Using Multilevel Representations
Vu, H. T., Nguyen, T. D., Le, T., et al. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015216 · Cited by 101 · cited 1×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection
Astrid, M., Zaheer, M. Z., & Lee, S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00028 · Cited by 96 · cited 5×
“We compare the approach based on UBnormal samples with the following state-of-the-art meth-ods [3, 4, 7, 11–13, 18, 19, 21, 23, 24, 26–28, 30–32, 34, 36, 39, 41, 43,44,53–56,59–61,63,65].”
InfluentialSTAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection
Lee, S., Kim, H. G., & Ro, Y. M. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8462388 · Cited by 90
Dance with Self-Attention: A New Look of Conditional Random Fields on Anomaly Detection in Videos
Purwanto, D., Chen, Y., & Fang, W. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00024 · Cited by 77
Unsupervised Behavior-Specific Dictionary Learning for Abnormal Event Detection
Ren, H., Liu, W., Olsen, S. I., Escalera, S., & Moeslund, T. B. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.28 · Cited by 67
Zhang, X., Yang, S., Zhang, J., & Zhang, W. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107394 · Cited by 60
Online Detection of Abnormal Events Using Incremental Coding Length
Dutta, J., & Banerjee, B. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9799 · Cited by 56
Decoupled appearance and motion learning for efficient anomaly detection in surveillance video
Li, B., Leroux, S., & Simoens, P. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103249 · Cited by 44
Bidirectional Retrospective Generation Adversarial Network for Anomaly Detection in Videos
Yang, Z., Liu, J., & Wu, P. (2021) · IEEE Access · doi:10.1109/access.2021.3100678 · Cited by 38
X-MAN: Explaining multiple sources of anomalies in video
Szymanowicz, S., Charles, J., & Cipolla, R. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00360 · Cited by 32
TAM-Net: Temporal Enhanced Appearance-to-Motion Generative Network for Video Anomaly Detection
Ji, X., Li, B., & Zhu, Y. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207231 · Cited by 26 · cited 4×
“In spite of the growing interest in video anomaly detection [11, 12, 17–19, 22–24, 27, 32, 34, 39–41, 43, 46, 52, 54, 60, 61, 64, 66], which generated significant advances leading to impressive performance levels [17, 18, 21, 27, 32, 56, 59, 60, 64, 66, 67], the task remains very challenging.”
InfluentialObject-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in VideoPreprint
Ionescu, R. T., Khan, F. S., Georgescu, M.-I., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04960 · Cited by 23
Self-citationPerceptual metric learning for video anomaly detection
Ramachandra, B., Jones, M., & Vatsavai, R. R. (2021) · Machine Vision and Applications · doi:10.1007/s00138-021-01187-5 · Cited by 12 · cited 1×
“[45] proposed a patch-level framework to localize anomalies in video by using a Siamese network to learn a metric from pairs of video patches.”
Metadata
- Authors
- Acsintoae, A., Florescu, A., Georgescu, M.-I., Mare, T., Sumedrea, P., Ionescu, R. T., Khan, F. S., & Shah, M.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 20111-20121
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3212899624
- Cited by
- 185
- References
- 72
- FWCI
- 21.87
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.