Learning Normal Dynamics in Videos with Meta Prototype Network
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than those of normal ones. Previous methods introduced the memory bank into AE, for encoding diverse normal patterns across the training videos. However, they are memory-consuming and cannot cope with unseen new scenarios in the testing data. In this work, we propose a dynamic prototype unit (DPU) to encode the normal dynamics as prototypes in real time, free from extra memory cost. In addition, we introduce meta-learning to our DPU to form a novel few-shot normalcy learner, namely Meta-Prototype Unit (MPU). It enables the fast adaption capability on new scenes by only consuming a few iterations of update. Extensive experiments are conducted on various benchmarks. The superior performance over the state-of-the-art demonstrates the effectiveness of our method. Our code is available at https://github.com/ktr-hubrt/MPN/.
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“Video anomaly detection (VAD) refers to the identification of behaviors or appearance patterns that do not conform to the expectation [2, 3, 5, 28].”
BackgroundModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 3×
“[25] follow the optimization-based meta-learning approach [8] and apply it to train a model for scene-adaptive anomaly detection.”
MethodLearning to Compare: Relation Network for Few-Shot Learning
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H. S., & Hospedales, T. M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00131 · Cited by 5,816
Residual Attention Network for Image Classification
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.683 · Cited by 4,073
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · cited 1×
“In few-shot learning, researchers aim to mimic the fast and nimble learning ability of humans, which can quickly adapt to a new scenario with only a few data examples [18].”
BackgroundAdversarially Learned One-Class Classifier for Novelty Detection
Sabokrou, M., Khalooei, M., Fathy, M., & Adeli, E. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00356 · Cited by 765
Latent Space Autoregression for Novelty Detection
Abati, D., Porrello, A., Calderara, S., & Cucchiara, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00057 · Cited by 508 · cited 2×
“Recently, many methods leverage deep Auto-Encoder (AE) to model regular patterns and reconstruct video frames [11, 31, 39, 4, 40, 1].”
BackgroundMethod
Cited by
TransCNN: Hybrid CNN and transformer mechanism for surveillance anomaly detection
Ullah, W., Hussain, T., Ullah, F. U. M., Lee, M. Y., & Baik, S. W. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106173 · Cited by 128
Semi-supervised bidirectional alignment for remote sensing cross-domain scene classification
Huang, W., Shi, Y., Xiong, Z., Wang, Q., & Zhu, X. X. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.11.013 · Cited by 76
Weakly Supervised Video Anomaly Detection via Transformer-Enabled Temporal Relation Learning
Zhang, D., Huang, C., Liu, C., & Xu, Y. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3175092 · Cited by 58
SwinAnomaly: Real-Time Video Anomaly Detection Using Video Swin Transformer and SORT
Bajgoti, A., Gupta, R., Balaji, P., Dwivedi, R., Siwach, M., & Gupta, D. (2023) · IEEE Access · doi:10.1109/access.2023.3321801 · Cited by 38
“Latest models such as Transanomaly [30], and Meta Prototype Network [35] were also compared.”
MethodPaulraj, S., & Vairavasundaram, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109496 · Cited by 27
Yun, S., Masukawa, R., Na, M., & Imani, M. (2025) · 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61041.2025.00464 · Cited by 14
Metadata
- Authors
- Lv, H., Chen, C., Cui, Z., Xu, C., Li, Y., & Yang, J.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 15420-15429
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3176309086
- Cited by
- 222
- References
- 10
- FWCI
- 17.89
- 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.