2000 character limit reached
Context-aware Video Anomaly Detection in Long-Term Datasets
Published 11 Apr 2024 in cs.CV | (2404.07887v1)
Abstract: Video anomaly detection research is generally evaluated on short, isolated benchmark videos only a few minutes long. However, in real-world environments, security cameras observe the same scene for months or years at a time, and the notion of anomalous behavior critically depends on context, such as the time of day, day of week, or schedule of events. Here, we propose a context-aware video anomaly detection algorithm, Trinity, specifically targeted to these scenarios. Trinity is especially well-suited to crowded scenes in which individuals cannot be easily tracked, and anomalies are due to speed, direction, or absence of group motion. Trinity is a contrastive learning framework that aims to learn alignments between context, appearance, and motion, and uses alignment quality to classify videos as normal or anomalous. We evaluate our algorithm on both conventional benchmarks and a public webcam-based dataset we collected that spans more than three months of activity.
- LOST: Longterm Observation of Scenes (with Tracks). In 2012 IEEE Workshop on the Applications of Computer Vision (WACV), pages 297–304, 2012.
- Hierarchical Scene Normality-Binding Modeling for Anomaly Detection in Surveillance Videos. In Proceedings of the 30th ACM International Conference on Multimedia, pages 6103–6112. ACM, 2022.
- Unsupervised video anomaly detection via normalizing flows with implicit latent features. Pattern Recognition, 129:108703, 2022.
- Rethinking Video Anomaly Detection - A Continual Learning Approach. In 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 3036–3045, Waikoloa, HI, USA, 2022.
- An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2021.
- Unsupervised Discovery of Normal and Abnormal Activity Patterns in Indoor and Outdoor Environments:. In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 210–217, 2017.
- Anomaly Detection in Video via Self-Supervised and Multi-Task Learning. In CVPR, pages 12737–12747, 2021.
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection. In ICCV, pages 1705–1714, 2019.
- Learning Temporal Regularity in Video Sequences. In CVPR, pages 733–742, 2016.
- Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video. In CVPR, pages 7834–7843, 2019.
- Adam: A Method for Stochastic Optimization. In ICLR, 2015.
- Multi-branch Neural Networks for Video Anomaly Detection in Adverse Lighting and Weather Conditions. In 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 3027–3035. IEEE, 2022.
- Explainable contextual anomaly detection using quantile regression forests. Data Mining and Knowledge Discovery, 37(6):2517–2563, 2023.
- Robust contextual outlier detection: Where context meets sparsity. In Proceedings of the 25th ACM international on conference on information and knowledge management, pages 2167–2172, 2016.
- Future frame prediction for anomaly detection–a new baseline. In CVPR, pages 6536–6545, 2018.
- Diversity-measurable anomaly detection. In CVPR, pages 12147–12156, 2023.
- A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction. In ICCV, pages 13588–13597, 2021.
- SGDR: Stochastic gradient descent with warm restarts. In ICLR, 2017.
- Abnormal Event Detection at 150 FPS in MATLAB. In ICCV, pages 2720–2727, 2013.
- Learning normal dynamics in videos with meta prototype network. In CVPR, pages 15425–15434, 2021.
- Anomaly detection in video sequence with appearance-motion correspondence. In CVPR, pages 1273–1283, 2019.
- Seasons in drift: A long term thermal imaging dataset for studying concept drift. In NeurIPS, 2021.
- Learning Memory-Guided Normality for Anomaly Detection. In CVPR, pages 14360–14369, 2020.
- Learning transferable visual models from natural language supervision. In ICML, pages 8748–8763. PMLR, 2021.
- Street Scene: A new dataset and evaluation protocol for video anomaly detection. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 2558–2567, 2020.
- A Survey of Single-Scene Video Anomaly Detection. IEEE TPAMI, 44(5):2293–2312, 2020.
- Self-supervised predictive convolutional attentive block for anomaly detection. In CVPR, pages 13576–13586, 2022.
- Eval: Explainable video anomaly localization. In CVPR, pages 18717–18726, 2023.
- Conditional Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering, 19(5):631–645, 2007.
- Scene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos. In Proceedings of the 28th ACM International Conference on Multimedia, pages 184–192, 2020.
- Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection. In CVPR, pages 22846–22856, 2023.
- Contrastive Multiview Coding. In ECCV, pages 776–794, 2020.
- Neural Discrete Representation Learning. In NeurIPS, 2017.
- Attention is all you need. NeurIPS, 30, 2017.
- Anomaly Detection and Localization in Crowded Scenes. IEEE TPAMI, 36(1):18–32, 2014.
- Learning and inferring “dark matter” and predicting human intents and trajectories in videos. IEEE TPAMI, 40(7):1639–1652, 2017.
- Video event restoration based on keyframes for video anomaly detection. In CVPR, pages 14592–14601, 2023.
- A Duality Based Approach for Realtime TV-L 1 Optical Flow. In Pattern Recognition, pages 214–223. Berlin, Heidelberg, 2007.
- Online detection of unusual events in videos via dynamic sparse coding. In CVPR, pages 3313–3320, 2011.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.