MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos

2024-10-08 · Yiling Zhang, Erkut Akdag, Egor Bondarev, Peter H. N. de With

Detection of anomaly events is relevant for public safety and requires a combination of fine-grained motion information and contextual events at variable time-scales. To this end, we propose a Multi-Timescale Feature Learning (MTFL) method to enhance the representation of anomaly features. Short, medium, and long temporal tubelets are employed to extract spatio-temporal video features using a Video Swin Transformer. Experimental results demonstrate that MTFL outperforms state-of-the-art methods on the UCF-Crime dataset, achieving an anomaly detection performance 89.78% AUC. Moreover, it performs complementary to SotA with 95.32% AUC on the ShanghaiTech and 84.57% AP on the XD-Violence dataset. Furthermore, we generate an extended dataset of the UCF-Crime for development and evaluation on a wider range of anomalies, namely Video Anomaly Detection Dataset (VADD), involving 2,591 videos in 18 classes with extensive coverage of realistic anomalies.

📄 PDF Abstract BibTeX arXiv:2410.05900

Code (1)

erktkdg/MTFL 공식 구현 pytorch

Tasks

Anomaly Detection Anomaly Detection In Surveillance Videos Supervised Anomaly Detection Video Anomaly DetectionWeakly-supervised Anomaly Detection

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Residual Connection 설명 없음

Position-Wise Feed-Forward Layer 설명 없음

Attention 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Weakly Supervised Multimodal Temporal Forgery Localization via Multitask Learning

2025-08-04 · Wenbo Xu, Wei Lu, Xiangyang Luo arxiv

The spread of Deepfake videos has caused a trust crisis and impaired social stability. Although numerous approaches have been proposed to address the challenges of Deepfake detection and localization, there is still a la…

Binary Classification DeepFake Detection

Knowledge-data fusion dominated vehicle platoon dynamics modeling and analysis: A physics-encoded deep learning approach

2025-02-09 · Hao Lyu, Yanyong Guo, Pan Liu, Shuo Feng 외

Recently, artificial intelligence (AI)-enabled nonlinear vehicle platoon dynamics modeling plays a crucial role in predicting and optimizing the interactions between vehicles. Existing efforts lack the extraction and cap…

Multi-stage Multi-task feature learning via adaptive threshold

2014-06-16 · Yaru Fan, Yi-Lun Wang

Multi-task feature learning aims to identity the shared features among tasks to improve generalization. It has been shown that by minimizing non-convex learning models, a better solution than the convex alternatives can …

feature selection

Multi-Stage Multi-Task Feature Learning

2012-12-01 · NeurIPS 2012 12 · Pinghua Gong, Jieping Ye, Chang-Shui Zhang

Multi-task sparse feature learning aims to improve the generalization performance by exploiting the shared features among tasks. It has been successfully applied to many applications including computer vision and biomedi…

parameter estimation

Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing

2020-07-17 · Jed Mills, Jia Hu, Geyong Min

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent an…

Edge-computing Federated Learning