Weakly-Supervised Spatiotemporal Anomaly Detection

2026-05-13 · Urvi Gianchandani, Praveen Tirupattur, Mubarak Shah arxiv

In this paper, we explore a weakly supervised method for anomaly detection. Since annotating videos is time-consuming, we only look at weak video-level labels during training. This means that given a video, we know that it is either normal or contains an anomaly, but no further annotations are used to train the network. Features are extracted from video clips that are either normal or anomalous. These features are used to determine anomaly scores for spatiotemporal regions of the clips based on a classifier and the implementation of a multiple instance ranking loss (MIL). We represent both anomalous and normal video clips as positive and negative bags, respectively, to apply MIL. Furthermore, since anomalies are usually localized to a part of a frame rather than the whole frame, we chose to explore temporal as well as spatial anomaly detection. We show our results on the UCF Crime2Local Dataset, which contains spatiotemporal annotations for a portion of the UCF Crime Dataset.

📄 PDF Abstract BibTeX arXiv:2605.13746

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Learning Where and When: Patch-Based Spatiotemporal Localization in Weakly Supervised Video Anomaly Detection

2026-06-28 · Hamza Karim, Nghia Nguyen, Lokman Bekit, Yasin Yilmaz arxiv

Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neglecting their spatial extent within frames. Yet, spatial localizatio…

Multiple Instance Learning Video Anomaly Detection

Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection

2024-01-07 · Zhangkai Wu, Longbing Cao, Qi Zhang, Junxian Zhou 외

Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detection (TSAD). Existing VAE-based TSAD method…

Anomaly Detection Self-Supervised Learning Time Series Time Series Anomaly Detection

Weakly-supervised anomaly detection for multimodal data distributions

2024-06-13 · Xu Tan, Junqi Chen, Sylwan Rahardja, Jiawei Yang 외

Weakly-supervised anomaly detection can outperform existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing we…

Anomaly Detection Supervised Anomaly Detection Weakly-supervised Anomaly Detection

Low-rank on Graphs plus Temporally Smooth Sparse Decomposition for Anomaly Detection in Spatiotemporal Data

2020-10-23 · Seyyid Emre Sofuoglu, Selin Aviyente

Anomaly detection in spatiotemporal data is a challenging problem encountered in a variety of applications including hyperspectral imaging, video surveillance, and urban traffic monitoring. Existing anomaly detection met…

Anomaly Detection Tensor Decomposition

Robust Spatiotemporally Contiguous Anomaly Detection Using Tensor Decomposition

2025-10-01 · Rachita Mondal, Mert Indibi, Tapabrata Maiti, Selin Aviyente arxiv

Anomaly detection in spatiotemporal data is a challenging problem encountered in a variety of applications, including video surveillance, medical imaging data, and urban traffic monitoring. Existing anomaly detection met…