Spatio-temporal predictive tasks for abnormal event detection in videos

• URL: http://arxiv.org/abs/2210.15741v2
• Date: Sun, 23 Apr 2023 16:35:35 GMT
• Title: Spatio-temporal predictive tasks for abnormal event detection in videos
• Authors: Yassine Naji, Aleksandr Setkov, Ang\'elique Loesch, Mich\`ele Gouiff\`es, Romaric Audigier
• Abstract summary: We propose new constrained pretext tasks to learn object level normality patterns. Our approach consists in learning a mapping between down-scaled visual queries and their corresponding normal appearance and motion characteristics. Experiments on several benchmark datasets demonstrate the effectiveness of our approach to localize and track anomalies.
• Score: 60.02503434201552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Abnormal event detection in videos is a challenging problem, partly due to the multiplicity of abnormal patterns and the lack of their corresponding annotations. In this paper, we propose new constrained pretext tasks to learn object level normality patterns. Our approach consists in learning a mapping between down-scaled visual queries and their corresponding normal appearance and motion characteristics at the original resolution. The proposed tasks are more challenging than reconstruction and future frame prediction tasks which are widely used in the literature, since our model learns to jointly predict spatial and temporal features rather than reconstructing them. We believe that more constrained pretext tasks induce a better learning of normality patterns. Experiments on several benchmark datasets demonstrate the effectiveness of our approach to localize and track anomalies as it outperforms or reaches the current state-of-the-art on spatio-temporal evaluation metrics.

Related papers

• Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
  This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs) Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
  arXiv  Detail & Related papers  (2024-08-12T03:31:29Z)
• Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection [103.92970668001277]
  We propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection. We first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths. Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies.
  arXiv  Detail & Related papers  (2023-12-04T09:40:11Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Future Video Prediction from a Single Frame for Video Anomaly Detection [0.38073142980732994]
  Video anomaly detection (VAD) is an important but challenging task in computer vision. We introduce the task of future frame prediction proxy-task, as a novel proxy-task for video anomaly detection. This proxy-task alleviates the challenges of previous methods in learning longer motion patterns.
  arXiv  Detail & Related papers  (2023-08-15T14:04:50Z)
• Time series anomaly detection with reconstruction-based state-space models [10.085100442558828]
  We propose a novel unsupervised anomaly detection method for time series data. A long short-term memory (LSTM)-based encoder-decoder is adopted to represent the mapping between the observation space and the latent space. Regularization of the latent space places constraints on the states of normal samples, and Mahalanobis distance is used to evaluate the abnormality level.
  arXiv  Detail & Related papers  (2023-03-06T17:52:35Z)
• Object-centric and memory-guided normality reconstruction for video anomaly detection [56.64792194894702]
  This paper addresses anomaly detection problem for videosurveillance. Due to the inherent rarity and heterogeneity of abnormal events, the problem is viewed as a normality modeling strategy. Our model learns object-centric normal patterns without seeing anomalous samples during training.
  arXiv  Detail & Related papers  (2022-03-07T19:28:39Z)
• Video Anomaly Detection By The Duality Of Normality-Granted Optical Flow [1.8065361710947974]
  We propose to discriminate anomalies from normal ones by the duality of normality-granted optical flow. We extend the appearance-motion correspondence scheme from frame reconstruction to prediction.
  arXiv  Detail & Related papers  (2021-05-10T12:25:00Z)
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video [120.18562044084678]
  Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. We propose a background-agnostic framework that learns from training videos containing only normal events.
  arXiv  Detail & Related papers  (2020-08-27T18:39:24Z)
• Learning Memory-guided Normality for Anomaly Detection [33.77435699029528]
  We present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly. We also present novel feature compactness and separateness losses to train the memory, boosting the discriminative power of both memory items and deeply learned features from normal data.
  arXiv  Detail & Related papers  (2020-03-30T05:30:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.