Approaches Toward Physical and General Video Anomaly Detection (2021-12-14T00:00:00.000000Z)

TL;DR

This work introduces the Physical Anomalous Trajectory or Motion (PHANTOM) dataset 1, which contains six different video classes, which differs in the presented phenomena, the normal class variability, and the kind of anomalies in the videos.

Abstract

In recent years, many works have addressed the problem of finding never-seen-before anomalies in videos. Yet, most work has been focused on detecting anomalous frames in surveillance videos taken from security cameras. Meanwhile, the task of anomaly detection (AD) in videos exhibiting anomalous mechanical behavior, has been mostly overlooked. Anomaly detection in such videos is both of academic and practical interest, as they may enable automatic detection of malfunctions in many manufacturing, maintenance, and real-life settings. To assess the potential of the different approaches to detect such anomalies, we evaluate two simple baseline approaches: (i) Temporal-pooled image AD techniques. (ii) Density estimation of videos represented with features pretrained for video-classification.Development of such methods calls for new benchmarks to al-low evaluation of different possible approaches. We introduce the Physical Anomalous Trajectory or Motion (PHANTOM) dataset 1, which contains six different video classes. Each class consists of normal and anomalous videos. The classes differ in the presented phenomena, the normal class variability, and the kind of anomalies in the videos. We also suggest an even harder benchmark where anomalous activities should be spotted on highly variable scenes.

Authors

Laura Kart

1 papers

Niv Cohen

2 papers

TL;DR

Abstract

Authors

References30 items

Mean-Shifted Contrastive Loss for Anomaly Detection

Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies

Is Space-Time Attention All You Need for Video Understanding?

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision

Continual Learning for Anomaly Detection in Surveillance Videos

Learning Memory-Guided Normality for Anomaly Detection

Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection

Deep Nearest Neighbor Anomaly Detection

More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation

Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection

Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection

Using Pre-Training Can Improve Model Robustness and Uncertainty

Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video

A Short Note about Kinetics-600

Real-World Anomaly Detection in Surveillance Videos

Future Frame Prediction for Anomaly Detection - A New Baseline

A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

The “Something Something” Video Database for Learning and Evaluating Visual Common Sense

Learning Temporal Regularity in Video Sequences

Deep Residual Learning for Image Recognition

Anomaly detection in crowded scenes

Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates

A Day on Campus - An Anomaly Detection Dataset for Events in a Single Camera

BMAN: Bidirectional Multi-Scale Aggregation Networks for Abnormal Event Detection

Viral Bhalodia, and Nuno Vasconcelos

Using Pre-Training Can Improve Model Robustness and Uncertainty

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names