Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

TL;DR

This paper introduces a comprehensive benchmark and evaluation metric for understanding the causes, reasons, and severity of video anomalies, advancing beyond detection to explainability.

Contribution

It presents the CUVA benchmark with detailed annotations for anomaly type, cause, and effect, along with MMEval, a new metric for assessing causation understanding in videos.

Findings

The MMEval metric better aligns with human judgment.

The prompt-based approach outperforms existing methods.

The dataset enables detailed causation analysis of video anomalies.

Abstract

Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on anomaly detection and localization, our focus is on more practicality, prompting us to raise the following crucial questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we present a comprehensive benchmark for Causation Understanding of Video Anomaly (CUVA). Specifically, each instance of the proposed benchmark involves three sets of human annotations to indicate the "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. In addition, we also introduce MMEval, a novel evaluation metric designed to better align with human preferences for CUVA, facilitating the measurement of existing LLMs in comprehending the underlying cause and corresponding effect of video anomalies. Finally, we propose a novel prompt-based method that can serve as a baseline approach for the challenging CUVA. We conduct extensive experiments to show the superiority of our evaluation metric and the prompt-based approach. Our code and dataset are available at https://github.com/fesvhtr/CUVA.