Garbage in, garbage out: Zero-shot detection of crime using Large Language Models

2023/07/04 by Rajesh Vasa, Simmons, Anj, Vasa, Rajesh · 1 citation
Computer Science · Medicine · #Multimodal Machine Learning Applications #Viral Infections and Outbreaks Research #Anomaly Detection Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2307.06844

Abstract

This paper proposes exploiting the common sense knowledge learned by large language models to perform zero-shot reasoning about crimes given textual descriptions of surveillance videos. We show that when video is (manually) converted to high quality textual descriptions, large language models are capable of detecting and classifying crimes with state-of-the-art performance using only zero-shot reasoning. However, existing automated video-to-text approaches are unable to generate video descriptions of sufficient quality to support reasoning (garbage video descriptions into the large language model, garbage out).

Cited by

• The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge

Related

• Zero-Shot Action Recognition in Surveillance Videos
• Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges
• Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
• Large Language Models for Video Surveillance Applications
• A Benchmark for Crime Surveillance Video Analysis with Large Models