LazyVLM: Neuro-Symbolic Approach to Video Analytics

TL;DR

LazyVLM is a neuro-symbolic video analytics system that combines user-friendly querying with scalable processing by decomposing complex video queries into efficient operations, addressing the limitations of existing VLMs.

Contribution

LazyVLM introduces a scalable neuro-symbolic framework that enables complex multi-frame video queries through a semi-structured interface, improving efficiency and flexibility.

Findings

Provides robust and efficient video querying at scale.

Decomposes complex queries into fine-grained operations.

Outperforms traditional VLMs in scalability and flexibility.

Abstract

Current video analytics approaches face a fundamental trade-off between flexibility and efficiency. End-to-end Vision Language Models (VLMs) often struggle with long-context processing and incur high computational costs, while neural-symbolic methods depend heavily on manual labeling and rigid rule design. In this paper, we introduce LazyVLM, a neuro-symbolic video analytics system that provides a user-friendly query interface similar to VLMs, while addressing their scalability limitation. LazyVLM enables users to effortlessly drop in video data and specify complex multi-frame video queries using a semi-structured text interface for video analytics. To address the scalability limitations of VLMs, LazyVLM decomposes multi-frame video queries into fine-grained operations and offloads the bulk of the processing to efficient relational query execution and vector similarity search. We demonstrate that LazyVLM provides a robust, efficient, and user-friendly solution for querying open-domain video data at scale.