VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things

TL;DR

VIoTGPT is a framework leveraging large language models to intelligently schedule and analyze vision tools in Video Internet of Things, supported by a new dataset and benchmark for multi-model evaluation.

Contribution

The paper introduces VIoTGPT, a novel LLM-based framework for intelligent vision tool scheduling in VIoT, along with the VIoT-Tool dataset and benchmark for model evaluation.

Findings

Demonstrates effectiveness of VIoTGPT through experiments

Supports intelligent, human-centered VIoT applications

Provides a new dataset and benchmark for vision model evaluation

Abstract

Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data. How to schedule the domain-specific perceiving models and analyze the collected videos uniformly, efficiently, and especially intelligently to accomplish complicated tasks is challenging. To address the challenge, we build VIoTGPT, the framework based on LLMs to correctly interact with humans, query knowledge videos, and invoke vision models to analyze multimedia data collaboratively. To support VIoTGPT and related future works, we meticulously crafted the VIoT-Tool dataset, including the training dataset and the benchmark involving 11 representative vision models across three categories based on semi-automatic annotations. To guide LLM to act as the intelligent agent towards intelligent VIoT, we resort to the ReAct instruction tuning method based on VIoT-Tool to learn the tool capability. Quantitative and qualitative experiments and analyses demonstrate the effectiveness of VIoTGPT. We believe VIoTGPT contributes to improving human-centered experiences in VIoT applications. The project website is https://github.com/zhongyy/VIoTGPT.