Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhong, Yaoyao, Qi, Mengshi, Wang, Rui, Qiu, Yuhan, Zhang, Yang, Ma, Huadong
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.00401
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912164271357952
author Zhong, Yaoyao
Qi, Mengshi
Wang, Rui
Qiu, Yuhan
Zhang, Yang
Ma, Huadong
author_facet Zhong, Yaoyao
Qi, Mengshi
Wang, Rui
Qiu, Yuhan
Zhang, Yang
Ma, Huadong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_00401
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
Zhong, Yaoyao
Qi, Mengshi
Wang, Rui
Qiu, Yuhan
Zhang, Yang
Ma, Huadong
Computer Vision and Pattern Recognition
Multimedia
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.
title VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2312.00401