VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT

Author:

Yifang Xu, Yunzhuo Sun, Zien Xie, Benxiang Zhai, Sidan Du

Keyword:

Computer Science, Computer Vision and Pattern Recognition, Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI)

journal:

date:

2024-03-04 00:00:00

Abstract

Video temporal grounding (VTG) aims to locate specific temporal segments from an untrimmed video based on a linguistic query. Most existing VTG models are trained on extensive annotated video-text pairs, a process that not only introduces human biases from the queries but also incurs significant computational costs. To tackle these challenges, we propose VTG-GPT, a GPT-based method for zero-shot VTG without training or fine-tuning. To reduce prejudice in the original query, we employ Baichuan2 to generate debiased queries. To lessen redundant information in videos, we apply MiniGPT-v2 to transform visual content into more precise captions. Finally, we devise the proposal generator and post-processing to produce accurate segments from debiased queries and image captions. Extensive experiments demonstrate that VTG-GPT significantly outperforms SOTA methods in zero-shot settings and surpasses unsupervised approaches. More notably, it achieves competitive performance comparable to supervised methods. The code is available on https://github.com/YoucanBaby/VTG-GPT

PDF: VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT.pdf