ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Mengxue, Chen, Xiaodong, Liu, Wu, Li, Alicia, Zhao, Yao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917805867139072
author Qu, Mengxue
Chen, Xiaodong
Liu, Wu
Li, Alicia
Zhao, Yao
author_facet Qu, Mengxue
Chen, Xiaodong
Liu, Wu
Li, Alicia
Zhao, Yao
contents Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (LLMs) for zero-shot video temporal grounding. Our ChatVTG leverages Video Dialogue LLMs to generate multi-granularity segment captions and matches these captions with the given query for coarse temporal grounding, circumventing the need for paired annotation data. Furthermore, to obtain more precise temporal grounding results, we employ moment refinement for fine-grained caption proposals. Extensive experiments on three mainstream VTG datasets, including Charades-STA, ActivityNet-Captions, and TACoS, demonstrate the effectiveness of ChatVTG. Our ChatVTG surpasses the performance of current zero-shot methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12813
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
Qu, Mengxue
Chen, Xiaodong
Liu, Wu
Li, Alicia
Zhao, Yao
Multimedia
Computer Vision and Pattern Recognition
Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is labor-intensive and prone to human biases. To address these challenges, we present ChatVTG, a novel approach that utilizes Video Dialogue Large Language Models (LLMs) for zero-shot video temporal grounding. Our ChatVTG leverages Video Dialogue LLMs to generate multi-granularity segment captions and matches these captions with the given query for coarse temporal grounding, circumventing the need for paired annotation data. Furthermore, to obtain more precise temporal grounding results, we employ moment refinement for fine-grained caption proposals. Extensive experiments on three mainstream VTG datasets, including Charades-STA, ActivityNet-Captions, and TACoS, demonstrate the effectiveness of ChatVTG. Our ChatVTG surpasses the performance of current zero-shot methods.
title ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
topic Multimedia
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.12813