Enhancing Temporal Modeling of Video LLMs via Time Gating

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zi-Yuan, Zhong, Yiwu, Huang, Shijia, Lyu, Michael R., Wang, Liwei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910640924262400
author Hu, Zi-Yuan
Zhong, Yiwu
Huang, Shijia
Lyu, Michael R.
Wang, Liwei
author_facet Hu, Zi-Yuan
Zhong, Yiwu
Huang, Shijia
Lyu, Michael R.
Wang, Liwei
contents Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding. To address this gap, we propose a Time Gating Video LLM (TG-Vid) designed to enhance temporal modeling through a novel Time Gating module (TG). The TG module employs a time gating mechanism on its sub-modules, comprising gating spatial attention, gating temporal attention, and gating MLP. This architecture enables our model to achieve a robust understanding of temporal information within videos. Extensive evaluation of temporal-sensitive video benchmarks (i.e., MVBench, TempCompass, and NExT-QA) demonstrates that our TG-Vid model significantly outperforms the existing Video LLMs. Further, comprehensive ablation studies validate that the performance gains are attributed to the designs of our TG module. Our code is available at https://github.com/LaVi-Lab/TG-Vid.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Temporal Modeling of Video LLMs via Time Gating
Hu, Zi-Yuan
Zhong, Yiwu
Huang, Shijia
Lyu, Michael R.
Wang, Liwei
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding. To address this gap, we propose a Time Gating Video LLM (TG-Vid) designed to enhance temporal modeling through a novel Time Gating module (TG). The TG module employs a time gating mechanism on its sub-modules, comprising gating spatial attention, gating temporal attention, and gating MLP. This architecture enables our model to achieve a robust understanding of temporal information within videos. Extensive evaluation of temporal-sensitive video benchmarks (i.e., MVBench, TempCompass, and NExT-QA) demonstrates that our TG-Vid model significantly outperforms the existing Video LLMs. Further, comprehensive ablation studies validate that the performance gains are attributed to the designs of our TG module. Our code is available at https://github.com/LaVi-Lab/TG-Vid.
title Enhancing Temporal Modeling of Video LLMs via Time Gating
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.05714