Online Video Understanding: OVBench and VideoChat-Online

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zhenpeng, Li, Xinhao, Li, Jiaqi, Wang, Jing, Zeng, Xiangyu, Liang, Cheng, Wu, Tao, Chen, Xi, Li, Liang, Wang, Limin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913796763680768
author Huang, Zhenpeng
Li, Xinhao
Li, Jiaqi
Wang, Jing
Zeng, Xiangyu
Liang, Cheng
Wu, Tao
Chen, Xi
Li, Liang
Wang, Limin
author_facet Huang, Zhenpeng
Li, Xinhao
Li, Jiaqi
Wang, Jing
Zeng, Xiangyu
Liang, Cheng
Wu, Tao
Chen, Xi
Li, Liang
Wang, Limin
contents Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features 6 core task types across three temporal contexts-past, current, and future-forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy. % Our approach surpasses existing state-of-the-art offline models Qwen2-VL 7B and online models Flash-VStream, by 4.19% and 23.7% on OVBench, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Video Understanding: OVBench and VideoChat-Online
Huang, Zhenpeng
Li, Xinhao
Li, Jiaqi
Wang, Jing
Zeng, Xiangyu
Liang, Cheng
Wu, Tao
Chen, Xi
Li, Liang
Wang, Limin
Computer Vision and Pattern Recognition
Machine Learning
Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features 6 core task types across three temporal contexts-past, current, and future-forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy. % Our approach surpasses existing state-of-the-art offline models Qwen2-VL 7B and online models Flash-VStream, by 4.19% and 23.7% on OVBench, respectively.
title Online Video Understanding: OVBench and VideoChat-Online
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.00584