arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.04478cs.CVcs.CL
收藏

基于视觉语言模型的高效视频理解

Prompting Visual-Language Models for Efficient Video Understanding

Shanghai Jiao Tong University(上海交通大学);University of Oxford(牛津大学)

Chen Ju, Tengda Han, Kunhao Zheng, Ya Zhang, Weidi Xie

摘要:

基于图像的视觉语言(I-VL)预训练在从大规模网络数据中学习联合视觉-文本表示方面取得了巨大的成功,揭示了zero-shot泛化的显着能力。本文提出了一个简单但强大的基线,以有效地适应预训练的I-VL模型,并利用其强大的能力,资源饥饿的视频理解任务,以最少的训练。具体来说,我们建议优化一些随机向量,称为连续提示向量,将视频相关任务转换为与预训练目标相同的格式。此外,为了弥合静态图像和视频之间的差距,时间信息编码与轻量级的Transformers堆叠上的逐帧视觉功能。在实验上,我们进行了广泛的消融研究,以分析关键部件。在动作识别,动作定位和文本视频检索的10个公共基准测试中,在闭集,Few-Shot和zero-shot场景中,我们实现了与现有方法相比具有竞争力或最先进的性能,尽管优化了显着较少的参数。

英文摘要:

Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but strong baseline to efficiently adapt the pre-trained I-VL model, and exploit its powerful ability for resource-hungry video understanding tasks, with minimal training. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert video-related tasks into the same format as the pre-training objectives. In addition, to bridge the gap between static images and videos, temporal information is encoded with lightweight Transformers stacking on top of frame-wise visual features. Experimentally, we conduct extensive ablation studies to analyse the critical components. On 10 public benchmarks of action recognition, action localisation, and text-video retrieval, across closed-set, few-shot, and zero-shot scenarios, we achieve competitive or state-of-the-art performance to existing methods, despite optimising significantly fewer parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑