arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.09469cs.CV
收藏

面向视频描述的视觉常识感知表示网络

Visual Commonsense-aware Representation Network for Video Captioning

University of Electronic Science and Technology of China(电子科技大学);Southwest Jiaotong University(西南交通大学)

Pengpeng Zeng, Haonan Zhang, Lianli Gao, Xiangpeng Li, Jin Qian, Heng Tao Shen

摘要:

生成视频的连续描述,即,视频描述要求在生成过程中充分利用视觉表示。现有的视频描述方法集中于探索时空表示及其关系以产生推断。然而,这些方法只利用了视频本身所包含的表面关联,而没有考虑视频数据集中存在的内在视觉常识知识,这可能会影响其知识认知能力,从而导致准确的描述。为了解决这个问题,我们提出了一个简单而有效的方法,称为视觉常识感知表示网络(VCRN),视频描述。具体来说,我们构建了一个视频字典,即插即用的组件,通过将所有视频特征从总数据集中聚类到多个聚类中心而无需额外的注释。每个中心隐式地表示视频域中的视觉常识概念,该视觉常识概念被用于我们提出的视觉概念选择(Visual Concept Selection,简称VCP)中以获得与视频相关的概念特征。接着,提出了一种概念整合生成(CIG)来增强字幕生成。在三个公开的视频描述基准测试:MSVD、MSR-VTT和VATEX上进行的大量实验表明,我们的方法达到了最先进的性能,表明了我们方法的有效性。此外,我们的方法被集成到现有的视频问答的方法,并提高了这种性能,进一步显示了我们的方法的推广。源代码已在https://github.com/zchoi/VCRN上发布。

英文摘要:

Generating consecutive descriptions for videos, i.e., Video Captioning, requires taking full advantage of visual representation along with the generation process. Existing video captioning methods focus on making an exploration of spatial-temporal representations and their relationships to produce inferences. However, such methods only exploit the superficial association contained in the video itself without considering the intrinsic visual commonsense knowledge that existed in a video dataset, which may hinder their capabilities of knowledge cognitive to reason accurate descriptions. To address this problem, we propose a simple yet effective method, called Visual Commonsense-aware Representation Network (VCRN), for video captioning. Specifically, we construct a Video Dictionary, a plug-and-play component, obtained by clustering all video features from the total dataset into multiple clustered centers without additional annotation. Each center implicitly represents a visual commonsense concept in the video domain, which is utilized in our proposed Visual Concept Selection (VCS) to obtain a video-related concept feature. Next, a Conceptual Integration Generation (CIG) is proposed to enhance the caption generation. Extensive experiments on three publicly video captioning benchmarks: MSVD, MSR-VTT, and VATEX, demonstrate that our method reaches state-of-the-art performance, indicating the effectiveness of our method. In addition, our approach is integrated into the existing method of video question answering and improves this performance, further showing the generalization of our method. Source code has been released at https://github.com/zchoi/VCRN.

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。

↑