Knowledge Commons of Institute of Automation,CAS
DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization | |
Yujia Zhang1,2![]() ![]() ![]() | |
2019-05 | |
会议名称 | ACM China Turing Award Celebration Conference |
会议日期 | 2019-5 |
会议地点 | Chengdu, China |
摘要 | Video summarization targets the challenge of finding the smallest subset of frames, while still conveying the whole story of a given video. Thus it is of great significance for large-scale video understanding, allowing efficient processing of the large amount of videos that are uploaded every day. In this paper, we introduce a Dilated Temporal Relational Adversarial Network (DTR-GAN) to achieve frame-level video summarization. The dilated temporal relational units in the generator aim to exploit multi-scale temporal context in order to select key frames. To ensure that the model predicts high quality summaries, we present a discriminator that learns to enhance both the information completeness and compactness via a three-player loss. Experiments on the public TVSum dataset demonstrate the effectiveness of the proposed approach. |
七大方向——子方向分类 | 多模态智能 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23649 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Yujia Zhang |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Machine Learning Group, UiT The Arctic University of Norway |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yujia Zhang,Michael Kampffmeyer,Xiaoguang Zhao,et al. DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
sigai.pdf(7580KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论