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 2008.08502cs.CV
收藏

学习完整长度电影中的预告片时刻

Learning Trailer Moments in Full-Length Movies

Rutgers University(罗格斯大学);Netflix(奈飞);Twitch

Lezi Wang, Dong Liu, Rohit Puri, Dimitris N. Metaxas

摘要:

一部电影的关键时刻从剧本中脱颖而出,抓住观众的注意力,使电影浏览效率。但由于缺乏注释,使得现有的方法不适用于电影关键时刻检测。为了摆脱人工注释,我们利用官方发布的预告片作为弱监督来学习一个可以从全长电影中检测关键时刻的模型。我们引入了一种新的排名网络,该网络利用电影和预告片之间的共同注意力作为指导来生成训练对,其中与预告片高度校正的时刻预计将比不相关的时刻得分更高。此外,我们提出了一个对比注意力模块,以提高功能表示,使关键和非关键时刻的功能之间的比较对比最大化。我们构建了第一个电影预告片数据集,所提出的Co-Attention辅助排名网络甚至比监督方法表现出更好的性能。我们的对比注意力模块的有效性也通过在公共基准上的最新技术的性能改进来证明。

英文摘要:

A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient. But a lack of annotations makes the existing approaches not applicable to movie key moment detection. To get rid of human annotations, we leverage the officially-released trailers as the weak supervision to learn a model that can detect the key moments from full-length movies. We introduce a novel ranking network that utilizes the Co-Attention between movies and trailers as guidance to generate the training pairs, where the moments highly corrected with trailers are expected to be scored higher than the uncorrelated moments. Additionally, we propose a Contrastive Attention module to enhance the feature representations such that the comparative contrast between features of the key and non-key moments are maximized. We construct the first movie-trailer dataset, and the proposed Co-Attention assisted ranking network shows superior performance even over the supervised approach. The effectiveness of our Contrastive Attention module is also demonstrated by the performance improvement over the state-of-the-art on the public benchmarks.

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。

↑