论文标题
视频音乐检索：双路横式模式网络
Video-Music Retrieval:A Dual-Path Cross-Modal Network
论文作者
论文摘要
我们建议一种为视频推荐背景音乐的方法。当前的作品很少考虑音乐的情感信息，这对于视频音乐检索至关重要。为了实现这一目标，我们设计了两个途径来处理模式之间的内容信息和情感信息。根据视频和音乐的特征，我们设计了各种特征提取方案和共同表示空间。更重要的是，我们建议一种将内容信息与情感信息相结合的方法。此外，我们对经典指标损失进行了改进，以更适合这项任务。实验表明，这种双重路径视频音乐检索网络可以有效合并信息。与现有方法相比，检索任务评估索引：增加召回@1乘3.94，将@25召回16.36。
We propose a method to recommend background music for videos. Current work rarely considers the emotional information of music, which is essential for video music retrieval. To achieve this, we design two paths to process content information and emotional information between modal. Based on characteristics of video and music, we design various feature extraction schemes and common representation spaces. More importantly, we propose a way to combine content information with emotional information. Additionally, we make improvements to the classical metric loss to be more suited to this task. Experiments show that this dual path video music retrieval network can effectively merge information. Compare with existing methods, the retrieval task evaluation index: increasing Recall@1 by 3.94 and Recall@25 by 16.36.
