MVBIND：通过嵌入空间绑定实现面向视频的自监督音乐推荐
MVBIND: Self-Supervised Music Recommendation For Videos Via Embedding Space Binding
AI总结：
针对短视频缺乏自动背景音乐推荐方法的问题，提出自监督跨模态检索模型MVBind，通过嵌入空间绑定实现音乐推荐，构建SVM-10K数据集，性能优于基线方法且将开源数据与代码。
摘要：
近年来短视频发展迅速，通常同时包含视觉和音频模态。背景音乐对短视频至关重要，会显著影响观众的情绪。但目前短视频的背景音乐一般由视频制作者选择，缺乏面向短视频的自动音乐推荐方法。本文提出MVBind，一种用于跨模态检索的创新型音乐-视频嵌入空间绑定模型。MVBind采用自监督方法，无需人工标注，直接从数据中获取模态间关系的固有知识。此外，为弥补短视频领域缺乏对应音视频配对数据集的问题，我们构建了SVM-10K（带音乐的短视频-10K）数据集，该数据集主要由精心挑选的短视频组成。在该数据集上，MVBind相比其他基线方法表现出显著提升的性能。我们将公开所构建的数据集和代码，以助力未来研究。
英文摘要：
Recent years have witnessed the rapid development of short videos, which usually contain both visual and audio modalities. Background music is important to the short videos, which can significantly influence the emotions of the viewers. However, at present, the background music of short videos is generally chosen by the video producer, and there is a lack of automatic music recommendation methods for short videos. This paper introduces MVBind, an innovative Music-Video embedding space Binding model for cross-modal retrieval. MVBind operates as a self-supervised approach, acquiring inherent knowledge of intermodal relationships directly from data, without the need of manual annotations. Additionally, to compensate the lack of a corresponding musical-visual pair dataset for short videos, we construct a dataset, SVM-10K(Short Video with Music-10K), which mainly consists of meticulously selected short videos. On this dataset, MVBind manifests significantly improved performance compared to other baseline methods. The constructed dataset and code will be released to facilitate future research.
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。
