Themes Informed Audio-visual Correspondence Learning
This addresses the problem of multimodal learning for applications like social media videos, but it is incremental as it builds on existing audio-visual correspondence methods with a theme-based approach.
The paper tackled the challenge of learning audio-visual correspondence in short user-generated videos, proposing a new framework that leverages video themes, and achieved a 23.15% absolute improvement over baselines on a released dataset of 85,432 advertisement videos.
The applications of short-term user-generated video (UGV), such as Snapchat, and Youtube short-term videos, booms recently, raising lots of multimodal machine learning tasks. Among them, learning the correspondence between audio and visual information from videos is a challenging one. Most previous work of the audio-visual correspondence(AVC) learning only investigated constrained videos or simple settings, which may not fit the application of UGV. In this paper, we proposed new principles for AVC and introduced a new framework to set sight of videos' themes to facilitate AVC learning. We also released the KWAI-AD-AudVis corpus which contained 85432 short advertisement videos (around 913 hours) made by users. We evaluated our proposed approach on this corpus, and it was able to outperform the baseline by 23.15% absolute difference.