Pseudo Dataset Generation for Out-of-Domain Multi-Camera View Recommendation

TL;DR

This paper introduces a method to generate pseudo-labeled datasets from regular videos to improve multi-camera view recommendation models, significantly enhancing their accuracy in unseen domains.

Contribution

It proposes transforming ordinary videos into pseudo-labeled datasets, addressing data scarcity and domain generalization issues in multi-camera view recommendation.

Findings

68% relative accuracy improvement in target domain

Bridges the gap between in-domain and unseen domains

Effective pseudo-labeling from edited videos

Abstract

Multi-camera systems are indispensable in movies, TV shows, and other media. Selecting the appropriate camera at every timestamp has a decisive impact on production quality and audience preferences. Learning-based view recommendation frameworks can assist professionals in decision-making. However, they often struggle outside of their training domains. The scarcity of labeled multi-camera view recommendation datasets exacerbates the issue. Based on the insight that many videos are edited from the original multi-camera videos, we propose transforming regular videos into pseudo-labeled multi-camera view recommendation datasets. Promisingly, by training the model on pseudo-labeled datasets stemming from videos in the target domain, we achieve a 68% relative improvement in the model's accuracy in the target domain and bridge the accuracy gap between in-domain and never-before-seen domains.