Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos

TL;DR

This paper introduces LangView, a weakly supervised framework that identifies the most informative viewpoint in multi-view instructional videos using language cues, outperforming existing methods without requiring explicit view supervision.

Contribution

We propose a novel weakly supervised approach that leverages language to predict the most informative view in multi-view videos, eliminating the need for costly view annotations.

Findings

Outperforms state-of-the-art baselines on two datasets

Uses language to effectively identify best viewpoints

Achieves higher accuracy with human evaluation support

Abstract

Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive "best-view" supervision to answer this question, limiting their applicability. We propose a weakly supervised approach that leverages language accompanying an instructional multi-view video as a means to recover its most informative viewpoint(s). Our key hypothesis is that the more accurately an individual view can predict a view-agnostic text summary, the more informative it is. To put this into action, we propose LangView, a framework that uses the relative accuracy of view-dependent caption predictions as a proxy for best view pseudo-labels. Then, those pseudo-labels are used to train a view selector, together with an auxiliary camera pose predictor that enhances view-sensitivity. During inference, our model takes as input only a multi-view video--no language or camera poses--and returns the best viewpoint to watch at each timestep. On two challenging datasets comprised of diverse multi-camera setups and how-to activities, our model consistently outperforms state-of-the-art baselines, both with quantitative metrics and human evaluation. Project page: https://vision.cs.utexas.edu/projects/which-view-shows-it-best.