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

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 viewagnostic 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 pseudolabels 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 howto activities, our model consistently outperforms state-ofthe-art baselines, both with quantitative metrics and human evaluation. Project: https://vision.cs.utexas . edu/projects/which-view-shows-it-best.