U-LanD: Uncertainty-Driven Video Landmark Detection.
Volume: 41, Issue: 4, Pages: 793 - 804
Published: Apr 1, 2022
Abstract
This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in...
Paper Details
Title
U-LanD: Uncertainty-Driven Video Landmark Detection.
Published Date
Apr 1, 2022
Volume
41
Issue
4
Pages
793 - 804
Citation AnalysisPro
You’ll need to upgrade your plan to Pro
Looking to understand the true influence of a researcher’s work across journals & affiliations?
- Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
- Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.
Notes
History