Year: 2020
Type: article
Abstract: This work addresses the long-standing problem of robustly learning precise temporal point event localization despite only having access to poorly aligned labels for training.To that end, we introduce a novel loss function that relaxes the reliance of the training on the exact position of labels, thus allowing for a softer learning of event localization.We demonstrate state-of-theart performance against standard benchmarks in challenging experiments.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Nvidia
OpenAlex ID: W3135796411