Semi-supervised Active Learning for Video Action Detection

arXiv:2312.07169v2 Announce Type: replace
Abstract: In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for action detection. Video action detection requires spatio-temporal localization along with classification, which poses several challenges for both active learning informative sample selection as well as semi-supervised learning pseudo label generation. First, we propose NoiseAug, a simple augmentation strategy which …

abstract active learning arxiv classification cs.cv data detection focus localization novel sample semi-supervised temporal type video work