ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos

arXiv:2404.06243v1 Announce Type: cross
Abstract: Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised methods require large annotated datasets for training, which are expensive and time-consuming to acquire. This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition. Our framework leverages both labeled and unlabelled data to robustly learn action representations in …

action recognition arxiv cs.ai cs.cv cs.hc cs.lg cs.mm hybrid recognition resnet semi-supervised transformer type videos