Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

arXiv:2312.02914v3 Announce Type: replace-cross
Abstract: In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first employs self-supervised pre-training to promote discriminative feature learning on target domain videos using a teacher-guided masked distillation objective. We then perform self-training on masked target data, using the video student model and image teacher model together …

abstract action recognition adapt arxiv call collaborative cs.cv cs.lg domain domain adaptation image pre-training promote recognition self-training training type unite unsupervised video work