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 to generate improved pseudolabels for unlabeled target videos. Our self-training process successfully leverages the strengths of both models to achieve strong transfer performance across domains. We evaluate our approach on multiple video domain adaptation benchmarks and observe significant improvements upon previously reported results.

翻译：本文针对视频动作识别中的无监督域适应问题展开研究。我们提出的方法UNITE通过图像教师模型，使视频学生模型适应目标域。首先，UNITE利用自监督预训练，借助教师引导的掩码蒸馏目标，促进目标域视频的判别性特征学习。随后，针对掩码目标数据执行自训练，联合视频学生模型与图像教师模型为未标注的目标视频生成更优的伪标签。该自训练过程有效融合了两种模型的优势，实现了跨域的强迁移性能。我们在多个视频域适应基准上评估了方法，观察到相较于已有成果的显著提升。