Data augmentation is a ubiquitous technique for improving image
classification when labeled data is scarce. Constraining the model predictions
to be invariant to diverse data augmentations effectively injects the desired
representational invariances to the model (e.g., invariance to photometric
variations) and helps improve accuracy. Compared to image data, the appearance
variations in videos are far more complex due to the additional temporal
dimension. Yet, data augmentation methods for videos remain under-explored.
This paper investigates various data augmentation strategies that capture
different video invariances, including photometric, geometric, temporal, and
actor/scene augmentations. When integrated with existing semi-supervised
learning frameworks, we show that our data augmentation strategy leads to
promising performance on the Kinetics-100/400, Mini-Something-v2, UCF-101, and
HMDB-51 datasets in the low-label regime. We also validate our data
augmentation strategy in the fully supervised setting and demonstrate improved
performance.

使用不同的数据增强策略对视频进行数据增强，结合现有的半监督学习框架，能够在低标签模式下提高 Kinetics-100/400, Mini-Something-v2, UCF-101 和 HMDB-51 数据集的性能，并在完全监督的情况下证明提高了性能。