Recent contrastive language image pre-training has led to learning highly transferable and robust image representations. However, adapting these models to video domains with minimal supervision remains an open problem. We explore a simple step in that direction, using language tied self-supervised learning to adapt an image CLIP model to the video domain. A backbone modified for temporal modeling is trained under self-distillation settings with train objectives operating in an action concept space. Feature vectors of various action concepts extracted from a language encoder using relevant textual prompts construct this space. We introduce two train objectives, concept distillation and concept alignment, that retain generality of original representations while enforcing relations between actions and their attributes. Our approach improves zero-shot and linear probing performance on three action recognition benchmarks.

翻译：近期基于对比学习的语言-图像预训练方法已能学习到高度可迁移且鲁棒的图像表征。然而，如何以最小监督方式将这些模型适配到视频领域仍是一个开放性问题。我们探索了该方向的一个简单步骤：利用语言自监督学习将图像CLIP模型适配到视频领域。经过时序建模改进的骨干网络在自蒸馏设置下训练，其训练目标在动作概念空间中运作。通过相关文本提示从语言编码器中提取的各类动作概念的特征向量构成了该空间。我们提出了两种训练目标——概念蒸馏与概念对齐——在保持原始表征通用性的同时强化动作及其属性间的关联。该方法在三个动作识别基准测试中提升了零样本与线性探测性能。