Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
This addresses the need for efficient self-supervised learning in video analysis, offering a flexible and interpretable approach, though it appears incremental as it builds on existing 3D-CNN frameworks.
The paper tackles the problem of learning spatial-temporal representations from videos by proposing Video Cloze Procedure (VCP), a self-supervised method that generates blanks and options to predict operation categories, resulting in models that outperform state-of-the-art self-supervised models on action recognition and video retrieval benchmarks.
We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates "blanks" by withholding video clips and then creates "options" by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with "options" and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning. As a target task, it can assess learned representation models in a uniform and interpretable manner. With VCP, we train spatial-temporal representation models (3D-CNNs) and apply such models on action recognition and video retrieval tasks. Experiments on commonly used benchmarks show that the trained models outperform the state-of-the-art self-supervised models with significant margins.