Deep video representation learning: a survey

This paper provides a review on representation learning for videos. We classify recent spatio-temporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective features for videos is a fundamental problem in computer vision tasks involving video analysis and understanding. Existing features can be generally categorized into spatial and temporal features. Their effectiveness under variations of illumination, occlusion, view and background are discussed. Finally, we discuss the remaining challenges in existing deep video representation learning studies.

Automated summary

This paper reviews representation learning for videos, discussing recent spatio-temporal feature learning methods and comparing their advantages and disadvantages for general video analysis. It emphasizes the importance of building effective video features in computer vision tasks and summarizes the effectiveness and challenges of existing spatial and temporal features.