Adaptive Hierarchical Motion-Focused Model for Video Prediction

Video prediction is a promising task in computer vision for many real-world applications and worth exploring. Most existing methods generate new frames based on appearance features with few constrain, which results in blurry predictions. Recently, some motion-focused methods are proposed to alleviate the problem. However, it's difficult to capture the object motions from a video sequence and apply the learned motions to appearance, due to variety and complexity of real-world motions. In this paper, an adaptive hierarchical motion-focused model is introduced to predict realistic future frames. This model takes advantage of hierarchical motion modeling and adaptive transformation strategy, which can achieve better motion understanding and applying. We train our model end to end and employ the popular adversarial training to improve the quality of generations. Experiments on two challenging datasets: Penn Action and UCF101, demonstrate that the proposed model is effective and competitive with outstanding approaches.