Long History Short-Term Memory for Long-Term Video Prediction

While video prediction approaches have advanced considerably in recent years, learning to predict long-term future is challenging — ambiguous future or error propagation over time yield blurry predictions. To address this challenge, existing algorithms rely on extra supervision (e.g., action or object pose), motion flow learning, or adversarial training. In this paper, we propose a new recurrent unit, Long History Short-Term Memory (LH-STM). LH-STM incorporates long history states into a recurrent unit to learn longer range dependencies. To capture spatio-temporal dynamics in videos, we combined LH-STM with the Context-aware Video Prediction model (ContextVP). Our experiments on the KTH human actions and BAIR robot pushing datasets demonstrate that our approach produces not only sharper near-future predictions, but also farther into the future compared to the state-of-the-art methods.