On Encoding Temporal Evolution for Real-time Action Prediction
This addresses the need for real-time action prediction in applications like robotics and autonomous vehicles, representing an incremental improvement over existing methods.
The paper tackled the problem of anticipating future actions in real-time systems by focusing on motion evolution in video frames, achieving high accuracy and outperforming state-of-the-art methods on three benchmark datasets.
Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars. While recent works have addressed prediction of raw RGB pixel values, we focus on anticipating the motion evolution in future video frames. To this end, we construct dynamic images (DIs) by summarising moving pixels through a sequence of future frames. We train a convolutional LSTMs to predict the next DIs based on an unsupervised learning process, and then recognise the activity associated with the predicted DI. We demonstrate the effectiveness of our approach on 3 benchmark action datasets showing that despite running on videos with complex activities, our approach is able to anticipate the next human action with high accuracy and obtain better results than the state-of-the-art methods.