Encouraging LSTMs to Anticipate Actions Very Early
This addresses the problem of early action recognition for applications like autonomous navigation, representing a strong specific gain in a domain-specific area.
The paper tackles action anticipation from partial videos by proposing a multi-stage LSTM architecture with a novel loss function to encourage early predictions, achieving relative accuracy increases of 22.0% on JHMDB-21, 14.0% on UT-Interaction, and 49.9% on UCF-101 compared to state-of-the-art methods.
In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos. As such, it is therefore key to the success of computer vision applications requiring to react as early as possible, such as autonomous navigation. In this paper, we propose a new action anticipation method that achieves high prediction accuracy even in the presence of a very small percentage of a video sequence. To this end, we develop a multi-stage LSTM architecture that leverages context-aware and action-aware features, and introduce a novel loss function that encourages the model to predict the correct class as early as possible. Our experiments on standard benchmark datasets evidence the benefits of our approach; We outperform the state-of-the-art action anticipation methods for early prediction by a relative increase in accuracy of 22.0% on JHMDB-21, 14.0% on UT-Interaction and 49.9% on UCF-101.