The task of predicting future actions from a video is crucial for a
real-world agent interacting with others. When anticipating actions in the
distant future, we humans typically consider long-term relations over the whole
sequence of actions, i.e., not only observed actions in the past but also
potential actions in the future. In a similar spirit, we propose an end-to-end
attention model for action anticipation, dubbed Future Transformer (FUTR), that
leverages global attention over all input frames and output tokens to predict a
minutes-long sequence of future actions. Unlike the previous autoregressive
models, the proposed method learns to predict the whole sequence of future
actions in parallel decoding, enabling more accurate and fast inference for
long-term anticipation. We evaluate our method on two standard benchmarks for
long-term action anticipation, Breakfast and 50 Salads, achieving
state-of-the-art results.

提出了一种全新的基于注意力机制的动作预测模型，称为 Future Transformer (FUTR)，它能够学习全局的视频动作信息，以预测长达数分钟的未来动作序列，和传统的自回归模型相比，FUTR 可以更准确、更快速地进行长期预测。在两个标准数据集 Breakfast 和 50Salads 上进行了实验，FUTR 模型取得了最新的最优结果。