论文标题
人群的智慧：早期行动预测的时间渐进式关注
The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction
论文作者
论文摘要
早期动作预测通常在视频开始时推断出部分观察到的视频的持续动作。我们提出了一个基于瓶颈的注意模型，该模型通过在细节到斑点的尺度上进行逐步采样来捕获动作的演变。我们提出的时间渐进式（TEMPR）模型由多个注意力塔组成，每个量表都一个。预测的行动标签是基于考虑这些塔的信心的集体协议。四个视频数据集的广泛实验展示了对各种编码器体系结构的早期动作预测任务的最新性能。我们通过详细消融证明了TEMPR的有效性和一致性。
Early action prediction deals with inferring the ongoing action from partially-observed videos, typically at the outset of the video. We propose a bottleneck-based attention model that captures the evolution of the action, through progressive sampling over fine-to-coarse scales. Our proposed Temporal Progressive (TemPr) model is composed of multiple attention towers, one for each scale. The predicted action label is based on the collective agreement considering confidences of these towers. Extensive experiments over four video datasets showcase state-of-the-art performance on the task of Early Action Prediction across a range of encoder architectures. We demonstrate the effectiveness and consistency of TemPr through detailed ablations.
