论文标题
学会循环：偶然的功能发现以进行动作识别
Learn to cycle: Time-consistent feature discovery for action recognition
论文作者
论文摘要
概括时间变化是在视频中有效采取行动识别的先决条件。尽管深层神经网络取得了重大进展，但与动作的整体性能有关的短期歧视动作仍然是一个挑战。我们通过在发现相关时空特征时允许灵活性来应对这一挑战。我们引入了挤压和递归时间门（SRTG），这种方法有利于具有相似激活的输入，具有潜在的时间变化。我们使用一个新颖的CNN块实现了这个想法，该块使用LSTM封装了特征动力学，并与负责评估发现的动力学和建模功能的一致性的时间门结合使用。当使用SRTG块时，我们显示出一致的改进，而Gflops数量只有最小的增加。在Kinetics-700上，我们以当前最新模型的形式表现出色，并且在HAC，时间时刻，UCF-101和HMDB-51上表现出色。
Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to focus on short-term discriminative motions in relation to the overall performance of an action. We address this challenge by allowing some flexibility in discovering relevant spatio-temporal features. We introduce Squeeze and Recursion Temporal Gates (SRTG), an approach that favors inputs with similar activations with potential temporal variations. We implement this idea with a novel CNN block that uses an LSTM to encapsulate feature dynamics, in conjunction with a temporal gate that is responsible for evaluating the consistency of the discovered dynamics and the modeled features. We show consistent improvement when using SRTG blocks, with only a minimal increase in the number of GFLOPs. On Kinetics-700, we perform on par with current state-of-the-art models, and outperform these on HACS, Moments in Time, UCF-101 and HMDB-51.
