arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08247cs.CV
收藏

学习循环:用于动作识别的时间一致性特征发现

Learn to cycle: Time-consistent feature discovery for action recognition

Utrecht University(乌得勒支大学)

Alexandros Stergiou, Ronald Poppe

摘要:

在时间变化上进行概括是视频中有效动作识别的先决条件。尽管深度神经网络取得了重大进展,但关注与动作的整体表现相关的短期辨别性运动仍然是一个挑战。我们通过允许一些灵活性来发现相关的时空特征来应对这一挑战。我们介绍了挤压和递归时间门(SRTG),一种方法,有利于输入类似的激活与潜在的时间变化。我们用一个新的CNN块来实现这个想法,该块使用LSTM来封装特征动态,并结合一个时间门来评估发现的动态和建模特征的一致性。当使用SRTG块时,我们表现出一致的改进,GFLOPs的数量只有最小的增加。在Kinetics-700上,我们的表现与当前最先进的模型相当,并且在HACS,Moments in Time,UCF-101和HMDB-51上表现优于这些模型。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑