Temporal modeling is the key for action recognition in videos, but traditional 2D CNNs do
not capture temporal relationships well. 3D CNNs can achieve good performance, but are …

Recently, deep learning methods have been extensively applied for action recognition in
videos. Most existing deep networks equally treat every video frame and directly assign a …

Deep neural networks have received increasing attention in human action recognition.
Previous research has established that utilizing 3D convolution is a reasonable approach to …

The work in this paper is driven by the question if spatio-temporal correlations are enough
for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local …

Deep ConvNets have shown its good performance in image classification tasks. However it
still remains as a problem in deep video representation for action recognition. The problem …

Self-attention learns pairwise interactions to model long-range dependencies, yielding great
improvements for video action recognition. In this paper, we seek a deeper understanding of …

Action Recognition is a fundamental task in computer vision field, with a wide range of
applications in autonomous driving, security monitoring, etc. However, previous action …

The modeling, computational complexity, and accuracy of spatio-temporal models are the
three major foci in the field of video action recognition. The traditional 2D convolution has …

Understanding human actions in wild videos is an important task with a broad range of
applications. In this paper we propose a novel approach named Hierarchical Attention …

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling
such visual tempos of different actions facilitates their recognition. Previous works often …