In this paper, a novel two-stream architecture has been designed to improve action
recognition accuracy for hockey using three main components. First, pose is estimated via …

A convolutional neural network (CNN) has been designed to interpret player actions in ice
hockey video. The hourglass network is employed as the base to generate player pose …

In recent years, many works in the video action recognition literature have shown that two
stream models (combining spatial and temporal input streams) are necessary for achieving …

Artificial intelligence models are widely used in the field of human activity recognition, and
human action recognition is an important aspect of human activity recognition. The core of …

Most current action recognition methods heavily rely on appearance information by taking
an RGB sequence of entire image regions as input. While being effective in exploiting …

Although action recognition in videos is widely studied, current methods often fail on real-
world datasets. Many recent approaches improve accuracy and robustness to cope with …

Convolutional neural networks have recently shown proficiency at recognizing actions in
RGB video. Existing models are generally very deep, requiring large amounts of data to train …

Recognizing human actions in videos is a challenging problem owning to complex motion
appearance, various backgrounds and semantic gap between low-level features and high …

Most state-of-the-art methods for action recognition rely on a two-stream architecture that
processes appearance and motion independently. In this paper, we claim that considering …

Taking advantage of human pose data for understanding human activities has attracted
much attention these days. However, state-of-the-art pose estimators struggle in obtaining …