We investigate the problem of human action recognition by studying the effects of fusing
feature streams retrieved from color and depth sequences. Our main contribution is two-fold …

The local spatio-temporal descriptor and feature encoding algorithm are two crucial key
steps for human action recognition based on spatio-temporal interest points (STIP). Since …

Practically, action recognition using deep learning approaches are slow because of high
temporal redundancy and large size of the raw video data. One of the solutions for boosting …

The biggest difference between video-based action recognition and image-based action
recognition is that the former has an extra feature of time dimension. Most methods of action …

For a long-term complex Action, it is typically composed of various short-term Actions. The
speed and importance of these short-term Actions directly affect the recognition results …

In this paper, we investigate action recognition using an inexpensive RGB-D sensor
(Microsoft Kinect). First, a depth spatial-temporal descriptor is developed to extract the …

The two-stream convolutional neural network exhibits excellent performance in the video
action recognition. The crux of the matter is to use the frames already clipped by the videos …

Appearance and depth-based action recognition has been researched exclusively for
improving recognition accuracy by considering motion and shape recovery particulars from …

In recent years, human action recognition is modeled as a spatial-temporal video volume.
Such aspects have recently expanded greatly due to their explosively evolving real-world …

Human action recognition (HAR) in videos is a challenging task in computer vision.
Conventional methods are prone to explore the spatiotemporal or optical representations for …