Higher dimensional data such as video and 3D are the leading edge of multimedia retrieval
and computer vision research. In this survey, we give a comprehensive overview and key …

Human action recognition targets recognising different actions from a sequence of
observations and different environmental conditions. A wide different applications is …

Derived from rapid advances in computer vision and machine learning, video analysis tasks
have been moving from inferring the present state to predicting the future state. Vision-based …

This paper introduces a video representation based on dense trajectories and motion
boundary descriptors. Trajectories capture the local motion information of the video. A dense …

Visual features are of vital importance for human action understanding in videos. This paper
presents a new video representation, called trajectory-pooled deep-convolutional descriptor …

Vision-based human action recognition is the process of labeling image sequences with
action labels. Robust solutions to this problem have applications in domains such as visual …

In this paper, we propose an effective method to recognize human actions from sequences
of depth maps, which provide additional body shape and motion information for action …

In this paper, we propose an effective method to recognize human actions from 3D positions
of body joints. With the release of RGBD sensors and associated SDK, human body joints …

This paper introduces a state-of-the-art video representation and applies it to efficient action
recognition and detection. We first propose to improve the popular dense trajectory features …

Most state-of-the-art action feature extractors involve differential operators, which act as
highpass filters and tend to attenuate low frequency action information. This attenuation …