Semantic Embedding Space for Zero-Shot Action Recognition [PDF]
, 2015 The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category.
Gong, Shaogang +2 more
core +1 more source
A Comprehensive Survey of RGB-Based and Skeleton-Based Human Action Recognition
IEEE Access, 2023 With the advancement of computer vision, human action recognition (HAR) has shown its broad research worth and application prospects in a wide range of fields such as intelligent security, automatic driving and human-machine interaction.
Cai-ling Wang, Jingjing Yan
semanticscholar +1 more source
P-CNN: Pose-based CNN Features for Action Recognition [PDF]
, 2015 This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose.
Chéron, Guilhem +2 more
core +5 more sources
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks [PDF]
, 2016 Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem.
Du Y. +6 more
core +3 more sources
Human action recognition using trajectory-based representation
Egyptian Informatics Journal, 2015 Recognizing human actions in video sequences has been a challenging problem in the last few years due to its real-world applications. A lot of action representation approaches have been proposed to improve the action recognition performance.
Haiam A. Abdul-Azim, Elsayed E. Hemayed
doaj +1 more source
Semi-Supervised Adaptation for Skeletal-Data-Based Human Action Recognition
Engineering Proceedings, 2023 Recent research on human action recognition is largely facilitated by skeletal data, a compact representation composed of key joints of the human body.
Haitao Tian, Pierre Payeur
doaj +1 more source
Robust recognition and segmentation of human actions using HMMs with missing observations [PDF]
, 2005 This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation.
Bui, Hung H. +3 more
core +3 more sources
Continuous Human Action Recognition for Human-machine Interaction: A Review [PDF]
ACM Computing Surveys, 2022 With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams.
Harshala Gammulle +5 more
semanticscholar +1 more source
Unsafe action recognition in underground coal mine based on cross-attention mechanism
Gong-kuang zidonghua, 2022 The real-time video monitoring and alarming of unsafe actions of coal mine personnel is an important means to improve the level of safety in production. The coal mine underground environment is complex, and the monitoring video quality is poor.
RAO Tianrong, PAN Tao, XU Huijun
doaj +1 more source
Histogram of Oriented Principal Components for Cross-View Action Recognition [PDF]
, 2015 Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown
Huynh, Du +3 more
core +1 more source