Results 211 to 220 of about 342,546 (256)

View invariants for human action recognition

2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003
This paper presents two approaches for the representation and recognition of human action in video, aiming for view-point invariance. The paper first presents new results using a 2D approach presented earlier. Inherent limitations of the 2D approach are discussed and a new 3D approach that builds on recent work on 3D model-based invariants, is ...
Vasu Parameswaran, Rama Chellappa
openaire   +1 more source

Cross-Domain Human Action Recognition

IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012
Conventional human action recognition algorithms cannot work well when the amount of training videos is insufficient. We solve this problem by proposing a transfer topic model (TTM), which utilizes information extracted from videos in the auxiliary domain to assist recognition tasks in the target domain. The TTM is well characterized by two aspects: 1)
Wei Bian 0003, Dacheng Tao, Yong Rui
openaire   +2 more sources

Human activity recognition with action primitives

2007 IEEE Conference on Advanced Video and Signal Based Surveillance, 2007
This paper considers the link between tracking algorithms and high-level human behavioural analysis, introducing the action primitives model that recovers symbolic labels from tracked limb configurations. The model consists of similar short-term actions, action primitives clusters, formed automatically and then labelled by supervised learning.
Zsolt L. Husz, Andrew M. Wallace, Patrick R. Green   +2 more
openaire   +1 more source

Transfer Learning for Human Action Recognition

2011 24th SIBGRAPI Conference on Graphics, Patterns and Images, 2011
To manually collect action samples from realistic videos is a time-consuming and error-prone task. This is a serious bottleneck to research related to video understanding, since the large intra-class variations of such videos demand training sets large enough to properly encompass those variations.
Ana Paula Brandão Lopes, Elerson Rubens da Silva Santos, Eduardo Valle, Jussara M. Almeida, Arnaldo de Albuquerque Araújo   +4 more
openaire   +1 more source

Feature covariance for human action recognition

2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), 2016
In this paper, we present a novel method for human action recognition using covariance features. Computationally efficient action features are extracted from the skeleton of the subject performing the action. They aim to capture relative positions of the joints and motion over time.
Alexandre Perez, Hedi Tabia, David Declercq, Alain Zanotti   +3 more
openaire   +1 more source

Oriented gradients for human action recognition

Proceedings of the Second International Conference on Internet Multimedia Computing and Service, 2010
In this study, we present a simple and effective approach to human action recognition in real time video. We use oriented gradients to represent human contour and recognize human action. First, we detect the human area and obtain human contour information.
Yuan Shen 0004, Zhenjiang Miao
openaire   +1 more source

3D CNN for Human Action Recognition

2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), 2021
Recognizing different human actions from still images or videos is an important research area in the computer vision and artificial intelligence domains. It represents a key step for a wide range of applications including: human-computer interaction, ambient assisted living, intelligent driving and video surveillance.
Sameh Neili Boualia, Najoua Essoukri Ben Amara   +1 more
openaire   +1 more source

A discriminative representation for human action recognition

Pattern Recognition, 2016
Action recognition has been standing as an active research topic over the past years. Many efforts have been made and many methods have been proposed. However, there are still some challenges such as illumination condition, viewpoint, camera motion and cluttered background.
Yuan, Yuan, Zheng, Xiangtao, Lu, Xiaoqiang, Lu, Xiaoqiang (luxiaoqiang@opt.ac.cn)   +3 more
openaire   +2 more sources

Human action recognition

2021
Aquest projecte se centra en el procés de reconeixement i classificació de les accions que realitza una persona en un moment concret, també conegut com Human Activity Recognition. Per a realitzar el reconeixement d'activitat i pose s'ha fet ús d'un algorisme de pose estimation, el qual proporciona l'esquelet de la persona i és d'ajuda per a classificar
Picazos Carrillo, Jose Antonio, Universitat Autònoma de Barcelona. Escola d'Enginyeria   +1 more
openaire   +1 more source

Chaotic Invariants for Human Action Recognition

2007 IEEE 11th International Conference on Computer Vision, 2007
The paper introduces an action recognition framework that uses concepts from the theory of chaotic systems to model and analyze nonlinear dynamics of human actions. Trajectories of reference joints are used as the representation of the non-linear dynamical system that is generating the action.
Ali, Saad, Basharat, Arslan, Shah, Mubarak   +2 more
openaire   +2 more sources