Results 31 to 40 of about 2,834,648 (359)
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data [PDF]
AAAI Conference on Artificial Intelligence, 2016 Human action recognition is an important task in computer vision. Extracting discriminative spatial and temporal features to model the spatial and temporal evolutions of different actions plays a key role in accomplishing this task.
Sijie Song +4 more
semanticscholar +1 more source
Pairwise Features for Human Action Recognition [PDF]
2010 20th International Conference on Pattern Recognition, 2010 Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geometric relationships among the local features are ignored. This paper presents new features, called pairwise features (PWF), which encode both the appearance and the spatio ...
Ta, Anh Phuong +4 more
openaire +1 more source
Human Skeleton Action Recognition Algorithm Based on Dynamic Topological Graph [PDF]
Jisuanji kexue, 2022 Traditional human skeleton action recognition algorithms manually construct topological graphs to model the action sequence contained in multiple video frames and learn each video frame to reflect the data changes,which may lead to the high computational
XIE Yu, YANG Rui-ling, LIU Gong-xu, LI De-yu, WANG Wen-jian
doaj +1 more source
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data [PDF]
IEEE International Conference on Computer Vision, 2017 Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions.
Pengfei Zhang +5 more
semanticscholar +1 more source
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2019 Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feedforward neural networks to model the 3D coordinates of joints without ...
Pengfei Zhang +4 more
semanticscholar +1 more source
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [PDF]
Computer Vision and Pattern Recognition, 2017 The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-
João Carreira, Andrew Zisserman
semanticscholar +1 more source
Spatiotemporal Saliency for Human Action Recognition [PDF]
2005 IEEE International Conference on Multimedia and Expo, 2005 This paper addresses the problem of human action recognition by introducing a sparse representation of image sequences as a collection of spatiotemporal events that are localized at points that are salient both in space and time. We detect the spatiotemporal salient points by measuring changes in the information content of pixel neighborhoods not only ...
Antonios Oikonomopoulos +2 more
openaire +2 more sources
Research on Human Motion Recognition Based on Data Redundancy Technology
Complexity, 2021 Aiming at the problems of low recognition rate and slow recognition speed of traditional body action recognition methods, a human action recognition method based on data deduplication technology is proposed.
Hong-Lan Yang +2 more
doaj +1 more source
Interior Human Action Recognition Method Based on Prior Knowledge of Scene [PDF]
Jisuanji kexue, 2022 Currently,the recognition technology targeted at human action in an interior scene is widely used in video content understanding,home-based care,medical care and other fields,and existing researches pay more heed to the modelling of human action,while ...
LIU Xin, YUAN Jia-bin, WANG Tian-xing
doaj +1 more source
A Survey on Human Action Recognition
CoRR, 2022 Human Action Recognition (HAR), one of the most important tasks in computer vision, has developed rapidly in the past decade and has a wide range of applications in health monitoring, intelligent surveillance, virtual reality, human computer interaction and so on.
openaire +2 more sources