Results 21 to 30 of about 8,410,900 (380)
Rank-GCN for Robust Action Recognition
IEEE Access, 2022 We present a robust skeleton-based action recognition method with graph convolutional network (GCN) that uses the new adjacency matrix, called Rank-GCN. In Rank-GCN, the biggest change from previous approaches is how the adjacency matrix is generated to ...
Haetsal Lee +3 more
doaj +1 more source
Learning Discriminative Representations for Skeleton Based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2023 Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton representations
Huanyu Zhou, Qingjie Liu, Yunhong Wang
semanticscholar +1 more source
Convolutional Two-Stream Network Fusion for Video Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2016 Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information.
Christoph Feichtenhofer +2 more
semanticscholar +1 more source
Towards Understanding Action Recognition [PDF]
2013 IEEE International Conference on Computer Vision, 2013 -
H Jhuang +4 more
openaire +5 more sources
Hybrid Relation Guided Set Matching for Few-shot Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2022 Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies.
Xiang Wang +7 more
semanticscholar +1 more source
Darwintrees for Action Recognition [PDF]
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017 We propose a novel mid-level representation for action/activity recognition on RGB videos. We model the evolution of improved dense trajectory features not only for the entire video sequence, but also on subparts of the video. Subparts are obtained using a spectral divisive clustering that yields an unordered binary tree decomposing the entire cloud of
Clapes, Albert +2 more
openaire +3 more sources
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2023 The self-supervised pretraining paradigm has achieved great success in skeleton-based action recognition. However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts, which has a negative impact on ...
Lilang Lin, Jiahang Zhang, Jiaying Liu
semanticscholar +1 more source
View-Invariant Action Recognition [PDF]
, 2020 Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal appearance generated by human action is key for identifying the performed action.
Rawat, Yogesh S, Vyas, Shruti
openaire +2 more sources
Viewpoint Manifolds for Action Recognition
EURASIP Journal on Image and Video Processing, 2009 Action recognition from video is a problem that has many important applications to human motion analysis. In real-world settings, the viewpoint of the camera cannot always be fixed relative to the subject, so view-invariant action recognition methods are
Richard Souvenir, Kyle Parrigan
doaj +2 more sources
Progressive Teacher-student Learning for Early Action Prediction [PDF]
, 2020 The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition.
Hu, Jian-Fang +4 more
core +2 more sources