Cross-View Action Recognition via a Continuous Virtual Path

By Zhong Zhang, Chunheng Wang, Baihua Xiao, Wen Zhou, Shuang Liu, Cunzhao Shi. 2013

136 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “rely on geometric constraints [15, 16, 17, 18, 19], view invariant features [20, 21, 22, 23, 24, 25, 26], and human body joint tracking [27, 28]. More recent approaches transfer features across views [29, 30, 31, 32, 33, 34, 35, 36]. However, these methods do not perform as good as ﬁxed view action ”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “Transfer learning-bsaed cross-view action recognition methods [3, 11, 25] are based on local appearance features.”
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “0 CVP [64] D 60.”
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, background): “Researchers have paid much attention to this issue and designed view-invariant approaches for action recognition from color videos [16, 30, 3, 32, 20, 7, 33, 41, 23, 15, 22, 43, 44, 25, 49, 29, 8].”
Learning Action Recognition Model from Depth and Skeleton Videos (2017, methodology): “We compare our performance to the state-of-the-art action recognition methods including Comparative Coding Descriptor (CCD) [5], Histogram of Oriented Gradients (HOG(2)) [14], Discriminative Virtual Views (DVV) [11], Continuous Virtual Path (CVP) [41], Histogram of Oriented 4D Normals (HON4D) [15], ”
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, background): “For RGB-based action recognition, researchers have paid much attention to this issue and proposed various view-invariant approaches [3], [8], [9], [13], [14], [18], [22], [24], [29], [34], [35], [37], [38], [48], [50], [51], [58].”
Learning a non-linear knowledge transfer model for cross-view action recognition (2015, background): “Recently, knowledge transfer-based methods [6,7,10,19, 21,40,41] have become popular for cross-view action recog nition.”
Deep Domain Adaptation in Action Space (2018, background): “There are few studies [6, 19, 31] on cross-view action recognition and a few on heterogeneous domain adaptation [8, 9].”
Learning a Deep Model for Human Action Recognition from Novel Viewpoints (2016, methodology): “[22] extended this approach by applying an infinite sequence of linear transformations.”
3D Pose from Motion for Cross-View Action Recognition via Non-linear Circulant Temporal Encoding (2014, unknown): “[34] address this limitation by learning a virtual path between training and test view feature spaces in an unsupervised manner.”
Movement Pattern Histogram for Action Recognition and Retrieval (2014, methodology): “For the action retrieval task, we compare retrieval results against several BOF representations: cuboid [5], self-similarity matrix (SSM) [10], shapeflow [25], dense trajectories [26], and cuboid+shapeflow (used in [17,16,30]).”
3D Action Recognition from Novel Viewpoints (2016, background): “However, most cross-view action recognition methods [17, 27, 39, 40, 60, 72] represent the connection between action videos captured from two different views as a sequence of linear transformations of action descriptors.”