Dynamic Manifold Warping for view invariant action recognition
By Dian Gong, Gérard G. Medioni. 2011
92 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Control and Systems Engineering
- Sinisa Todorovic
- Behrooz Mahasseni
- William A. Hoff
- Brian Reily
- Fei Han
- Hao Zhang
- Dimitrios Makris
- Vasileios Argyriou
Citations in the corpus
- Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Gong and Medioni [181] introduced a spatio-temporal manifold and a dynamic manifold warping method, which is an adaptation of dynamic time warping methods for the manifold space.”
- Clustered Spatio-temporal Manifolds for Online Action Recognition (2014, background): “Similarly, Gong and Medioni [11] proposed a directed traversing path on a spatial manifold to incorporate the temporal dimension.”
- (2014). Online quality assessment of human movement from skeleton data . Paper presented at British Machine Vision Conference, (2014, background): “Gerber et al . introduced an extension of Laplacian Eigenmaps to cope with noisy input data [6], but Eigenmap representation depends on the density of the points on the manifold, which may not be suitable for non-uniformly sampled data, such as skeleton data.”
- Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition (2016, methodology): “Action classification using skeleton data has a longtrack record [10, 20, 33, 34, 37, 38, 5].”
- Latent Multitask Learning for View-Invariant Action Recognition (2013, unknown): “Some of these methods are limited by requiring access to mocap data, while others find invariant features for only a subset of views.”
- Action Recognition with Exemplar Based 2.5D Graph Matching (2012, methodology): “Manifold based warping methods are adopted in [13].”
- Structured Time Series Analysis for Human Action Segmentation and Recognition (2014, background): “By doing this, KTC does not only handle nonparametric and high dimensionality problems but also rests on a solid theoretical foundation [8].”