Elastic functional coding of human actions: From vector-fields to latent variables

By Rushil Anirudh, Pavan K. Turaga, Jingyong Su, Anuj Srivastava. 2015

96 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[144] introduced the transport square-root velocity function (TSRVF) to encode humans in 3D space, which provides an elastic metric to”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, neutral): “0%) to Elastic functional coding [68] (94.”
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold (2016, unknown): “18 - - - elastic[1] 85.”
Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks (2018, unknown): “22% − − Elastic functional coding [50] − − − 94.”
A Review of Human Activity Recognition Methods (2015, unknown): “Following a similar approach, Anirudh et al. (2015) represented skeletal joints as points on the product space.”
A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, methodology): “However, all the algorithms that overcome the proposed one exhibit greater complexity because they consider Lie group representations [33, 34], or several machine learning algorithms, such as SVM combined to HMM, to recognize activities composed of atomic actions [28].”
Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks (2017, unknown): “73 Elastic functional coding [3] 94.”
Coding Kendall's Shape Trajectories for 3D Action Recognition (2018, methodology): “In MSR-Action 3D, our approach performs better than the method of [1] using the first protocol.”
Principal component analysis for functional data on Riemannian manifolds and spheres (2017, methodology): “Specifically, in the engineering literature, dimension reduction for Riemannian manifold-valued motion data has been considered (Rahman et al. 2005; Tournier et al. 2009; Anirudh et al. 2015), where for example in the latter paper the time axis is discretized, followed by multivariate dimension redu”
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data (2016, methodology): “Instead of mapping to the Lie algebra, [1] obtained a lowerdimensional representation for curves in SE3 × .”
Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, background): “Various feature extractors and classifier learning methods for 3D action recognition have been proposed in the past few years [28, 37, 31, 65, 54, 26, 34, 5, 47, 59, 38, 56, 32, 2].”