Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data

By Raviteja Vemulapalli, Ramalingam Chellappa. 2016

207 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

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

In Human-Computer Interaction

Citations in the corpus

When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “Evaluation on Gaming 3D using the protocol of [36].”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “Skeleton-based action recognition has been explored in different aspects in recent years [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57].”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “Those local features includes rotations and translations to represent geometric relationships of body parts in a Lie group [39, 40], or the covariance matrix to learn the co-occurrence of skeleton points [14].”
Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, methodology): “To address the problem as in [42], we design the logarithm map (LogMap) layer to flatten the Lie group SO3 × .”
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, methodology): “TICS, VOL. X, NO. X, X 2016 (WILL BE INSERTED BY THE EDITOR) 2 Scores Scores Scores Multiply Score Fusion Accuracy Front Top Side Front Channel Top Channel [59], geometric descriptor [33], [34], [39]–[41], [60] or keySide Channel Skeleton Sequences ConvNet ConvNet ConvNet Rotation Color Encoding Col”
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations (2017, background): “Popular approaches include the use of temporal state-space models [17, 70, 74, 75, 86], key-poses [66, 85], hand-crafted pose features [64, 65], and temporal recurrent models [12, 63, 87].”
Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN (2017, methodology): “Previously, hand-crafted skeleton features have been de vised to capture the spatial configuration while Dynamic Time Warpings (DTW), Fourier Temporal Pyramid (FTP) or Hidden Markov Models (HMMs) have been employed to model the temporal information [3-7].”
Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks (2018, background): “To date, many skeleton-based action recognition methods [2]–[13] have been reported.”
On Human Motion Prediction Using Recurrent Neural Networks (2017, background): “Although their purpose (action classification from a sequence of poses) is different from ours, this field contains interesting insights for motion prediction, such as the importance of a mathematically sound orientation representation [46,47] or how learned, compact motion representations improve a”
Adaptive RNN Tree for Large-Scale Human Action Recognition (2017, methodology): “[23, 24] modeled the 3D geometric interactions between body parts using transformations, which are represented as elements in a Lie group.”
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, methodology): “Similarly, [26, 27] represents the whole skeletons as points in a Lie group before temporally aligning sequences using Dynamic Time Warping (DTW) and applying FTP.”
A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition (2017, background): “Recently, shape trajectory-based methods showed their effectiveness in many temporal pattern recognition tasks, especially in action recognition [2, 4, 6, 9, 40].”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, unknown): “Since the first work of such a type [2] reported in 2010, many methods [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13] have been proposed based on specifical handcrafted feature descriptors extracted from depth/skeleton.”
Vision-based human activity recognition: a survey (2020, background): “Typically, Fourier Transform [198, 199, 207], Wavelet representations [58, 229] and trajectories of body parts [176, 197] are templates that can be used for action recognition.”
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, background): “Joint representation captures the correlation of the body joints by extracting spatial descriptor [30], [56]– [59], geometric descriptor [33], [34], [39]–[41], [60] or key poses [35], [61]–[63].”
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], ”
Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks (2016, methodology): “, Kinect) in 2010, many methods [2], [3], [4], [5], [6], [7], [8], [9] for action recognition have been proposed based on specific hand-crafted feature descriptors extracted from depth or skeleton data.”
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (2019, background): “[29] represent each skeleton using the relative 3D rotations between various body parts.”
Coding Kendall's Shape Trajectories for 3D Action Recognition (2018, methodology): “Conscious of this limitation, the authors in [36] proposed a mapping of trajectories on Lie groups combining the usual logarithm map with a rolling map that guarantees a better flattening of trajectories on Lie groups.”