The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection

By Mihai Zanfir, Marius Leordeanu, Cristian Sminchisescu. 2013

463 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[180], [181], [183], [198], [209], [210].”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “Finally, we propose a global descriptor that is extracted from the normalized spatio-temporal distribution of STKs in 4-D. STK-Distribution and local HOPC descriptors were evaluated for cross-view human action recognition on the Northwestern-UCLA and UWA3D Multiview Activity II datasets.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, background): “a Moving Pose [40] used different setting.”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “Also, rather than using one ﬁxed scale [24] or multi-scale multi-round scans [70, 71], we propose a novel SS-Net for online prediction, which is supervised to choose the proper window for prediction at each time step.”
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “augmenting coordinates with velocities and acceleration [62].”
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition (2017, neutral): “augmenting coordinates with velocities and acceleration [46].”
Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, background): “Many of these methods either focus on modeling spatio-temporal structure with a certain assumption [34], or exploit the trajectories of human joints [42, 60] in the testing stage which rely on accurate skeleton joints detection.”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, methodology): “However, in many new works, recognizing the actions on the fly before the completion of the action is well studied by a learning formulation based on a structural SVM [13], or a non-parametric moving pose framework [55] and a dynamic integral bag-of-words approach [28].”
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, background): “Although online detection is of great importance, there are very few works specially designed for it [5,6].”
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets (2016, background): “Their approach has been applied to action recognition in still images [19], as well as in videos [26, 33, 41].”
Learning Action Recognition Model from Depth and Skeleton Videos (2017, background): “The depth sensor based human action recognition research can be broadly divided into three categories including skeleton data [6,12,25,33,34,38,40], depth images [15, 17,18,20,21,23,37,39] and depth skeleton [19,26,27,36] based methods.”
Learning hierarchical spatio-temporal pattern for human activity prediction (2016, result): “Method Same-environment Cross-environment Moving Pose [36] 38.”
Bio-inspired predictive orientation decomposition of skeleton trajectories for real-time human activity prediction (2015, methodology): “A moving pose descriptor was introduced in [10], which uses joint positions in a set of key frames and encodes kinematic information as differential 3D quantities.”
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, background): “In [31] a skeleton sequence is modeled as a continuous and differentiable function of the body joint locations over time.”
Bilinear heterogeneous information machine for RGB-D action recognition (2015, methodology): “BHIM is first compared with existing approaches [26, 11, 27, 13, 21, 25] on this dataset, and then evaluated given RGB, depth, and RGB-D data, respectively.”