EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor

By Xiaodong Yang, Yingli Tian. 2012

549 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, methodology): “The joint locations p are often normalized, so that the feature is invariant to the absolute body position, initial body orientation and body size [121], [129], [130].”
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, methodology): “For example, Yang and Tian [37] proposed pairwise 3D joint position differences in each frame and temporal differences across frames to represent an action.”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Joint based approaches consider the human skeleton as a set of points and use various positions based features such as joint positions [20, 31] and pairwise relative joint positions [46, 51] to characterize actions.”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “In [33], the pairwise relative positions of the joints are also used to characterize posture features, motion features, and offset features of the skeleton sequences.”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “ed Work 2.1. Feature Extraction from RGBD Data Since the ﬁrst work [32] on 3D action recognition from depth data captured by commodity depth sensors (e.g., Microsoft Kinect TM) in 2010, many methods [76, 65, 78, 22, 13, 42, 71, 6, 77, 1, 57, 41, 67, 68, 72, 28, 33, 20, 11, 79, 74, 37, 40, 46, 85, 8,”
A novel hierarchical framework for human action recognition (2016, methodology): “In [12], the higher order terms (position diﬀerences of diﬀerent joints) were utilized to reduce noise but without considering the time scale.”
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, methodology): “The proposed method has been evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.”
Learning Action Recognition Model from Depth and Skeleton Videos (2017, methodology): “For example, Yang and Tian [38] used pairwise 3D joint position differences in each frame and temporal differences across frames to represent an action.”
Simultaneous Feature and Body-Part Learning for real-time robot awareness of human behaviors (2017, methodology): “However, most existing methods apply only one type of skeletal feature [7], [6], while others simply concatenate several types of skeletal features together into a single bigger vector to encode human actions [8], [9].”
Accurate 3D action recognition using learning on the Grassmann manifold (2015, methodology): “…we conduct several tests on MSR-Action 3D dataset with di ↵ erent dimensions Method accuracy % Histograms of 3D Joints [58] 78.97 Eigen Joints [36] 82.33 DMM-HOG [33] 85.52 HON4D [34] 85.80 Random Occupancy patterns [32] 86.50 Actionlet Ensemble [45] 88.20 HOH4D + D disc [34] 88.89 TSVM on…”
Robust 3D Action Recognition with Random Occupancy Patterns (2012, background): “[15] proposes a dimension-reduced skeleton feature, and [16] developed a histogram of gradient feature over depth motion maps.”
Joint Distance Maps Based Action Recognition With Convolutional Neural Networks (2017, background): “In the past few years, many handcrafted skeleton features [4]–[14] have been proposed for action recognition.”
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera (2013, methodology): “Our algorithm outperforms the algorithms based on 3D silhouette features [13], skeletal joint features [30, 27] and local occupancy patterns[25, 26].”
Accurate and real-time human action recognition based on 3D skeleton (2013, methodology): “Figure 1 The feature extracting framework([1])”