Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks

By Yonghong Hou, Zhaoyang Li, Pichao Wang, Wanqing Li. 2018

326 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

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “Compared with the works reported by [155] and [53], JDM is less sensitive to view variations.”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “The last category represents a video in one or multiple compact images and adopt available trained ConvNet architectures for finetuning [51, 52, 56, 1, 9, 53, 54].”
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, methodology): “ARISON OF THE PROPOSED METHOD WITH THE EXISTING METHODS ON THE MSRC-12 KINECT GESTURE DATASET. Method Accuracy (%) HGM [80] 66.25% Pose-Lexicon [81] 85.86% ELC-KSVD [82] 90.22% Cov3DJ [57] 91.70% SOS [52] 94.27% Proposed Method 94.86% The confusion matrix is shown in Fig. 6. From the confusion matri”
Joint Distance Maps Based Action Recognition With Convolutional Neural Networks (2017, methodology): “Unlike the previous methods [21], [23]–[25] in which 3-D points are created and projected onto three orthogonal planes of the real-world coordinate system centered on the”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, methodology): “With the recent development of deep learning, a few methods have been developed based on Convolutional Neural Networks (ConvNets) [14], [15], [16], [17], [18] and Recurrent Neural Networks (RNNs) [19], [20], [21], [22].”
Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN (2017, methodology): “…II: Performance comparison on the UTD-MHAD dataset [11] Method Accuracy ELC-KSVD [31] 76.19% kinect & Inertial [30] 79.10% Cov3DJ [32] 85.58% SOS [33] 86.97% JTM [21] 87.90% Proposed Method 96.27% MSRC-12 [34] is a relatively large dataset for gesture/action recognition from 3D skeleton data…”
Recognizing Human Actions as the Evolution of Pose Estimation Maps (2018, unknown): “81% Kinect Optical Spectra [15] 2016 86.”
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, methodology): “Cov3DJ [57] 71.95% ELC-KSVD [82] 82.37% LRBM [83] 90.50% SOS [52] 95.45% Proposed Method 96.02% The confusion matrix is shown in ﬁgure 7.”
Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition (2018, background): “The last category is to represent video with one or multiple compact images and adopt available trained ConvNet architectures for fine-tuning [14], [15], [17], [29], [42]–[44].”
Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks (2016, methodology): “recent development of deep learning, a few methods have also been developed based on Convolutional Neural Networks (ConvNets) [10], [11], [12], [13], [14] and Recurrent Neural Networks (RNNs) [15], [16], [17], [18].”