ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring

By Pichao Wang, Wanqing Li, Zhimin Gao, Chang-Fu Tang, Jing Zhang, Philip O. Ogunbona. 2015

103 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism

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 Endocrinology, Diabetes and Metabolism

Citations in the corpus

RGB-D-based action recognition datasets: A survey (2016, neutral): “of-the-art Methods Acc.(%) Data Protocol 4Authorswillmaintainawebsitetokeepupdatingthestate-of-the-artresults 24 MSR-Action3D [8] 1. TriViews +PFA [60] 2. Decision-Level Fusion (SUM) [61] 3. ConvNets [62, 63] 1. 98.2 2. 98.2 3. 100 1. D, S 2. D, S 3. D 1. CS (Half training, half test) 2. CS (2,3,5,7”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “[149, 150] proposed a method called Weighted Hierarchical Depth Motion Maps (WHDMM) + 3ConvNet, for human action recognition from depth maps on small training datasets.”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “The promising performance of existing temporal encoding works [51, 52, 56, 1] provides a source of motivation.”
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition (2018, methodology): “Large Scale Combined (LSC) This dataset combines nine publicly available datasets (Li, Zhang, and Liu 2010; Wang et al. 2015b; 2016b; Xia, Chen, and”
Fusing shape and motion matrices for view invariant action recognition using 3D skeletons (2017, methodology): “What’s more, our method outperforms most of the methods such as SNV [12], DSTIP+DCSF [22], Skeleton Joint Features [21].”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “[39], [40] applied ConvNets to depth action recognition based on the variants of DMM [35], which is sensitive to noise and cannot work well in fine-grained action recognition.”
Joint Distance Maps Based Action Recognition With Convolutional Neural Networks (2017, methodology): “Inspired by the works [21], [23], [24], where the authors used color to encode the temporal information, Hue is adopted in this letter to encode the variations of joint distances.”
Structured Images for RGB-D Action Recognition (2017, methodology): “With the recent development of deep learning, a few methods [35, 36, 8, 38, 45, 24] have been developed based on Convolutional Neural Network (ConvNet) or Recurrent Neural Network (RNN).”
Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (2016, methodology): “The last category is to represent a video in one or multiple compact images and adopt available trained ConvNet architectures for finetuning [14], [15], [16], [23].”
Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks (2018, background): “Recently, deep learning methods have achieved promising results in various computer vision tasks and how to employ deep learning for action recognition has attracted increasing attention [14]–[17].”
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, background): “The last category is to represent a video in one or multiple compact images and adopt available trained ConvNet architectures for ﬁne-tuning [17], [51], [52], [77], [78].”
3D action recognition using data visualization and convolutional neural networks (2017, methodology): “[20] accumulated motions between projected depth maps as depth motion maps (DMM), which served as inputs for ConvNet.”