Action recognition based on a bag of 3D points

By Wanqing Li, Zhengyou Zhang, Zicheng Liu. 2010

1,474 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose, 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 3D Vision & Pose

In Human-Computer Interaction

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, background): “MSR-Action3D dataset [19] was one of the earliest ones which opened up the research in depth-based action analysis.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “The MSR-Action3D dataset [11] was the earliest which opened up the research in depth-based action analysis.”
RGB-D-based action recognition datasets: A survey (2016, methodology): “Since the ﬁrst work reported in 2010 [8], many benchmark datasets have been created to facilitate the development and evaluation of new action recognition algorithms.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Fusing RGB-D information with skeleton data to build a multisensory representation has the potential to address this problem [107], [126], [191] and improve the descriptive power of the existing space-time human representations.”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “We evaluate our method on three challenging depth based action recognition datasets: MSR-DailyActivity dataset [2], MSR-Action3D dataset [5], and 3D-ActionPairs dataset [3].”
Differential Recurrent Neural Networks for Action Recognition (2015, methodology): “This is in contrast to another evaluation protocol in literature [20] that splits across 20 action classes into three subsets and performs the evaluation within each individual subset.”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “Keywords: Spatio-temporal keypoint, pointcloud, view invariance.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “The proposed algorithms were evaluated on three benchmark datasets including MSRAction3D [13], MSRGesture3D [31], and ActionPairs3D [19].”
Learning human activities and object affordances from RGB-D videos (2012, methodology): “Li et al. (2010) proposed an expandable graphical model, to model the temporal dynamics of actions and use a bag of 3D points to model postures.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “MSR-Action3D MSR-Action3D (Li et al., 2010) (http://www.”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “Namely, we evaluated on MSR-Action3D [20], MSR-Action-Pairs (MSR-pairs) [27], Gaming-3D (G3D) [2], Florence3D [31], UTKinect [40], MSRC-Kinect12 [8], HDM-05 [25] and NTU RGB+D [32].”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “MSR Action3D Dataset [74] is widely used for depthbased action recognition.”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “Take the MSR Action3D dataset [28] as an example, the physical structure of the 20 joints is represented by an undirected graph in Figure 4(a).”
Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “We demonstrate that our approach can achieve higher accuracy on the three public benchmark datasets: MSR Action3D [26], SBU Interaction dataset [59] and Cornell Activity [39].”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “MSR Action3D dataset [17] is one of the earliest datasets for 3D skeleton based activity analysis.”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “Since the first work [20] on 3D action recognition from depth data captured by commodity depth sensors (e.”
Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017, methodology): “The confusion matrix for action recognition on MSRDailyActivity3D dataset [14].”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, methodology): “Besides, we have tested our model on MSR Action3D dataset [69] following the protocol in [30], and achieved an accuracy of 94.8%, which is slightly superior to 94.5% achieved by HBRNN [30].”
A novel hierarchical framework for human action recognition (2016, methodology): “In the second type of experiments, as with [6] all the 567 sequences of the dataset are split into three subsets, each with eight actions.”