G3D: A gaming action dataset and real time action recognition evaluation framework

By Victoria Bloom, Dimitrios Makris, Vasileios Argyriou. 2012

237 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Wanqing Li
4. Pichao Wang
5. Alex ChiChung Kot
6. Amir Shahroudy
7. Luc Van Gool
8. Ling-yu Duan

In Control and Systems Engineering

1. Wanqing Li
2. Jun Liu
3. Pichao Wang
4. Yonghong Hou
5. Siqi Nie
6. Qiang Ji
7. Vittorio Murino
8. Pietro Morerio

In Evaluation & Benchmarks

1. Jun Liu
2. Wanqing Li
3. Pichao Wang
4. Alex ChiChung Kot
5. Ling-yu Duan
6. G. Wang
7. Liang Wang
8. Amir Shahroudy

Citations in the corpus

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “The G3D [45] and PKUMMD [46] datasets were introduced for activity analysis in continuous sequences, which respectively contain 210 and 1076 videos.”
• RGB-D-based action recognition datasets: A survey (2016, neutral): “Gaming 3D dataset (G3D) [16, 17]( http://dipersec.king.ac.uk/G3D/ ) captured by Kingston University in 2012 focuses on real-time action recognition in gaming scenario.”
• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other datasets captured using a Kinect v1 camera were also released to the public, including the MSR Daily Activity 3D [121], MSR Action Pairs [113], Online RGBD Action (ORGBD) [107], UTKinect-Action [124], Florence 3D-Action [118], CMU-MAD [104], UTD-MHAD [103], G3D/G3Di [105], [119], SPHERE [”
• Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “Furthermore, we extensively evaluate the proposed action prediction framework on two more datasets, including the largescale ChaLearn Gesture dataset for body language understanding [73] and the G3D dataset for gaming action analysis [49].”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “G3D Gaming 3D dataset (G3D) [7](http://dipersec.”
• When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, positive): “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].”
• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “[3] use AdaBoost to combine five types of features, i.”
• PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “G3D [3] 20 210 1467 7 RGB+D+Skeleton Yes 2012 SBU Kinect interaction [54] 8 21 300 14.”
• Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, background): “As G3DGaming [5] dataset, 3D locations of 31 joints (i.”
• Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, methodology): “For the G3D dataset, we use the same setting as used in [29].”
• Dynamic Feature Selection for Online Action Recognition (2013, methodology): “We used pose based features extracted from skeleton data: position difference, position velocity, position velocity magnitude, angle velocity and joint angles similar to those used by [4], [17].”
• Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition (2018, methodology): “The proposed representation is evaluated on six benchmark data sets, namely,MSRAction3D, G3D,MSRDailyActivity3D, SYSU 3D HOI, UTD-MHAD, and M2I data sets and achieves the state-of-the-art results on all six data sets.”
• Spatiotemporal representation of 3D skeleton joints-based action recognition using modified spherical harmonics (2016, methodology): “• (AdaBoost ) used in (Bloom et al., 2012), • (HHM) used in (Xia et al., 2012).”
• Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks (2018, methodology): “2) Gaming 3D Dataset: The G3D [20] focuses on real-time action recognition in gaming scenario.”
• SSNet: Scale Selection Network for Online 3D Action Prediction (2018, unknown): “methods [3] which attempted untrimmed sequences.”
• Joint Geometrical and Statistical Alignment for Visual Domain Adaptation (2017, methodology): “There are 8 common actions between MSRAction3DExt and G3D: wave, forward punch, hand clap, forward kick, jogging, tennis swing, tennis serve, and golf swing.”
• Structured Images for RGB-D Action Recognition (2017, methodology): “The proposed method is evaluated on five widely used benchmark RGB-D datasets [41], namely, MSRAction3D [18], G3D [3], MSRDailyActivity3D [34], SYSU 3D HOI [13] and UTD-MHAD [4] datasets.”
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN (2017, background): “Gesture Dataset [11] Method Accuracy HGM [35] 66.25% Pose-Lexicon [36] 85.86% ELC-KSVD [31] 90.22% Cov3DJ [32] 91.70% SOS [33] 94.27% JTM [21] 94.86% Proposed Method 99.41% Gaming 3D Dataset (G3D) [37] focuses on real-time action recognition in a gaming scenario.”
• Real-Time Online Action Detection Forests Using Spatio-Temporal Contexts (2016, methodology): “The G3D dataset [2] provides action point annotations.”