Human Daily Action Analysis with Multi-view and Color-Depth Data

By Zhongwei Cheng, Lei Qin, Yituo Ye, Qingming Huang, Qi Tian. 2012

136 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, neutral): “MSR-Action3D [19] 567 20 10 1 N/A D+3DJoints 2010 CAD-60 [34] 60 12 4 - Kinect v1 RGB+D+3DJoints 2011 RGBD-HuDaAct [23] 1189 13 30 1 Kinect v1 RGB+D 2011 MSRDailyActivity3D [38] 320 16 10 1 Kinect v1 RGB+D+3DJoints 2012 Act4(2) [6] 6844 14 24 4 Kinect v1 RGB+D 2012 CAD-120 [18] 120 10+10 4 - Kinect ”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, neutral): “Act42 [16] 6,844 14 24 4 Kinect v1 RGB+D 2012”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “Experimental results show that our method is able to achieve significantly better accuracy than current state-of-the-art methods for cross-view action recognition and is robust to action speed variations.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “, [4,21,38]) treat depth sequences the same way as color videos and use color-based action recognition methods.”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “The action categories in ACT4 mainly focus on the activities of daily livings.”
Human Action Recognition From Various Data Modalities: A Review (2020, unknown): “Dataset Year Modality #Class #Subject #Sample #View KTH [347] 2004 RGB 6 25 2,391 1 Weizmann [40] 2005 RGB 10 9 90 1 IXMAS [348] 2006 RGB 11 10 330 5 HDM05 [349] 2007 RGB,S 130 5 2,337 1 Hollywood [350] 2008 RGB 8 - 430 Hollywood2 [351] 2009 RGB 12 - 3,669 MSR-Action3D [217] 2010 S,D 20 10 567 1 Oly”
View-Invariant 3D Action Recognition Using Spatiotemporal Self-Similarities from Depth Camera (2014, methodology): “EXPERIMENTAL RESULTS AND ANALYSIS In this section, we demonstrated our approach on the ACT4(2) dataset [12] and MSRAction3D dataset [19].”
Action recognition using ensemble weighted multi-instance learning (2014, background): “[1] built a comparative coding descriptor to describe the depth cuboid by comparing the depth value of the center point with the nearby 26 points.”
Hollywood 3D: Recognizing Actions in 3D Natural Scenes (2013, background): “In this work, a new natural action dataset is introduced termed Hollywood3D (see figure 1), it builds on the spirit 1 of the existing Hollywood datasets but includes 3D information.”
Multi-view Domain Generalization for Visual Recognition (2015, methodology): “Specifically, we extract the improved dense trajectory features [35] from each RGB and depth video in both ACT42 and ORGBD datasets.”
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera (2013, methodology): “[4] build a Comparative Coding Descriptor(CCD) to describe the 3 × 3 × 3 depth cuboid by comparing the depth value of the center point with the nearby 26 points.”
Learning Action Recognition Model from Depth and Skeleton Videos (2017, methodology): “We compare our performance to the state-of-the-art action recognition methods including Comparative Coding Descriptor (CCD) [5], Histogram of Oriented Gradients (HOG(2)) [14], Discriminative Virtual Views (DVV) [11], Continuous Virtual Path (CVP) [41], Histogram of Oriented 4D Normals (HON4D) [15], ”
RGB-Depth feature for 3D human activity recognition (2013, methodology): “CHENG et al. proposed a new descriptor of depth information, called Comparative Coding Descriptor (CCD) [30], for action representation, which depicted the structural relations of spatiotemporal points within action volume using the distance information in depth data.”
3D Action Recognition from Novel Viewpoints (2016, unknown): “CCD [7] 34.”
Space-Time Pose Representation for 3D Human Action Recognition (2013, methodology): “Several approaches are used for action recognition like 3D silhouettes [3], Comparative Coding Descriptor [5] .”