Robust 3D Action Recognition with Random Occupancy Patterns

By Jiang Wang, Zicheng Liu, Jan Chorowski, Zhuoyuan Chen, Ying Wu. 2012

499 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Jun Liu
2. Hossein Rahmani
3. G. Wang
4. Ajmal Saeed Mian
5. Amir Shahroudy
6. Wanqing Li
7. Yun Raymond Fu
8. Pichao Wang

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Hossein Rahmani
4. Luc Van Gool
5. Xiaogang Wang
6. Dacheng Tao
7. Ming-Hsuan Yang
8. Alan L. Yuille

In 3D Vision & Pose

1. Jun Liu
2. Hossein Rahmani
3. G. Wang
4. Tae-Kyun Kim
5. Amir Shahroudy
6. Ajmal Saeed Mian
7. Yingli Tian
8. Liliana Lo Presti

In Human-Computer Interaction

1. Hossein Rahmani
2. Jun Liu
3. Liliana Lo Presti
4. Marco La Cascia
5. Yingli Tian
6. Ajmal Saeed Mian
7. Xiaodong Yang
8. Hao Zhang

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Among a large number of human representation approaches [24], [25], [26], [27], [28], [29], most of the existing 3D based methods can be broadly grouped into two categories: representations based on local features [30], [31] and skeletonbased representations [32] [33] [34].”
• 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): “The proposed algorithms were evaluated on three benchmark datasets including MSRAction3D [13], MSRGesture3D [31], and ActionPairs3D [19].”
• A novel hierarchical framework for human action recognition (2016, methodology): “The widely-used features 23 include sampled 3D points from silhouettes [6, 7], histograms of oriented 24 gradients [8], histogram of oriented 4D normals [9], histogram of oriented 25 principal components [10], etc.”
• Action Classification with Locality-Constrained Linear Coding (2014, methodology): “In the first experiment, we evaluate the proposed method on the depth datasets (MSRGesture3D, MSRAction3D and MSRActionPairs3D).”
• Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition (2013, methodology): “[32] use random occupancy pattern descriptors with sparse coding and report 86.”
• Motion Recognition Employing Multiple Kernel Learning of Fisher Vectors Using Local Skeleton Features (2015, methodology): “Along with this change, various modalities such as skeleton[19][23][7], color, depth[14][22], silhouette[9][2] and space-time occupancy[17][18] are used as features for action recognition.”
• Accurate 3D action recognition using learning on the Grassmann manifold (2015, methodology): “Also in Wang et al. [32], the action sequence is considered as a 4D shape but Random Occupancy Pattern (ROP) is used for features extraction.”
• Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, unknown): “[38] sought to explicitly encode the geometric”
• Action Recognition Using Rate-Invariant Analysis of Skeletal Shape Trajectories (2016, unknown): “78 Random Occupancy Pattern [35] (from [18]) 0.”
• Super Normal Vector for Activity Recognition Using Depth Sequences (2014, methodology): “While still inferior to our method, the approaches in [17, 20, 21] improve the results in [23, 24] because cloud points are more resistant to occlusions and provide additional shape cues compared to skeleton joints.”
• Gesture Modeling by Hanklet-Based Hidden Markov Model (2014, methodology): “Methods [47]* [10]* [11]* [12] [24] [48]** [13]** [25] [23] [13]** Ours”