Super Normal Vector for Activity Recognition Using Depth Sequences

By Xiaodong Yang, Yingli Tian. 2014

396 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

1. Jun Liu
2. Hossein Rahmani
3. Wanqing Li
4. Pichao Wang
5. G. Wang
6. Amir Shahroudy
7. Qiuhong Ke
8. Philip O. Ogunbona

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Hossein Rahmani
4. Wanqing Li
5. Pichao Wang
6. Amir Shahroudy
7. Qiuhong Ke
8. Luc Van Gool

Citations in the corpus

• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, background): “Among them, HOG 2 [24], Super Normal Vector [44], and HON4D [25] extract features directly from depth maps without using the skeletal information.”
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Yang and Tian [50] proposed supernormal vectors as aggregated dictionary-based codewords of four-dimensional normals over space-time grids.”
• Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, neutral): “33% SVN [84] 98.”
• Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “Keywords: Spatio-temporal keypoint, pointcloud, view invariance.”
• Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, background): “hand, high-level representations [56] aim to globally model the postures and capture the temporal evolution of actions.”
• Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “These methods either extracted features from one modality: depth [49, 60, 29, 59, 24, 51, 52] or RGB [27, 33] or skeleton [43, 55, 56, 4, 34, 19], or fuse the features extracted separately from them at a later stage [28, 16, 10, 58].”
• Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017, methodology): “We split the 40 subjects into training and testing groups Methods Depth HOG [17] 32.24 Super Normal Vector [42] 31.82 HON4D [18] 30.56 Lie Group [32] 50.08 Skeletal Quads [3] 38.62 FTP Dynamic Skeletons [4] 60.23 HBRNN-L [2] 59.07 2 Layer P-LSTM [25] 62.93 Shuffle and Learn [15] 47.5 Our method…”
• ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring (2015, methodology): “[13] X. Yang and Y. Tian.”
• Human Action Recognition and Prediction: A Survey (2018, methodology): “Kinect [34]) which provide an additional depth channel data [35], [36], [37].”
• Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks (2016, methodology): “We compare our approach to state-of-theart methods: HOG+HOG2 [27], improved dense trajectories (iDT) [39], super normal vector (SNV) [42], two-stream CNNs [34], and convolutional 3D (C3D) [37], as well as human labeling accuracy.”
• Deep Bilinear Learning for RGB-D Action Recognition (2018, methodology): “The geometric information depicted in depth sequences can be used to characterize action [24, 36, 42, 26, 18].”
• A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, methodology): “The proposed algorithm is evaluated using three different sets of joints, from 𝑃 = 7 to 𝑃 = 15 , and the sequence of clusters 𝐾 = [3, 5, 10, 15, 20, 25, 30, 35] , as in the KARD dataset.”
• Learning features combination for human action recognition from skeleton sequences (2017, methodology): “Some methods use solely depth maps for action recognition [9, 11, 14, 16, 28].”