HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences

By Omar Oreifej, Zicheng Liu. 2013

976 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

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

In Human-Computer Interaction

1. Jun Liu
2. Wanqing Li
3. Pichao Wang
4. Hossein Rahmani
5. G. Wang
6. Amir Shahroudy
7. Liliana Lo Presti
8. Marco La Cascia

Citations in the corpus

• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, background): “3D Action Pairs [25] was proposed to provide multiple pairs of action classes.”
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Oreifej and Liu [18] proposed to calculate the four-dimensional normals (X-Y-depth-time) from depth sequences, and accumulate them on spatio-temporal cubes as quantized histograms over 120 vertices of a regular polychoron.”
• Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “For depth sequences, we use the histograms of oriented 4D normals (HON4D) features [41].”
• RGB-D-based action recognition datasets: A survey (2016, neutral): “MSRActionPair MSRActionPair dataset [21] (http://www.”
• 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 [”
• Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “Another solution is HON4D (histogram of oriented 4D normals) [3], which gives more descriptive and robust models of the local depth based appearance and motion, around the joints.”
• 3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “Oreifej and Liu [20] proposed to capture spatio-temporal changes of activities by using a histogram of oriented 4D surface normals (HON4D).”
• 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): “Recently, Oreifej and Liu [19] extended histogram of oriented 3D normals [27] to 4D by adding time derivative.”
• When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “In spite of that, we can nevertheless see that all hand-crafted approaches [42, 28, 41, 6, 35] are greatly outperformed in performance, but also scoring on par with respect to alternative deep architectures (e.”
• Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, background): “Action recognition from depth sequences [57, 34, 29, 44, 49] has attracted significant interest recently due to the emergence of low-cost depth sensors.”
• PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, neutral): “MSR-Action3D [17] 20 567 567 1 D+Skeleton No 2010 RGBD-HuDaAct [21] 13 1189 1189 1 RGB+D No 2011 MSR-DailyActivity [43] 16 320 320 1 RGB+D+Skeleton No 2012 Act4 [8] 14 6844 6844 1 RGB+D No 2012 UTKinect-Action [53] 10 200 200 1 RGB+D+Skeleton No 2012 3D Action Pairs [23] 12 360 360 1 RGB+D+Skeleton ”
• 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): “Dynamic Temporal Warping [16] 54.0 Actionlet Ensemble [35] 85.8 HON4D [18] 85 3D Trajectories [9] 72 Our method (Unsupervised training) 86.9 Table 3.”
• A novel hierarchical framework for human action recognition (2016, methodology): “In previous works, it was used in two ways, either as one dataset containing all actions [7, 9–11, 14, 19–21] or by division into three subsets [6, 8, 12, 13, 15–19”
• Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, methodology): “Since the first work of such a type [9] reported in 2010, many methods [17; 12; 23; 10] have been proposed based on specific hand-crafted feature descriptors extracted from depth.”
• 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).”
• Recognizing Human Actions as the Evolution of Pose Estimation Maps (2018, methodology): “, CNN [17, 20], RNN [9] and LSTM [26, 25], have achieved high performances on the extracted 3D poses, which outperform methods [32, 50] that rely on raw depth video sequences.”