Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition

Subfields: Computer Vision and Pattern Recognition

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “time dimension [121], [129], [190], [202], [208].”
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “3% Oriented Displacements [96] Geometric 91.”
• Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, background): “The elaborately designed features [26, 47, 34] are typically extracted from spatio-temporal interest points to describe the local appearance in 3D volumes or the area around human joints [16].”
• 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”
• Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “[190] utilized Histogram of Oriented Displacements (HOD) projected by three views to describe 3D joint trajectories, which is scaleinvariant and speed-invariant.”
• Action recognition on motion capture data using a dynemes and forward differences representation (2014, background): “in [23] proposed histograms of oriented displacements (HOD) for action recognition.”
• Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, background): “This work was supported by the National Natural Science Foundation of China (grant 61571325) and Key Projects in the Tianjin Science & Technology Pillar Program (grant 15ZCZD GX001900).”
• Bio-inspired predictive orientation decomposition of skeleton trajectories for real-time human activity prediction (2015, methodology): “Other skeleton based 3D human representations were also implemented based on histograms of oriented displacements [12], covariance of 3D joints [13], etc.”
• Real-Time Multi-scale Action Detection from 3D Skeleton Data (2015, background): “The steps of descriptor construction are illustrated in Figure 1.”
• A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, unknown): “Ensemble Weighted Multi-Instance Learning, Chen et al. [37] 2014 - - - 92? - Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition, Gowayyed et al. [38] 2013 92.39 90.18 91.43 91.26 - DMM-Pyramid Based Deep Architectures for Action Recognition with”
• Hierarchical recurrent neural network for skeleton based action recognition (2015, methodology): “[6], We can see that our proposed HBRNN-L achieves the best average accuracy and outperforms the four methods in [3, 6, 18, 31] with hand-crafted features, and the performances of two derived models HURNN-L and DBRNN-L are promising.”