Structured Time Series Analysis for Human Action Segmentation and Recognition

By Dian Gong, Gérard G. Medioni, Xuemei Zhao. 2014

106 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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. Tae-Kyun Kim
2. Liang Wang
3. Yun Raymond Fu
4. Fei Han
5. Yong Du
6. Hao Zhang
7. William A. Hoff
8. Brian Reily

In Computer Vision and Pattern Recognition

1. Jun Liu
2. Liang Wang
3. Yun Raymond Fu
4. Tae-Kyun Kim
5. G. Wang
6. Fei Han
7. Hao Zhang
8. William A. Hoff

In Signal Processing

1. Liang Wang
2. Tae-Kyun Kim
3. William A. Hoff
4. Brian Reily
5. Fei Han
6. Zhiyuan Shi
7. Yong Du
8. Hao Zhang

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “[176] directly concatenated 3D joint positions into a 1D vector as a representation at each frame to address the time series segmentation problem.”
• Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “To model sequential state transitions in a principled way, hidden Markov model (HMM) has attracted a lot of interest [14] in capturing the temporal structure of human action dynamics.”
• 3D skeleton-based human action classification: A survey (2016, unknown): “Emerging trends are action recognition “in the wild” [43], [44], [45], [46], [47], [48], and action “localization” [49], [50], [51], [52], [53].”
• Skeleton based action recognition with convolutional neural network (2015, background): “Temporal dynamics of postures over time can be modeled as a time series problem, which is crucial for sequencebased action recognition [4, 8, 9].”
• Accurate 3D action recognition using learning on the Grassmann manifold (2015, background): “Recently, Gong et al. [17] propose a Kernelized Temporal Cut (KTC) as an extension of their previous work [16].”
• WALKING WALKing walking: Action Recognition from Action Echoes (2017, methodology): “In this sense, the skeleton sequences can be regarded as multivariate time series, and recognizing human actions can be seen as a time series classification (TSC) problem [Gong et al. , 2014].”
• Hierarchical recurrent neural network for skeleton based action recognition (2015, background): “[5] perform both temporal segmentation and alignment with structured time series representations.”
• Manifold Warp Segmentation of Human Action (2018, methodology): “[15] proposed a kernel algorithm based on Hilbert space embedding, which can”