Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition

By Di Wu, Ling Shao. 2014

226 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, 3D Vision & Pose

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. Pichao Wang
2. Wanqing Li
3. Philip O. Ogunbona
4. Jun Liu
5. Yonghong Hou
6. Qiuhong Ke
7. Liang Wang
8. Zhimin Gao

In Computer Vision and Pattern Recognition

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

In Control and Systems Engineering

1. Liang Wang
2. Hongsong Wang
3. Basura Fernando
4. Guillermo Garcia-Hernando
5. Silvio Savarese
6. Yong Du
7. Danica Kragic
8. Qiuhong Ke

In 3D Vision & Pose

1. Yingli Tian
2. Jun Liu
3. Pichao Wang
4. Liang Wang
5. Tae-Kyun Kim
6. Chenyang Zhang
7. Yong Du
8. Sinisa Todorovic

Citations in the corpus

• Deep learning in neural networks: An overview (2014, background): “…2001), e.g., Baldi and Chauvin (1996), Bengio (1991), Bishop (2006), Bottou (1991), Bourlard andMorgan (1994), Dahl, Yu, Deng, and Acero (2012), Hastie, Tibshirani, and Friedman (2009), Hinton, Deng, et al. (2012), Jordan and Sejnowski (2001), Poon and Domingos (2011) and Wu and Shao (2014).”
• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “The state-of-the-art classification rate about this dataset is from [100] (72.”
• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “layer deep learning approaches have attracted an increasing attention in recent several years to learn human representations directly from human joint positions [146], [188].”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “Wu and Shao [161] adopted deep belief networks (DBN) to model the distribution of skeleton joint locations and extract high-level features to represent humans at each frame in 3D space.”
• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “, hidden Markov model [47, 49], to recognize actions.”
• A New Representation of Skeleton Sequences for 3D Action Recognition (2017, background): “Most existing works explicitly model the temporal dynamics of skeleton sequences using Hidden Markov Models (HMMs) [31], Conditional Random Fields (CRFs) [26] or Temporal Pyramids (TPs) [28].”
• Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks (2016, background): “16 SUBMITTED TO IEEE TRANSACTIONS ON CYBERNETICS, VOL. X, NO. X, X 2016 (WILL BE INSERTED BY THE EDITOR) 2 Scores Scores Scores Multiply Score Fusion Accuracy Front Top Side Front Channel Top Channel [59], geometric descriptor [33], [34], [39]–[41], [60] or keySide Channel Skeleton Sequences ConvNet”
• Linear-time online action detection from 3D skeletal data using bags of gesturelets (2015, result): “3Before the camera ready version, we found [18] which reports better results on MSRC-12.”
• WALKING WALKing walking: Action Recognition from Action Echoes (2017, methodology): “Popular dynamics-based methods include: Hidden Markov Models (HMMs) [X-ia et al. , 2012; Wu and Shao, 2014], Long-Short Term Memory networks (LSTM) [Du et al. , 2015; Zhu et al. , 2016; Song et al. , 2016].”
• Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks (2016, background): “Joint representation captures the correlation of the body joints by extracting spatial descriptor [30], [56]– [59], geometric descriptor [33], [34], [39]–[41], [60] or key poses [35], [61]–[63].”
• 3D skeleton-based human action classification: A survey (2016, methodology): “In [98], a HMM is used to model an action.”
• Rank Pooling for Action Recognition (2015, unknown): “∗basura.fernando@anu.edu.au †E.Gavves@uva.nl ‡jose.oramas@esat.kuleuven.be §amir.ghodrati@esat.kuleuven.be ¶tinne.tuytelaars@esat.kuleuven.be”
• Deep Representation Learning for Human Motion Prediction and Classification (2017, methodology): “In [24], the prominent use of Hidden Markov Models (HMMs) is combined with multilayer perceptrons to model action-dependent hidden state trajectories.”
• Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, methodology): “Generative models [14, 31, 32] such as Hidden Markov Models (HMM) have been proposed with the disadvantages of being difficult to estimate model parameters and time consuming learning and inference stages.”
• Learning Clip Representations for Skeleton-Based 3D Action Recognition (2018, methodology): “(HMMs) [19], [20], Conditional Random Fields (CRFs) [21] and Temporal Pyramids (TPs) [7], [22] have been used to”