Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion

By Feng Zhou, Fernando De la Torre, Jessica K. Hodgins. 2013

375 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, 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 Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Cordelia Schmid
4. Li Fei-Fei
5. Xiaogang Wang
6. Andrea Vedaldi
7. Alan L. Yuille
8. Dacheng Tao

In Control and Systems Engineering

1. René Vidal
2. Angela Yao
3. Silvio Savarese
4. Ferda Ofli
5. Ruzena Bajcsy
6. Siwei Lyu
7. Dian Gong
8. Tian Lan

In Signal Processing

1. Angela Yao
2. Fadime Sener
3. René Vidal
4. Silvio Savarese
5. Siwei Lyu
6. Dian Gong
7. Tian Lan
8. Michael Auli

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, neutral): “[159] 4D quaternions BoW Lowlv Dict X X X X”
• A Hierarchical Representation for Future Action Prediction (2014, methodology): “Once we have the similarity matrix, we cluster the frames of the person using a recently proposed temporal clustering algorithm [4].”
• Sequence of the Most Informative Joints (SMIJ): A new representation for human skeletal action recognition (2012, background): “007 the principle component analysis and data compression theory [20–22].”
• Structured Time Series Analysis for Human Action Segmentation and Recognition (2014, methodology): “Results show that this change reduces accuracy significantly, which supports the effectiveness of DMW not only in temporal alignment (Fig.”
• QuaterNet: A Quaternion-based Recurrent Model for Human Motion (2018, methodology): “Previous work in motion modeling has used quaternions for pose clustering [63], for joint limit estimation [20], and for motion retargeting [57].”
• Combined shape analysis of human poses and motion units for action segmentation and recognition (2015, positive): “Figure 6 shows the segmentation results of the fourth sequence obtained by HACA [19] (second row) and our method (third row), in comparison with ground truth segmentation (first row).”
• Manifold Warp Segmentation of Human Action (2018, background): “Moreover, they provide an unsupervised hierarchical bottom-up framework to find a low-dimensional embedding for the time series, which is effective for segmenting complex motions [12].”
• Unsupervised Learning and Segmentation of Complex Activities from Video (2018, background): “In the bigger scope of temporal sequences, several previous works have also addressed unsupervised segmentation [6, 11, 33].”
• Modeling transition patterns between events for temporal human action segmentation and classification (2015, methodology): “1) Training Segment-SVM with Max Margin Optimization: We learn discriminative patterns of each peak and transition segments using a multi-class SVM [6] similar to [9].”