Interactive body part contrast mining for human interaction recognition

By Yanli Ji, Guo Ye, Hong Cheng. 2014

142 citations recorded by the source corpus.

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

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. Qiuhong Ke
2. Liang Wang
3. Jun Liu
4. Cuiling Lan
5. Wenjun Zeng
6. Mohammed Bennamoun
7. Senjian An
8. Ferdous Sohel

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Qiuhong Ke
4. Dacheng Tao
5. Liang Wang
6. Mohammed Bennamoun
7. Luc Van Gool
8. Ming-Hsuan Yang

In Control and Systems Engineering

1. Hongsong Wang
2. Liang Wang
3. Qiuhong Ke
4. Wenjun Zeng
5. Mohammed Bennamoun
6. Junliang Xing
7. Michael S. Ryoo
8. Senjian An

Citations in the corpus

• Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “Similarly, actions involving two people can be characterized by the interactions of a subset of the two persons’ joints (Yun et al. 2012; Ji, Ye, and Cheng 2014).”
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “[88] Geometric 86.”
• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Method Accuracy Joint Feature [53] 80.3 Joint Feature [22] 86.9 HBRNN [7] 80.4 Deep LSTM [55] 86.0 Co-occurrence LSTM [55] 90.4 Trust Gate ST-LSTM [30] 93.3 Two-stream RNN 94.8 Table 5.”
• View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, methodology): “Raw skeleton [46] 49.7 Joint feature [46] 80.3 Raw skeleton [17] 79.4 Joint feature [17] 86.9 HBRNN-L [5] 80.4 Co-occurrence RNN [51] 90.4 STA-LSTM [35] 91.5 ST-LSTM (Tree Traversal) + Trust Gate [24] 93.3 VA-LSTM 97.2 Table 3: Comparisons on the SYSU dataset in accuracy (%).”
• A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “For all datasets, the clips are generated with all frames of the original skeleton sequence without any pre-processing such as normalization, temporal down-sampling or noise fil-tering.”
• Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, neutral): “[59] 80.3% Ji et al., [63] 86.9% CHARM [64] 83.9% HBRNN [30] (reported by [51]) 80.4% Co-occurrence LSTM [51] 90.4% Deep LSTM (reported by [51]) 86.0% ST-LSTM (Joint Chain) 84.7% ST-LSTM (Tree) 88.6% ST-LSTM (Tree) + Trust Gate 93.3% Table 3.”
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (2016, background): “A number of approaches have proposed using key frames as a representation for action recognition.”
• Multitype Activity Recognition in Robot-Centric Scenarios (2015, methodology): “We compute the RHI descriptor on each set of F frames in every video, therefore, if the video is composed of T frames, we extract (T −F) RHI descriptors, which constitute positive examples for the classifiers.”
• View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, unknown): “3 Raw skeleton [16] 79.”
• Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, unknown): “[19] 86.”
• Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks (2018, unknown): “[45], Li et al.”
• Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation (2018, unknown): “Raw skeleton [ Ji et al. , 2014 ] 79.4 Joint feature [ Ji et al. , 2014 ] 86.9 ST-LSTM [ Liu et al. , 2016 ] 88.6 Co-occurrence RNN [ Zhu et al. , 2016 ] 90.4 STA-LSTM [ Song et al. , 2017 ] 91.5 ST-LSTM+Trust Gate [ Liu et al. , 2016 ] 93.3 VA-LSTM [ Zhang et al. , 2017 ] 97.6 Proposed HCN 98.6…”