Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks

By Inwoong Lee, Doyoung Kim, Seoungyoon Kang, Sanghoon Lee. 2017

375 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

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. Jun Liu
2. Wanqing Li
3. Pichao Wang
4. Hossein Rahmani
5. Qiuhong Ke
6. Philip O. Ogunbona
7. Zehua Sun
8. Liang Wang

In Biomedical Engineering

1. Wanqing Li
2. Pichao Wang
3. Jun Liu
4. Philip O. Ogunbona
5. Hossein Rahmani
6. Qiuhong Ke
7. Liang Wang
8. Zehua Sun

In Computer Vision and Pattern Recognition

1. Wanqing Li
2. Pichao Wang
3. Jun Liu
4. Philip O. Ogunbona
5. Hossein Rahmani
6. Qiuhong Ke
7. Liang Wang
8. Zehua Sun

Citations in the corpus

• Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “2 Ensemble TS-LSTM [30] - 74.”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “[73] Skeleton Ensemble TS-LSTM Ensemble 74.”
• Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning (2018, methodology): “The most similar work to ours is [16] which proposes an ensemble temporal sliding LSTM (TS-LSTM) networks for skeleton-based action recognition.”
• Skeleton-Based Action Recognition With Shift Graph Convolutional Network (2020, neutral): “5 Ensemble TS-LSTM [8] 89.”
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (2019, methodology): “Recent methods can be grouped into two categories: joint-based [39, 41, 13, 30, 14] and part-based methods [22, 30, 5].”
• InfoGCN: Representation Learning for Human Skeleton-based Action Recognition (2022, neutral): “Lie Group [52] 74.2 Actionlet ensemble [54] 76.0 HBRNN-L [11] 78.5 Ensemble TS-LSTM [24] 89.2 AGC-LSTM [45] 93.3 Shift-GCN [9] 94.6 DC-GCN+ADG [8] 95.3 CTR-GCN [6] 96.5 Ours 97.0 Table 1.”
• A Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges (2020, methodology): “An Ensemble Learning model can be developed by combining different generative and discriminative DL techniques [181].”
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (2019, neutral): “chieves good accuracy, but the Table 6: Performance comparisons on the N-UCLA dataset in terms of accuracy (%). Method Year Acc. HBRNN-L [6] 2015 78.5 Visualization CNN[25] 2017 86.1 Ensemble TS-LSTM [18] 2017 89.2 EleAtt-GRU [53] 2018 90.7 SGN w/o Sem. - 91.2 SGN - 92.5 Table 7: Comparison with oth”
• Human Action Recognition From Various Data Modalities: A Review (2020, background): “[166] proposed an ensemble Temporal Sliding LSTM (TS-LSTM) framework composed of multiple parts, containing shortterm, medium-term, and long-term TS-LSTM networks.”