GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction
Human motion prediction involves forecasting future movements based on past observations, which is a complex task due to the inherent spatial-temporal dynamics of human motion. In this paper, we introduced a novel framework, GGTr, which adeptly encapsulates these patterns by integrating positional g...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/15/3305 |
| _version_ | 1797586865685004288 |
|---|---|
| author | Biaozhang Huang Xinde Li |
| author_facet | Biaozhang Huang Xinde Li |
| author_sort | Biaozhang Huang |
| collection | DOAJ |
| description | Human motion prediction involves forecasting future movements based on past observations, which is a complex task due to the inherent spatial-temporal dynamics of human motion. In this paper, we introduced a novel framework, GGTr, which adeptly encapsulates these patterns by integrating positional graph convolutional network (GCN) layers, gated recurrent unit (GRU) network layers, and transformer layers. The proposed model utilizes an enhanced GCN layer equipped with a positional representation to aggregate information from body joints more effectively. To address temporal dependencies, we strategically combined GRU and transformer layers, enabling the model to capture both local and global temporal dependencies across body joints. Through extensive experiments conducted on Human3.6M and CMU-MoCap datasets, we demonstrated the superior performance of our proposed model. Notably, our framework shows significant improvements in predicting long-term movements, outperforming state-of-the-art methods substantially. |
| first_indexed | 2024-03-11T00:28:13Z |
| format | Article |
| id | doaj.art-3a1d3255decb4d28a3b6f53b378e2b2f |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T00:28:13Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3a1d3255decb4d28a3b6f53b378e2b2f2023-11-18T22:49:12ZengMDPI AGElectronics2079-92922023-08-011215330510.3390/electronics12153305GGTr: An Innovative Framework for Accurate and Realistic Human Motion PredictionBiaozhang Huang0Xinde Li1Key Laboratory Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, ChinaKey Laboratory Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, ChinaHuman motion prediction involves forecasting future movements based on past observations, which is a complex task due to the inherent spatial-temporal dynamics of human motion. In this paper, we introduced a novel framework, GGTr, which adeptly encapsulates these patterns by integrating positional graph convolutional network (GCN) layers, gated recurrent unit (GRU) network layers, and transformer layers. The proposed model utilizes an enhanced GCN layer equipped with a positional representation to aggregate information from body joints more effectively. To address temporal dependencies, we strategically combined GRU and transformer layers, enabling the model to capture both local and global temporal dependencies across body joints. Through extensive experiments conducted on Human3.6M and CMU-MoCap datasets, we demonstrated the superior performance of our proposed model. Notably, our framework shows significant improvements in predicting long-term movements, outperforming state-of-the-art methods substantially.https://www.mdpi.com/2079-9292/12/15/3305human motion predictiongraph convolutional networkgated recurrent unittransformers |
| spellingShingle | Biaozhang Huang Xinde Li GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction Electronics human motion prediction graph convolutional network gated recurrent unit transformers |
| title | GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction |
| title_full | GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction |
| title_fullStr | GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction |
| title_full_unstemmed | GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction |
| title_short | GGTr: An Innovative Framework for Accurate and Realistic Human Motion Prediction |
| title_sort | ggtr an innovative framework for accurate and realistic human motion prediction |
| topic | human motion prediction graph convolutional network gated recurrent unit transformers |
| url | https://www.mdpi.com/2079-9292/12/15/3305 |
| work_keys_str_mv | AT biaozhanghuang ggtraninnovativeframeworkforaccurateandrealistichumanmotionprediction AT xindeli ggtraninnovativeframeworkforaccurateandrealistichumanmotionprediction |