Motion Learning Based on Bayesian Program Learning
The concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2017-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://doi.org/10.1051/itmconf/20171205011 |
| _version_ | 1819158032077029376 |
|---|---|
| author | Cheng Meng-Zhen Tang Quan-Hua Huang Long-Jun |
| author_facet | Cheng Meng-Zhen Tang Quan-Hua Huang Long-Jun |
| author_sort | Cheng Meng-Zhen |
| collection | DOAJ |
| description | The concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposing and combining. And the generated motion will be more realistic and natural than the traditional one.In this paper, Motion learning based on Bayesian program learning allows us to quickly generate new motion data, reduce workload, improve work efficiency, reduce the cost of motion capture, and improve the reusability of data. |
| first_indexed | 2024-12-22T16:18:12Z |
| format | Article |
| id | doaj.art-385af3efd81d492d9bba117a8502dc26 |
| institution | Directory Open Access Journal |
| issn | 2271-2097 |
| language | English |
| last_indexed | 2024-12-22T16:18:12Z |
| publishDate | 2017-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj.art-385af3efd81d492d9bba117a8502dc262022-12-21T18:20:19ZengEDP SciencesITM Web of Conferences2271-20972017-01-01120501110.1051/itmconf/20171205011itmconf_ita2017_05011Motion Learning Based on Bayesian Program LearningCheng Meng-ZhenTang Quan-HuaHuang Long-JunThe concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposing and combining. And the generated motion will be more realistic and natural than the traditional one.In this paper, Motion learning based on Bayesian program learning allows us to quickly generate new motion data, reduce workload, improve work efficiency, reduce the cost of motion capture, and improve the reusability of data.https://doi.org/10.1051/itmconf/20171205011 |
| spellingShingle | Cheng Meng-Zhen Tang Quan-Hua Huang Long-Jun Motion Learning Based on Bayesian Program Learning ITM Web of Conferences |
| title | Motion Learning Based on Bayesian Program Learning |
| title_full | Motion Learning Based on Bayesian Program Learning |
| title_fullStr | Motion Learning Based on Bayesian Program Learning |
| title_full_unstemmed | Motion Learning Based on Bayesian Program Learning |
| title_short | Motion Learning Based on Bayesian Program Learning |
| title_sort | motion learning based on bayesian program learning |
| url | https://doi.org/10.1051/itmconf/20171205011 |
| work_keys_str_mv | AT chengmengzhen motionlearningbasedonbayesianprogramlearning AT tangquanhua motionlearningbasedonbayesianprogramlearning AT huanglongjun motionlearningbasedonbayesianprogramlearning |