- 期刊
- OpenAccess
Extending Association from Human Motion Symbolsby Using Latent Semantics of Digital Book Library
並列摘要
This paper proposes the methods to associate various sentences with motions using stochastic models. The motion document language model, which associates the words with the motions through the latent concepts extracted from motions and documents stochastically. The Ngram language model represents the natural sequence of words. Sentences can be associated with motion symbols using the motion document language model and N-gram language model by rearranging words generated from motion. The sentence association algorithm is parallelized with MPI. Our method of sentence association was tested on captured human motion and a large corpus of digital books, and its validity was demonstrated. And the parallel computation is executed on cloud server of Amazon EC2.
延伸閱讀
- 薛良凱（2005）。Digital Publishing and Digital Library。臺北市立圖書館館訊，22(3)，32-41。https://www.airitilibrary.com/Article/Detail?DocID=10112081-200503-201312180027-201312180027-32-41
- 林信成、蕭勝文（2005）。Application of Fuzzy Classification to the Library System of Selective Dissemination of Information。圖書與資訊學刊，(52)，23-41。https://doi.org/10.6575/JoLIS.2005.52.03
- Fan, X. C. (2017). Research on Image Semantic Communication and Retrieval Based on Massive Resource Library of Internet. 電腦學刊, 28(1), 225-231. https://doi.org/10.3966/199115592017022801017
- 陳勇汀（2014）。An Exploratory Research on the Digital Library Model to Support Genetic Criticism。臺北市立圖書館館訊，32(2)，21-44。https://www.airitilibrary.com/Article/Detail?DocID=10112081-201412-201503300021-201503300021-21-44
- Chang, S. W. (2009). The Human Movement Analysis for Digital Human Motion Generation [doctoral dissertation, National Tsing Hua University]. Airiti Library. https://doi.org/10.6843/NTHU.2009.00769