Name
Abstract | ||
|---|---|---|
Along with the development of the motion capture (mocap) technique, large-scale 3D motion databases have become increasingly available. In this paper, a novel approach is presented for motion retrieval based on double-reference index (DRI). Due to the high dimensionality of motion's features, Isomap nonlinear dimension reduction is used. In addition, an algorithmic framework is employed to approximate the optimal mapping function by a Radial Basis Function (RBF) in handling new data. Subsequently, a DRI is built based on selecting a small set of representative motion clips in the database. Thus, the candidate set is obtained by discarding the most unrelated motion clips to significantly reduce the number of costly similarity measures. Finally, experimental results show that these approaches are effective for motion data retrieval in large-scale databases. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1142/S0218001410008044 | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
Feature, Isomap, RBF, index, double-reference, motion recognition and retrieval | Motion capture,Dimensionality reduction,Radial basis function,Data retrieval,Artificial intelligence,Small set,Computer vision,Pattern recognition,Curse of dimensionality,Nonlinear dimension reduction,Machine learning,Mathematics,Isomap | Journal |
Volume | Issue | ISSN |
24 | 4 | 0218-0014 |
Citations | PageRank | References |
0 | 0.34 | 16 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jian Xiang | 1 | 0 | 2.70 |
| Zhijun Zheng | 2 | 6 | 2.90 |