Efficient Indexing of 3D Human Motions
| Authors | |
|---|---|
| Year of publication | 2021 |
| Type | Article in Proceedings |
| Conference | ACM International Conference on Multimedia Retrieval (ICMR) |
| MU Faculty or unit | |
| Citation | |
| web | https://dl.acm.org/doi/10.1145/3460426.3463646 |
| Doi | http://dx.doi.org/10.1145/3460426.3463646 |
| Keywords | human motion data; skeleton sequences; motion word; text-based processing; indexing; extended inverted files; ranked retrieval; approximate searching; scalability |
| Description | Digitization of human motion using 2D or 3D skeleton representations offers exciting possibilities for many applications but, at the same time, requires scalable content-based retrieval techniques to make such data reusable. Although a lot of research effort focuses on extracting content-preserving motion features, there is a lack of techniques that support efficient similarity search on a large scale. In this paper, we introduce a new indexing scheme for organizing large collections of spatio-temporal skeleton sequences. Specifically, we apply the motion-word concept to transform skeleton sequences into structured text-like motion documents, and index such documents using an extended inverted-file approach. Over this index, we design a new similarity search algorithm that exploits the properties of the motion-word representation and provides efficient retrieval with a variable level of approximation, possibly reaching constant search costs disregarding the collection size. Experimental results confirm the usefulness of the proposed approach. |
| Related projects: |