Enhancing Effectiveness of Descriptors for Searching and Recognition in Motion Capture Data
| Authors | |
|---|---|
| Year of publication | 2017 |
| Type | Article in Proceedings |
| Conference | 19th IEEE International Symposium on Multimedia |
| MU Faculty or unit | |
| Citation | |
| Doi | http://dx.doi.org/10.1109/ISM.2017.39 |
| Field | Informatics |
| Keywords | motion capture data; similarity-based comparison; motion images; joint weights; deep convolutional neural network; distance function; action recognition |
| Description | Computer-aided analyses of motion capture data require an effective and efficient concept of motion similarity. Traditional methods generally compare motion sequences by applying time-warping techniques to high-dimensional trajectories of joints. An increasing effectiveness of machine-learning techniques, such as deep convolutional neural networks, brings new possibilities for similarity comparison. Inspired by recent advances in neural networks and image processing, we propose new variants of transformation of motion sequences into 2D images. The generated images are used to fine-tune a neural network from which 4,096D features are extracted and compared by a modified Euclidean distance. The proposed concept is not only efficient but also very effective and outperforms existing methods on a challenging dataset with 130 categories. |
| Related projects: |