Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimation
By: Researcher
Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
| Authors | Huazhong Yang, Guijin Wang, Fei Qiao, Hengkai Guo, Xinghao Chen, Cairong Zhang |
| Journal/Conference Name | Proceedings - International Conference on Image Processing, ICIP |
| Paper Category | Artificial Intelligence |
| Paper Abstract | Hand pose estimation from monocular depth images is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with sophisticated design have been employed to address it, but the improvement over traditional methods is not so apparent. To promote the performance of directly 3D coordinate regression, we propose a tree-structured Region Ensemble Network (REN), which partitions the convolution outputs into regions and integrates the results from multiple regressors on each regions. Compared with multi-model ensemble, our model is completely end-to-end training. The experimental results demonstrate that our approach achieves the best performance among state-of-the-arts on two public datasets. |
| Date of publication | 2017 |
| Code Programming Language | Python |
| Comment |
Copyright Researcher 2022