Abstract | ||
---|---|---|
We propose a deep learning based method to directly estimate the human joint positions in 3D space from 2D fisheye images captured in an egocentric manner. The core of our method is a novel network architecture based on Inception-v3 [4], featuring the asymmtric convolutional filter size, the long short-term memory module, and the anthropomorphic weights on the training loss. We demonstrate our method outperform state-of-the-art method under different tasks. Our method can be helpful to develop useful deep learning network for human-machine interaction and VR/AR applications.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3180308.3180344 | COMPANION OF THE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT USER INTERFACES (IUI'18) |
Keywords | Field | DocType |
Fisheye Image, 3D Human Pose Estimation, Egocentric View, Convolutional Neural Networks, Anthropomorphic Weights | Computer vision,Computer science,Convolutional neural network,Network architecture,Pose,Human–computer interaction,Artificial intelligence,Deep learning,Memory module | Conference |
ISBN | Citations | PageRank |
978-1-4503-5571-1 | 0 | 0.34 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ching-Chun Chen | 1 | 0 | 0.34 |
Chia-Min Wu | 2 | 0 | 0.34 |
I-Chao Shen | 3 | 109 | 13.17 |
Bing-Yu Chen | 4 | 1132 | 101.82 |