Abstract | ||
---|---|---|
In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i. e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improves our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges. |
Year | Venue | Field |
---|---|---|
2018 | THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Generalizability theory,ENCODE,Kinematics,Computer science,Virtual camera,3D pose estimation,Grammar,Pose,Artificial intelligence,Hierarchy,Machine learning |
DocType | Citations | PageRank |
Conference | 13 | 0.50 |
References | Authors | |
16 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haoshu Fang | 1 | 57 | 6.86 |
Yuanlu Xu | 2 | 128 | 6.96 |
Wenguan Wang | 3 | 1019 | 37.24 |
Xiaobai Liu | 4 | 800 | 40.79 |
Song-Chun Zhu | 5 | 6580 | 741.75 |