ABEJA provides an AI platform that allows for faster circulation of high-volume data through their system which includes data collection, storage, training models, deploying models for inference, and retraining models. The platform aims to make deploying machine learning in production less complex than expected through their AI-Ops services for businesses. Their goal is to implement machine learning to create a more fruitful world.
4. Related Work
Pictorial structures Hierarchical models
Sequential prediction Convolutional architectures
[A. Toshev and C. Szegedy, CVPR’2013]
[Tian et al., ICCV’2011][Mykhaylo et al., CVPR’2009]
[Ramakrishna et al., 2014]
5. Related Work
Pictorial structures Hierarchical models
Sequential prediction Convolutional architectures
[A. Toshev and C. Szegedy, CVPR’2013]
[Tian et al., ICCV’2011][Mykhaylo et al., CVPR’2009]
[Ramakrishna et al., 2014]
10. Pose Machines
Stage I Confidence
Head Neck L-Shoulder L-Elbow L-Wrist
g2g1 g3
Context
Features
Context
Features
Stage I
Confidence Maps
Stage II
Confidence Maps
Stage III
Confidence Maps
Image
Features
[Ramakrishna et al., 2014]
11. Pose Machines
Stage II Confidence
g2g1 g3
Context
Features
Context
Features
Stage I
Confidence Maps
Stage II
Confidence Maps
Stage III
Confidence Maps
Image
Features
Head Neck L-Shoulder L-Elbow L-Wrist
[Ramakrishna et al., 2014]
12. Pose Machines
Stage III Confidence
Head Neck L-Shoulder L-Elbow L-Wrist
g2g1 g3
Context
Features
Context
Features
Stage I
Confidence Maps
Stage II
Confidence Maps
Stage III
Confidence Maps
Image
Features
Head Neck L-Shoulder L-Elbow L-Wrist
[Ramakrishna et al., 2014]
13. Pose Machines
Stage III Confidence
Head Neck L-Shoulder L-Elbow L-Wrist
g2g1 g3
Context
Features
Context
Features
Stage I
Confidence Maps
Stage II
Confidence Maps
Stage III
Confidence Maps
Image
Features
Head Neck L-Shoulder L-Elbow L-Wrist
[Ramakrishna et al., 2014]