Details for entry MIPAL

Short Name:
MIPAL
Long Name:
Machine intelligence and pattern analysis Lab, Seoul national university
Use MPII Pose for training:
no
Use COCO for training:
yes
Use external training:
no
Use multiple frames for pose estimation:
no
Predict pose tracks:
yes
URL:
https://arxiv.org/abs/1905.09500
Description:
For human pose estimation in videos, it is significant how to use temporal information between frames. We propose temporal flow maps for limbs (TML) and a multi-stride method to estimate and track human poses. The proposed temporal flow maps are unit vectors describing the limbs’ movements. We constructed a network to learn both spatial information and temporal information end-to-end. Spatial information such as joint heatmaps and part affinity fields is regressed in the spatial network part, and the TML is regressed in the temporal network part. We also propose a data augmentation method to learn various types of TML better. The proposed multi-stride method expands the data by randomly selecting two frames within a defined range.
Bibtex:
Specs:
TitanX GPU
Runtime:
1
Open Source:
no
Number of submissions:
2
Last Submission:
2018-08-31 12:36:08
Published:
0000-00-00 00:00:00

Imprint | Data Protection


© PoseTrack