Conservative wasserstein training for pose estimation
This paper targets the task with discrete and periodic class labels (eg, pose/orientation
estimation) in the context of deep learning. The commonly used cross-entropy or regression …
estimation) in the context of deep learning. The commonly used cross-entropy or regression …
Self-supervised learning for specified latent representation
C Liu, L Song, J Zhang, K Chen… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Current latent representation methods using unsupervised learning have no semantic
meaning; thus, it is difficult to directly express their physical task in the real world. To this …
meaning; thus, it is difficult to directly express their physical task in the real world. To this …
Coarse-to-fine deep learning of continuous pedestrian orientation based on spatial co-occurrence feature
SS Kim, IY Gwak, SW Lee - IEEE transactions on intelligent …, 2019 - ieeexplore.ieee.org
The continuous orientation estimation of a moving pedestrian is a crucial issue in
autonomous driving that requires the detection of a pedestrian intending to cross a road. It is …
autonomous driving that requires the detection of a pedestrian intending to cross a road. It is …
Hierarchical regression learning for car pose estimation
D Yang - 2017 - trepo.tuni.fi
Car pose estimation is a hot topic in computer vision because of its significance in intelligent
transportation system. Considering the circular label space of car pose, the main limitation of …
transportation system. Considering the circular label space of car pose, the main limitation of …