Search Results for author:
Found 5 papers, 1 papers with code
Argoverse: 3D Tracking and Forecasting with Rich Maps
In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting.
Domain Adaptation through Synthesis for Unsupervised Person Re-identification
To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised way.
Ranked #13 on
Person Re-Identification
on PRID2011
Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence.
One-Shot Metric Learning for Person Re-Identification
The proposed one-shot learning achieves performance that is competitive with supervised methods, but uses only a single example rather than the hundreds required for the fully supervised case.
Automatic Tracker Selection w.r.t Object Detection Performance
The tracking algorithm performance depends on video content.
