Search Results for author:
Found 4 papers, 3 papers with code
CLRmatchNet: Enhancing Curved Lane Detection with Deep Matching Process
Our research introduces MatchNet, a deep learning submodule-based approach aimed at improving the label assignment process.
Ranked #11 on
Lane Detection
on CULane
Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations
TransCenter is the first center-based transformer framework for MOT, and is also among the first to show the benefits of using transformer-based architectures for MOT.
Ranked #1 on
Multiple Object Tracking with Transformer
on MOT20
Multi-Object Tracking
Multiple Object Tracking with Transformer
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object.
Ranked #3 on
Multi-Object Tracking
on MOT20
(using extra training data)
Insights on Evaluation of Camera Re-localization Using Relative Pose Regression
We believe that unlike other relocalization approaches, in the case of relative pose regression, the regressed subspace 3D volume is less dependent on the scene and more affect by the method used to score the overlap, which determined how closely sampled viewpoints are.
