We present the 1st-place solution of OpenLane Topology in Autonomous Dri...
Although end-to-end multi-object trackers like MOTR enjoy the merits of
...
In recent years, transformer-based detectors have demonstrated remarkabl...
The labels of monocular 3D object detection (M3OD) are expensive to obta...
As an inherently ill-posed problem, depth estimation from single images ...
Discriminative representation is crucial for the association step in
mul...
Multivariate time series forecasting is a challenging task because the d...
Existing online multiple object tracking (MOT) algorithms often consist ...
Few-shot learning is challenging due to the limited data and labels. Exi...