We present the 1st-place solution of OpenLane Topology in Autonomous Dri...
DETR has set up a simple end-to-end pipeline for object detection by
for...
Mainstream 3D representation learning approaches are built upon contrast...
The success of deep learning heavily relies on large-scale data with
com...
This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) v...
Existing deepfake detection methods perform poorly on face forgeries
gen...
Learning accurate depth is essential to multi-view 3D object detection.
...
Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to ...
To date, the most powerful semi-supervised object detectors (SS-OD) are ...
In this report, we present some experienced improvements to YOLO series,...
Recent advances in label assignment in object detection mainly seek to
i...
Label assignment has been widely studied in general object detection bec...
Imbalance issue is a major yet unsolved bottleneck for the current objec...
Although significant progress has been made in pedestrian detection rece...
Detecting human bodies in highly crowded scenes is a challenging problem...