It is desirable to enable robots capable of automatic assembly. Structur...
We present TWIST, a novel self-supervised representation learning method...
Compared to many other dense prediction tasks, e.g., semantic segmentati...
Multiple-object tracking(MOT) is mostly dominated by complex and multi-s...
We present Sparse R-CNN, a purely sparse method for object detection in
...
To date, most existing self-supervised learning methods are designed and...
To date, instance segmentation is dominated by twostage methods, as pion...
In this work, we aim at building a simple, direct, and fast instance
seg...
Vehicle re-identification (Re-ID) often requires one to recognize the
fi...