The absolute depth values of surrounding environments provide crucial cu...
We propose a domain adaptation method, MoDA, which adapts a pretrained
e...
Recent advances in vision-language pre-training have demonstrated astoun...
Patient scans from MRI often suffer from noise, which hampers the diagno...
In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US
...
We propose a light-weight, self-supervised adaptation for a visual navig...
We present SGoLAM, short for simultaneous goal localization and mapping,...