Recent advancements in vision foundation models (VFMs) have opened up ne...
Learning from large-scale contrastive language-image pre-training like C...
Recent incremental learning for action recognition usually stores
repres...
Due to the extreme complexity of scale and shape as well as the uncertai...
Current methods for LIDAR semantic segmentation are not robust enough fo...
Due to the more dramatic multi-scale variations and more complicated
for...
3D object detection has been wildly studied in recent years, especially ...
Classical close-set semantic segmentation networks have limited ability ...
The semantic representation of deep features is essential for image cont...
Scene recognition is a fundamental task in robotic perception. For human...