Abstract: Vision-language models such as CLIP have boosted the performance of open-vocabulary object detection, where the detector is trained on base categories but required to detect novel categories ...

Abstract: It is always a challenging task in the industry to detect the small printing defects under complex background. To address this problem, a defect detection algorithm based on multi-scale ...

In fiction, magic makes levitation easy. With a simple swish-and-flick of his wand, Ron Weasley yanks a troll’s club high above its head in Harry Potter and the Sorcerer’s Stone. Through graceful ...