Abstract: Current audio-visual representation learning can capture rough object categories (e.g., "animals" and "instruments"), but it lacks the ability to recognize fine-grained details, such as ...

Abstract: Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against ...

The technical merits of every science fiction film get debated ad nauseam, and we’re seeing that with Project Hail Mary. NASA has even posted a page on its website discussing the movie’s science. And ...