BMVC

CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a …

Enhancing Human Motion Assessment by Self-supervised Representation Learning

The space of human motions is vast, ranging from daily behaviors of healthy adults to the slow and stiff motions of Parkinson's patients, or to infant motions. This poses significant challenges when the task is focused on a relatively niche motion …