Working memory inspired hierarchical video decomposition with transformative representations. (arXiv:2204.10105v3 [cs.CV] UPDATED)

Video decomposition is very important to extract moving foreground objects
from complex backgrounds in computer vision, machine learning, and medical
imaging, e.g., extracting moving contrast-filled vessels from the complex and
noisy backgrounds of X-ray coronary angiography (XCA). However, the challenges
caused by dynamic backgrounds, overlapping heterogeneous environments and
complex noises still exist in video decomposition. To solve these problems,
this study is the first to introduce a flexible visual working memory model in
video decomposition tasks to provide interpretable and …

arxiv cv hierarchical memory video