Working memory inspired hierarchical video decomposition with transformative representations
Binjie Qin, Haohao Mao, Ruipeng Zhang, Yueqi Zhu, Song Ding, Xu Chen

TL;DR
This paper introduces a novel hierarchical deep architecture inspired by visual working memory for effective video decomposition, especially in medical imaging, by integrating transformative representations and advanced neural modules.
Contribution
It pioneers the integration of a flexible visual working memory model into video decomposition, combining structured and unstructured representations for improved performance.
Findings
Outperforms state-of-the-art methods in vessel extraction accuracy
Effectively separates moving objects from complex backgrounds
Demonstrates high flexibility and computational efficiency
Abstract
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 high-performance hierarchical deep architecture, integrating the transformative representations between sensory and control layers from the perspective of visual and cognitive neuroscience. Specifically, robust PCA unrolling networks acting as a structure-regularized sensor layer decompose XCA into…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPhotoacoustic and Ultrasonic Imaging · Image and Signal Denoising Methods · Medical Image Segmentation Techniques
MethodsTanh Activation · Sigmoid Activation · Long Short-Term Memory · Principal Components Analysis
