Light Work
"Light work," in the context of recent research, encompasses diverse applications of light and image processing techniques across various scientific domains. Current research focuses on improving image quality and analysis under challenging lighting conditions, developing efficient algorithms for tasks like 3D reconstruction, object detection, and anomaly detection in images and videos, often leveraging deep learning models such as convolutional neural networks, transformers, and variational autoencoders. These advancements have significant implications for fields ranging from medical imaging and autonomous driving to remote sensing and quantum optics, enabling more robust and efficient solutions for complex problems.
Papers
BusiNet -- a Light and Fast Text Detection Network for Business Documents
Oshri Naparstek, Ophir Azulai, Daniel Rotman, Yevgeny Burshtein, Peter Staar, Udi Barzelay
Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures
Tianping Zhang, Yizhuo Zhang, Wei Cao, Jiang Bian, Xiaohan Yi, Shun Zheng, Jian Li