Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

Images captured in low-light conditions usually suffer from degradation problems. Recently,
numerous deep learning-based methods are proposed for low-light image enhancement …

Abstract Zero-Reference Deep Curve Estimation (Zero-DCE) pioneers a new idea for Low-
Light Image Enhancement (LLIE), which is to formulate LLIE as a task of image-specific …

The proliferation of videos captured by sensor-based cameras has driven the application of
human action recognition (HAR) task. As the fundamental video application in human …

Self-training techniques have shown remarkable value across many deep learning models
and tasks. However, such techniques remain largely unexplored when considered in the …