Powdered activated carbon (PAC) was introduced into hydrothermal carbonization (HTC) as
a catalyst for treatment of cotton pulp black liquor (CPBL) in the present work. The influence …

While scene text image super-resolution (STISR) has yielded remarkable improvements in
accurately recognizing scene text, prior methodologies have placed excessive emphasis on …

Few-shot recognition learns a recognition model with very few (eg, 1 or 5) images per category,
and current few-shot learning methods focus on improving the average accuracy over …

Advances in vehicle-networking technologies have enabled vehicles to cooperate in mixed
traffic. However, realizing the cooperative decision-making of multiple connected …

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to
real-world applications this paper proposes a practical FSL (pFSL) setting. pFSL is based on …

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream
tasks steadily increases, too. To economically fine-tune these models, parameter-efficient …

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth
recently, and they mostly rely on either a dedicated dense matching mechanism or a costly …

Nano-flowered yavapaiite anchored on magnetic graphite oxide (YMGO) was firstly fabricated
by one-pot with K 2 FeO 4 as both oxidant and iron source to selectively reduce nitrate to …

Long-tailed object detection faces great challenges because of its extremely imbalanced
class distribution. Recent methods mainly focus on the classification bias and its loss function …

Deep neural networks, while achieving remarkable success across diverse tasks, demand
significant resources, including computation, GPU memory, bandwidth, storage, and energy. …