Object detection is a widely applied approach in addressing many real-world computer
vision challenges. Despite its importance, object detection is computationally intensive and …

Abstract According to the World Health Organization, healthy communities rely on well-
functioning ecosystems. Clean air, fresh water, and nutritious food are inextricably linked to …

In this paper, we address the question of achieving high accuracy in deep learning models
for agricultural applications through edge computing devices while considering the …

Deep neural network (DNN) inference service at the edge is promising, but it is still non-
trivial to achieve high-throughput for multi-DNN model deployment on resource-constrained …

Early detection and diagnosis of brain tumors are of great significance, as they can be life
saving. Current state-of-the-art methods, including X-ray and magnetic resonance imaging …

The application of Transformer-based large models has achieved numerous success in
recent years. However, the exponential growth in the parameters of large models introduces …

Coastal wetlands and nearshore environments significantly contribute to carbon storage,
accounting for nearly half of global blue carbon. However, threats like climate change …

Edge AI has increasingly been adopted due to the rapid development of deep learning and
AI. At the same time, as AI models quickly grow in size and complexity, resource-constrained …

Artificial intelligence workloads, especially transformer models, exhibit emergent sparsity in
which computations perform selective sparse access to dense data. The workloads are …

Several Virtual Machines (VMs) belonging to various users transparently share physical
resources in multi-tenancy cloud milieu. In these situations, implementing an effective …