The burst of applications empowered by massive data have aroused unprecedented privacy
concerns in AI society. Currently, data confidentiality protection has been one core issue …

Enormous waves of technological innovations over the past several years, marked by the
advances in AI technologies, are profoundly reshaping the industry and the society …

In this work, we propose a novel and scalable solution to address the challenges of
developing efficient dense predictions on edge platforms. Our first key insight is that …

Blending multiple convolutional kernels is proved advantageous in neural architecture
design. However, current two-stage neural architecture search methods are mainly limited to …

Older adults around the world lack access to a wide range of potentially life-changing digital
applications, services, and information that could be provided by voice assistants (such as …

This study aims to solve the problems of inaccurate weighing of bamboo sticks and
inefficient manual counting. To overcome this problem, an improved MobileNetV3 model …

Pre-training over mixtured multi-task, multi-domain, and multi-modal data remains an open
challenge in vision perception pre-training. In this paper, we propose GPPF, a General …

We do not all have equal voices in the design decisions that affect us. Often, the institutions
that make these decisions are not committed to designing for members of marginalized …

The past decade has been witnessing remarkable advancements in computer vision and
deep learning algorithms, ushering in a transformative wave of large-scale edge …

Abstract Neural Architecture Search (NAS) can achieve accuracy superior to human-
designed neural networks, because of the easier automation process and searching …