The energy consumption in buildings accounts for a significant proportion of total energy and
carbon emissions over the world. To reduce the building energy consumption and achieve …

With the rapid development of urbanization and the improvement of living standards of
residents in China, the energy consumption and carbon emissions of the building sector is …

Passing gradient is a widely used scheme in modern multi-node learning system (eg,
distributed training, collaborative learning). In a long time, people used to believe that gradients …

Abstract Model compression is an effective technique to efficiently deploy neural network
models on mobile devices which have limited computation resources and tight power budgets. …

Multi-sensor fusion is essential for an accurate and reliable autonomous driving system.
Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with …

The performance of generative adversarial networks (GANs) heavily deteriorates given a
limited amount of training data. This is mainly because the discriminatorsis memorizing the …

Abstract Model quantization is a widely used technique to compress and accelerate deep
neural network (DNN) inference. Emergent DNN hardware accelerators begin to support …

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive
safely. Given the limited hardware resources, existing 3D perception models are not able to …

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work
processes 3D data using either voxel-based or point-based NN models. However, both …

Objective: To assess the current evidence of the relationship between malocclusion/orthodontic
treatment need and quality of life (QoL). Materials and Methods: Four electronic …