Reusing features in deep networks through dense connectivity is an effective way to achieve
high computational efficiency. The recent proposed CondenseNet has shown that this …

During the past decade, human activity recognition (HAR) using wearable sensors has
become a new research hot spot due to its extensive use in various application domains …

Learning user representations is a vital technique toward effective user modeling and
personalized recommender systems. Existing approaches often derive an individual set of …

Deep neural networks (DNNs) have shown great success in completing complex tasks.
However, DNNs inevitably bring high computational cost and storage consumption due to …

Abstract Knowledge distillation has demonstrated encouraging performances in deep model
compression. Most existing approaches, however, require massive labeled data to …

Abstract Knowledge distillation is a promising model compression technique that generally
distills the knowledge from a complex teacher model to a lightweight student model …

The short-form videos have explosive popularity and have dominated the new social media
trends. Prevailing short-video platforms, eg, TikTok, Instagram Reels, and YouTube Shorts …

With the development of high-resolution remote sensing images (HR-RSIs) and the
escalating demand for intelligent analysis, fine-grained recognition of geospatial objects has …

As the development of wind energy industry, the safe production of wind farms has become
an urgent problem. To avoid serious faults and deterioration, building effective diagnostic …

Self-supervised pre-training has attracted increasing attention given its promising
performance in training backbone networks without using labels. By far, most methods focus …