microCLIP is a lightweight self-training framework that adapts CLIP for fine-grained image classification without requiring labeled data. While CLIP is strong in zero-shot transfer, it primarily ...

This is the supplementary material for the paper "Machine learning classification of CHIME fast radio bursts: II. Unsupervised Methods". zhugejiaming@mail.ustc.edu.cn ...

Abstract: There has been significant progress in unsupervised network representation learning (UNRL) approaches over graphs recently with flexible random-walk approaches, new optimization objectives, ...

Abstract: The report focuses on underground cable fault detection using IoT and machine learning techniques. Underground cables play a critical role in electrical distribution systems, and timely ...

Deep learning has transformed remote sensing, driving state-of-the-art results in land use and land cover classification, ...

Parents of young children with elevated blood sugar now have a new option that does not require a doctor’s prescription. The ...

Get an overview of generative AI, how it works, and how it’s poised to shape the future. Generative AI refers to a class of AI models, such as the GPT series or Llama, that analyzes large amounts of ...

From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media. Maria Ryskina, Matthew R. Gormley, Kyle Mahowald, David R. Mortensen, Taylor Berg-Kirkpatrick, ...

Cancer survivorship is frequently accompanied by long-term physical, psychological, and social challenges, including cancer-related fatigue, reduced ...

BACKGROUND: Hypertension induces structural and functional damage in multiple organs. Evidence of subclinical damage ...

Find out more about undergraduate study at the School of Electronic Engineering and Computer Science.