CNN

Scientist turns people’s mental images into text using ‘mind-captioning’ technology

A scientist in Japan has developed a technique that uses brain scans and artificial intelligence to turn a person’s mental images into accurate, descriptive sentences. While there has been progress in ...
9to5Mac

Apple just dropped a research dataset to help train AI image editing models

Apple has released Pico-Banana-400K, a highly curated 400,000-image research dataset which, interestingly, was built using Google’s Gemini-2.5 models. Here are the details. Apple’s research team has ...
Local News 8

Trump White House hangs image of Biden autopen signature in new ‘Presidential Walk of Fame’

(CNN) — President Donald Trump has introduced a “Presidential Walk of Fame” along a noticeable walkway outside the West Wing of the White House. “The Presidential Walk of Fame has arrived on the West ...
Frontiers

Fine-grained image classification using the MogaNet network and a multi-level gating mechanism

1 School of Electronics and Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou, China 2 Department of Mechanical and Electrical Engineering, Henan Vocational College of ...
GitHub

MinOS-WJ/CNN-MNIST

• Architecture: 4-layer CNN (convolutional layers with 32, 64, 128, and 256 filters) → Max pooling → Dropout → Fully connected layers. • Training: Dataset: MNIST (28×28 grayscale digits).
IEEE

IMed-CNN: Ensemble Learning Approach With Systematic Model Dropout for Enhanced Medical Image Classification Using Image Channels and Pixel Intervals

Abstract: To obtain light ensemble model through clearly explained effective ensemble member selection and finding data representation in various valuable forms are major challenges in medical image ...
Frontiers

Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism

1 State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research (IGSNRR), Chinese Academy of Sciences (CAS), Beijing, China 2 ...
IEEE

Benchmarking CNN Architectures for Tool Classification: Evaluating CNN Performance on a Unique Dataset Generated by Novel Image Acquisition System

Abstract: In this study, we introduce the ToolSurface-144 dataset, which is presented here for the first time. It comprises four subsets – Full R, Full S, Top R, and Top S – each containing 144 tool ...