IEEE

Leveraging Transfer Learning and Mobile-Enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition

Abstract: The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing ...
CNET

Meta's Neural Band Can Now Let You Handwrite on Your Pants

An early access update is giving the bands the ability to scribble messages on your leg (or anywhere else) while wearing Ray-Ban Display glasses. I haven't tried it yet. I started with CNET reviewing ...
GitHub

official codes for our BMVC 2025 paper (Catch Your Concepts: A Flexible Concept Locator for Interpretable Visual Recognition)

Python 3.10 & PyTorch 2.1 with CUDA. Use conda to install a virtual environment. The following steps have been tested on Miniconda3. conda create -n loc-cbm python=3.10 conda activate loc-cbm conda ...
IEEE

Clustering research of handwritten digit recognition by genetic algorithm

Abstract: A method of genetic algorithms is briefly introduced in research of handwritten digit recognition in this paper. Considering the features of handwritten digit, genetic algorithm is ...
GitHub

Hierarchical Deep Temporal Models for Group Activity Recognition

A PyTorch implementation of "Hierarchical Deep Temporal Models for Group Activity Recognition" (CVPR 2016). This repository reproduces and extends the baselines described in the paper and provides ...