Triplet Vision Transformer for Word Image Retrieval in Historical Arabic Documents

Word Spotting in Historical Arabic Documents Using Deep Learning

Evaluation of feature-embedding methods for word spotting in historical arabic documents

International audience Retrieving and indexing historical Arabic documents remain a v

Optimal Transport Distillation for Robust Multilingual Vision-Language Image Retrieval in Low-Resource Noisy Text Queries

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Continual Learning for documents image recognition

Continual Learning for documents image recognition

Poster presented at the Deep Learning Indaba 2023 by Marwa Dhiaf

Computer Vision for Image Classification

A learning competition for CMU Data Science Club and AI Saturdays Kigali in Rwanda
The instances were drawn randomly from a database of 7 outdoor images. The images were hand-segmented to create a classification for every pixel.
Each instance is a 3 pixe

MonkeyPox Skin Image Dataset for Computer Vision (MPox-Vision)

Mpox-Vision is a quality-verified dataset of monkeypox skin images curated to support the developmen