Talah Almuhawwis

Artificial Intelligence Specialization · Cohort 2025

Ball Action Spotting

We developed an AI-powered ball action spotting system that detects and classifies 12 types of ball-related actions from broadcast football videos, pinpointing the exact timestamps of each event. Our model processes dense, untrimmed match footage to retrieve moments with specific semantic meaning — enabling faster highlight generation, real-time analytics, and advanced coaching insights without manual tagging.

Read the final report (PDF)

See it in the program report (PDF)

Artificial Intelligence Specialization · Cohort 2023

Arabic Deepfake Audio Detection

With the fast evolution and widespread of deep-fake techniques in real-world scenarios, ensuring the authenticity and credibility of Arabic audio content has emerged as a paramount challenge. The imperative task of detecting deep-fake Arabic audio holds significant importance in upholding the reliability of auditory information and countering potential hazards. We propose a novel approach for deep-fake Arabic audio detection using machine learning and deep learning techniques, with a diverse dataset of real and fake Arabic audio, the dataset used is generated with put in mind high-quality and representative data and annotated In alignment with our commitment to advancing the field.

See it in the program report (PDF)