بعد أكاديمية كاوست
Mohamed is an AI researcher at KAUST and earned the Kaggle Competitions Master title in December 2024. In 2026, Mohamed had a paper accepted at NeurIPS and mentored about 20 students at the KAUST Academy AI Summer School.
المشروع الصيفي
تخصص الذكاء الاصطناعي · دفعة 2024
Zero-Shot Multimodal Video Querying with Adaptive Candidates Ranking
Video content retrieval involves searching and extracting relevant video sections based on user queries. We introduce a multimodal video querying system that integrates text and image data to improve accuracy and efficiency. The system uses dynamic candidates generation and ranking techniques to improve response accuracy in zero-shot scenarios, where models haven’t been trained on specific datasets. Our system has set a new state-of-the-art benchmark on YouCook2 benchmark dataset.
مع أكاديمية كاوست
- دفعة 2024
جامعة الملك عبدالله للعلوم والتقنية (كاوست) · المدرسة الصيفية للذكاء الاصطناعي
هل تريد تحديث بياناتك أو حذفها؟ تواصل معنا.