no code implementations • 18 Jun 2024 • Sarah Alyami, Hamzah Luqman
Continuous Sign Language Recognition (CSLR) focuses on the interpretation of a sequence of sign language gestures performed continually without pauses.
1 code implementation • 12 Jun 2024 • Ahmed Abul Hasanaath, Hamzah Luqman, Raed Katib, Saeed Anwar
Recently, several techniques have been proposed to differentiate deepfakes from realistic images and videos.
1 code implementation • 28 Jun 2023 • Zaid Alyafeai, Maged S. Alshaibani, Badr AlKhamissi, Hamzah Luqman, Ebrahim Alareqi, Ali Fadel
Large language models (LLMs) have demonstrated impressive performance on various downstream tasks without requiring fine-tuning, including ChatGPT, a chat-based model built on top of LLMs such as GPT-3. 5 and GPT-4.
1 code implementation • 9 May 2023 • Rawwad Alhejaili, Motaz Alfarraj, Hamzah Luqman, Ali Al-Shaikhi
Secondly, we randomize the number of recursions during training to decrease the overall training time.
1 code implementation • 10 Oct 2022 • Mohammed R. Al-Sinan, Aseel F. Haneef, Hamzah Luqman
In this work, we propose a system for masked face recognition.
1 code implementation • 8 Oct 2022 • Hamzah Luqman
To benchmark this dataset, we propose an encoder-decoder model for Continuous ArSL recognition.
1 code implementation • IEEE Access 2022 • Hamzah Luqman
This approach preserves the spatial and temporal information of the sign by fusing the sign’s key postures in the forward and backward directions to generate an accumulative video motion frame.
2 code implementations • ACM Transactions on Asian and Low-Resource Language Information Processing 2021 • Ala Addin I. Sidig, Hamzah Luqman, Sabri Mahmoud, Mohamed Mohandes
The availability of a comprehensive benchmarking database for ArSL is one of the challenges of the automatic recognition of Arabic Sign language.