no code implementations • ResTUP (LREC) 2022 • Md Saroar Jahan, Mainul Haque, Nabil Arhab, Mourad Oussalah
This paper introduces BanglaHateBERT, a retrained BERT model for abusive language detection in Bengali.
no code implementations • LREC 2022 • Md Saroar Jahan, Mourad Oussalah, Nabil Arhab
The majority of this research has concentrated on English, although one notices the emergence of multilingual detection tools such as multilingual-BERT (mBERT).
no code implementations • LREC 2022 • Md Saroar Jahan, Djamila Romaissa Beddiar, Mourad Oussalah, Muhidin Mohamed
Automatic identification of cyberbullying from textual content is known to be a challenging task.
no code implementations • 30 Mar 2024 • Md Saroar Jahan, Mourad Oussalah, Djamila Romaissa Beddia, Jhuma Kabir Mim, Nabil Arhab
The surge of interest in data augmentation within the realm of NLP has been driven by the need to address challenges posed by hate speech domains, the dynamic nature of social media vocabulary, and the demands for large-scale neural networks requiring extensive training data.
no code implementations • 16 Dec 2023 • Jhuma Kabir Mim, Mourad Oussalah, Akash Singhal
The primary emphasis is placed on the meticulous detection of hate speech within the linguistic domains of Bengali, Assamese, and Bodo, forming the framework for Task 4: Annihilate Hates.
no code implementations • 10 Sep 2023 • Usman Muhammad, Mourad Oussalah, Jorma Laaksonen
Conventional feature extraction techniques in the face anti-spoofing domain either analyze the entire video sequence or focus on a specific segment to improve model performance.
no code implementations • 23 Aug 2023 • Usman Muhammad, Mourad Oussalah, Jorma Laaksonen
Inspired by the visual saliency theory, we present a video summarization method for face anti-spoofing detection that aims to enhance the performance and efficiency of deep learning models by leveraging visual saliency.
2 code implementations • 6 Jul 2023 • Usman Muhammad, Md Ziaul Hoque, Mourad Oussalah, Jorma Laaksonen
Face presentation attacks (PA), also known as spoofing attacks, pose a substantial threat to biometric systems that rely on facial recognition systems, such as access control systems, mobile payments, and identity verification systems.
no code implementations • 5 Jan 2023 • Usman Muhammad, Jorma Laaksonen, Djamila Romaissa Beddiar, Mourad Oussalah
The latter combines the predictions from the base models, leveraging their complementary information to better handle unseen target domains and enhance the overall performance.
no code implementations • 28 Aug 2022 • Usman Muhammad, Mourad Oussalah
In particular, the proposed scheme provides a much lower error (from 15. 2% to 6. 7% on CASIA-FASD and 5. 9% to 4. 9% on Replay-Attack) compared to baselines in cross-database scenarios.
no code implementations • 27 Aug 2022 • Usman Muhammad, Mourad Oussalah
To achieve this, we exploit the temporal consistency based on three RGB frames which are acquired at three different times in the video sequence.
2 code implementations • 25 Sep 2021 • Amine Abdaoui, Mohamed Berrimi, Mourad Oussalah, Abdelouahab Moussaoui
The obtained results show that pre-training a dedicated model on a small dataset (150 MB) can outperform existing models that have been trained on much more data (hundreds of GB).
no code implementations • 25 May 2021 • Djamila Romaissa Beddiar, Md Saroar Jahan, Mourad Oussalah
With proliferation of user generated contents in social media platforms, establishing mechanisms to automatically identify toxic and abusive content becomes a prime concern for regulators, researchers, and society.
no code implementations • 22 May 2021 • Md Saroar Jahan, Mourad Oussalah
With the multiplication of social media platforms, which offer anonymity, easy access and online community formation, and online debate, the issue of hate speech detection and tracking becomes a growing challenge to society, individual, policy-makers and researchers.