Assane Gueye

Automatic Sign Language Recognition (ASLR) has emerged as a vital field for bridging the gap between deaf and hearing communities. However, the problem of sign-to-sign retrieval or detecting a specific sign within a sequence of continuous signs remains largely unexplored. We define this novel task as Sign Language Spotting. In this paper, we present a first step toward sign language retrieval by addressing the challenge of detecting the presence or absence of a query sign video within a sentence-level gloss or sign video. Unlike conventional approaches that rely on intermediate gloss recognition or text-based matching, we propose an end-to-end model that directly operates on pose keypoints extracted from sign videos. Our architecture employs an encoder-only backbone with a binary classification head to determine whether the query sign appears within the target sequence. By focusing on pose representations instead of raw RGB frames, our method significantly reduces computational cost and mitigates visual noise. We evaluate our approach on the Word Presence Prediction dataset from the WSLP 2025 shared task, achieving 61.88\% accuracy and 60.00\% F1-score. These results demonstrate the effectiveness of our pose-based framework for Sign Language Spotting, establishing a strong foundation for future research in automatic sign language retrieval and verification. Code is available at https://github.com/EbimoJohnny/Pose-Based-Sign-Language-Spotting

Continuously recognizing sign gestures and converting them to glosses plays a key role in bridging the gap between the hearing and hearing-impaired communities. This involves recognizing and interpreting the hands, face, and body gestures of the signer, which pose a challenge as it involves a combination of all these features. Continuous Sign Language Recognition (CSLR) methods rely on multi-stage pipelines that first extract visual features, then align variable-length sequences with target glosses using CTC or HMM-based approaches. However, these alignment-based methods suffer from error propagation across stages, overfitting, and struggle with vocabulary scalability due to the intermediate gloss representation bottleneck. To address these limitations, we propose AutoSign, an autoregressive decoder-only transformer that directly translates pose sequences to natural language text, bypassing traditional alignment mechanisms entirely. The use of this decoder-only approach allows the model to directly map between the features and the glosses without the need for CTC loss while also directly learning the textual dependencies in the glosses. Our approach incorporates a temporal compression module using 1D CNNs to efficiently process pose sequences, followed by AraGPT2, a pre-trained Arabic decoder, to generate text (glosses). Through comprehensive ablation studies, we demonstrate that hand and body gestures provide the most discriminative features for signer-independent CSLR. By eliminating the multi-stage pipeline, AutoSign achieves substantial improvements on the Isharah-1000 dataset, achieving an improvement of up to 6.1\% in WER score compared to the best existing method.

Birth Apshyxia (BA) is a severe condition characterized by insufficient supply of oxygen to a newborn during the delivery. BA is one of the primary causes of neonatal death in the world. Although there has been a decline in neonatal deaths over the past two decades, the developing world, particularly sub-Saharan Africa, continues to experience the highest under-five (<5) mortality rates. While evidence-based methods are commonly used to detect BA in African healthcare settings, they can be subject to physician errors or delays in diagnosis, preventing timely interventions. Centralized Machine Learning (ML) methods demonstrated good performance in early detection of BA but require sensitive health data to leave their premises before training, which does not guarantee privacy and security. Healthcare institutions are therefore reluctant to adopt such solutions in Africa. To address this challenge, we suggest a federated learning (FL)-based software architecture, a distributed learning method that prioritizes privacy and security by design. We have developed a user-friendly and cost-effective mobile application embedding the FL pipeline for early detection of BA. Our Federated SVM model outperformed centralized SVM pipelines and Neural Networks (NN)-based methods in the existing literature

The Internet today is owned, managed and controlled by a heterogeneous mix of autonomous systems. As a result, there's no one single entity that holds the "Internet kill switch". However, for emerging Low-Earth Orbit satellite Internet services, few gatekeepers control access globally, going against the fundamental principle of the Internet as a distributed and decentralized system. While satellite Internet remains a small part of the Internet today, it is growing exponentially and is often the only connectivity option for regions that are sparsely populated, experience political instability, or are prone to natural disasters that are likely to damage equipment. We first discuss why the satellite Internet world is ripe for monopolies, global ownership, and vertical integration. We then lay out OpenSpace, an architectural roadmap for a more open and heterogeneous satellite Internet paradigm, where many players build, launch, and manage satellites that communicate, to collectively deliver a reliable Internet service. We also discuss several open problems and research challenges in making satellite Internet more interoperable and heterogeneous, facilitating accessibility for big and small firms alike.

Africa lags behind in broadband connectivity and performance. The internet cost remains significantly higher compared to the Global North, and users experience network delays, availability issues, and slow speeds. Several studies demonstrated that measuring internet performance in Africa will provide a better understanding of the reasons underpinning poor broadband performance and ultimately driving substantial improvements. While internet measurement is critical on the continent, effective measurement requires robust infrastructure. We recognize that robust network measurement is expensive but need to be context-based and involve all the internet stakeholders from users to regulators to service providers and more. However, current measurement tools are mostly designed in the West and do not necessarily reflect Africa's broadband measurement challenges. To address this, we propose in this work a cost-effective and context-based mobile broadband measurement infrastructure.

Research on mobile money smishing is hindered, especially in the African context, as there is a lack of data. The absence of datasets and the fact that Mobile Network Operators don’t maintain such data pose a significant challenge. Additionally, the absence of a data collection infrastructure further complicates the data acquisition process. In response to this challenge, we developed a scalable and cost-effective honeynet infrastructure tailored for the efficient collection of organic Short Message Service (SMS) messages. The innovative approach involves harnessing the capabilities of Raspberry Pi units, USB multipliers, SIM cards from MNOs and GSM modems to create a scalable and adaptable solution. This aims to enhance smishing data collection, facilitating more efficient research into mobile money smishing.