arXiv subjects

Mayada Hadhoud

Publications and source records attributed to Mayada Hadhoud.

3 recordsLinked to original sources

arXiv2026

TOSHFA: A Mobile VR-Based System for Pose-Guided Exercise Rehabilitation for Low Back Pain

Low back pain (LBP) is a pervasive global health challenge, affecting approximately 80% of adults and frequently progressing into chronic or recurrent episodes. While exercise therapy is a primary clinical intervention, traditional at-home programs suffer from low adherence rates and the absence of professional supervision. This study introduces TOSHFA, an accessible mobile VR-based rehabilitation system that bridges this gap by combining computer vision with affordable hardware. The system utilizes a laptop webcam to perform real-time pose estimation via the MediaPipe framework, tracking 33 skeletal landmarks to provide immediate biofeedback. This data is streamed via low-latency UDP protocols to a smartphone mounted in a cardboard-style VR headset, where patients interact with a gamified 3D environment. A pilot study with 20 participants evaluated the system's performance and user engagement. Quantitative results yielded a mean System Usability Scale (SUS) score of 47.4, indicating marginal usability and a need for interface optimization. However, Game Experience Questionnaire (GEQ) data revealed high scores in positive affect and enjoyment, suggesting that the gamification elements--such as coin rewards and streak tracking--successfully maintained user motivation despite technical friction. These findings validate the feasibility of a smartphone-based tele-rehabilitation model and establish a technical foundation for future clinical trials involving multi-exercise protocols.

cs.HC↗

arXiv2022

Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes

A level generator is a tool that generates game levels from noise. Training a generator without a dataset suffers from feedback sparsity, since it is unlikely to generate a playable level via random exploration. A common solution is shaped rewards, which guides the generator to achieve subgoals towards level playability, but they consume effort to design and require game-specific domain knowledge. This paper proposes a novel approach to train generators without datasets or shaped rewards by learning at multiple level sizes starting from small sizes and up to the desired sizes. The denser feedback at small sizes negates the need for shaped rewards. Additionally, the generators learn to build levels at various sizes, including sizes they were not trained for. We apply our approach to train recurrent auto-regressive generative flow networks (GFlowNets) for controllable level generation. We also adapt diversity sampling to be compatible with GFlowNets. The results show that our generators create diverse playable levels at various sizes for Sokoban, Zelda, and Danger Dave. When compared with controllable reinforcement learning level generators for Sokoban, the results show that our generators achieve better controllability and competitive diversity, while being 9x faster at training and level generation.

cs.LG↗

arXiv2021

INSTA-YOLO: Real-Time Instance Segmentation

Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different object of the scene, even if they belong to the same class. This is useful in various scenarios, especially in occlusions. Instance segmentation is usually performed as a two-stage pipeline. First, an object is detected, then semantic segmentation within the detected box area. This process involves costly up-sampling, especially for the segmentation part. Moreover, for some applications, such as LiDAR point clouds and aerial object detection, it is often required to predict oriented boxes, which add extra complexity to the two-stage pipeline. In this paper, we propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation. The proposed model is inspired by the YOLO one-shot object detector, with the box regression loss is replaced with polynomial regression in the localization head. This modification enables us to skip the segmentation up-sampling decoder altogether and produces the instance segmentation contour from the polynomial output coefficients. In addition, this architecture is a natural fit for oriented objects. We evaluate our model on three datasets, namely, Carnva, Cityscapes and Airbus. The results show our model achieves competitive accuracy in terms of mAP with significant improvement in speed by 2x on GTX-1080 GPU.

cs.CV↗