Multimodal AI, Computer Vision and Sign Language Technologies

Our research group at Hacettepe University, works on computer vision, machine learning, multimodal and cross-modal learning, and learning from limited data. We have strong experience in sign language AI, including continuous sign language translation, sign spotting, sign language production, pose/skeleton-based modeling, and multimodal representation learning.

We also work on applied machine learning in medical imaging, including dermatology and endoscopic image analysis, as well as other scientific data domains. Our current research is supported by TÜBİTAK 1001 and EuroHPC grants.

We are interested in joining Horizon Europe consortia as a technical research partner, particularly in projects related to multimodal AI, inclusive human–AI interaction, digital health, future workplaces, accessibility, and low-resource AI.