The team is dedicated to automatically understanding multimedia data (images, video, digital documents) using deep learning techniques. We focus on acquisition, indexing, modeling, classification or automatic content recognition.
Skills: image processing (segmentation, feature extraction), machine learning and pattern recognition (connectionist, statistical and structural approaches), information fusion.
Working across disciplines of AI, Machine Learning and pattern recognition. With a team specialising in machine learning, deep learning, computer vision, data science and software, our team brings together a diverse set of skills to solve problems in these areas and build robust solutions.