Developing technology for visual, aural and multi-modal data understanding.
Eyes and ears on the future
VAIL is pioneering the development and application of machine-learning algorithms for a wide variety of multimedia and computer vision applications. Technologies developed in our lab are transforming a diversity of sectors including surveillance, agriculture, biomedical, manufacturing, sport, media and entertainment.
Our researchers are advancing image and video understanding for object detection, recognition, tracking and retrieval, analysis of medical imaging, scene understanding and event detection, and image classification. We’re pushing the boundaries of affective computing sentiment analysis for recognition and analysis of multimedia emotion and facial expression, powering meaningful recommendations in social networks and delivering superior audio analysis for event recognition and speaker verification.
The VAIL lab is equipped with advanced facilities including high-performance computation (GPUs), high-resolution cameras and mm-wave sensors.