To retrieve information from the enormous mass of today's multimedia data, users require tools that automatically understand and manipulate the image/video content in the same structured way as a traditional database manages numeric and textual data. This problem is both important and challenging.
Audio-Visual Signal Processing focuses on areas such as Automatic Speech Recognition (ASR) and Biometrics. Our most recent research includes facial tracking and feature extraction algorithms, information fusion across the audio and visual modalities, and ASR system architectures using dynamic Bayesian networks (DBNs).
Image and Video Analysis aims to extract semantics from digital images and video streams, such as object detection/tracking, multimedia information search/summarization, intelligent surveillance and remote monitoring.
Image and Video Recovery are the problems of uncovering with digital signal processing approaches the information lost due a number of reasons in the acquisition process. Typical applications are blur removal, denoising, increasing the resolution (super resolution).
Machine learning is a subfield of computer science that evolved from the study of pattern recognition and computational learning theory in artificial intelligence. Deep Learning is a branch of Machine Learning based on learning representations of data.
Compressive sensing is an emerging new paradigm for signal sensing and many related fields in signal processing, where signal acquisition and compression are merged together with the use of prior knowledge about the signals.
Many multimedia communication applications require transporting of compressed video data over lossy channels that can exhibit wide variability in throughput, delay, and packet loss. Providing acceptable video quality in such environments is a demanding task for both the video encoder/decoder as well as the communication and networking infrastructure.