Multimedia Processing Group

Welcome to the Multimedia Processing Group (GPM) website. We are part of the Signal Theory and Communications Department of the University Carlos III Madrid.

Would you like to join us?

Our research interests are on speech, audio, image and video processing, specially on automatic content extraction, speech recognition and last generation video coding. We have applied these methods in a variety of research projects like embedded vocal interfaces, speech transcription for hearing-impaired caption generation, automatic image and video annotation or HDTV video coding. Our main areas of research comprise:

• Classification, analysis and indexing of images and video
• Object tracking in images and video
• Speech technologies
• Multimedia applications of machine learning
• Video coding H.264/AVC, HVC, 3D, SVC and Perceptual Video Coding

More information:

• Fully Reconfigurable Video Coding (FRVC)
• Rate Control Algorithms for H.264/SVC
• Perceptual Video Coding
• Unsupervised learning methods for sequences: Theory and Applications
• Subjective Video Quality Assessment

List of publications

• Browse the list of publications of the members of GPM by author, year or category.

E-Archivo, Institutional Repository of University Carlos III Madrid

• You can also find full-text versions of many of our papers in the Institutional Open Repository of the University.

• More details about the members of GPM

The Multimedia Processing Group has a significant experience in R&D projects. Click below for an outline of the most relevant:

• AFICUS
• TRECVID
• Standard- and High- Definition Real-Time Video Coding: H.264/AVC and Beyond
• NowCasting: predición meteorológica para la gestión de plantas solare
• Mediapro