magyar nyelvű adatlap
angol nyelvű adatlap
Media Informatics Systems
A tantárgy neve magyarul / Name of the subject in Hungarian: Médiainformatikai rendszerek
Last updated: 2018. augusztus 26.
Name
Position
University, Department
Dr. Gábor MAGYAR PhD
Associate Professor
BME-TMIT
Dr. Péter MIHAJLIK PhD
Lecturer
Dr. Gábor SZŰCS PhD
Week 1:
Basic definitions. Media content management. Main topics of multimedia (image, voice, video) processing.
Week 2:
Processing audio contents. Short Time Fourier Spectrum, windowing, spectrogram computation. The fundamentals of signal detection.
Week 3:
Music recognition. Challenges in real-time pattern matching: additive noise, linear and non-linear distortions. Audio fingerprinting. Case study: Shazam.
Week 4:
Recognition of variable sound and image signals. Statistics based general classification. Probability density function, likelihood, training and test. Bayes' theorem.
Week 5:
Multimedia classification tasks based on multi-variate Gaussian Mixture Models.
Week 6:
Maximum Likelihood vs. Discriminative Training – theoretical and practical issues regarding audio and image data. The application of Multi Layer Perceptrons on media informatics tasks.
Week 7:
Processing time-varying signals: Dynamic Time Warping, Hidden Markov-Models and their practical implementations. Fundamentals of speech recognition.
Week 8:
Contemporary speech recognition technologies. Acoustic, pronunciation and language models. Subtitling methods and standards. Case studies: BBC and the Hungarian National Television subtitling approaches.
Week 9:
Deep learning: deep feed-forward neural nets, convolutional nets and requrrent networks - and their applications on automatic annotation of media contents (text, sound, image and video).
Week 10:
Complex tasks based on multimedia technologies: shape detection in images, object tracking in videos. Face detection and recognition solutions. Video processing methods in practice: hand gesture recognition in videos.
Week 11:
Metadata: semantic and desriptive metadata. Multimedia metadata standards. EBU/SMPTE metadata, Dublin Core, Material Exchange Format (MXF).
Week 12:
Multimedia databases. Multimedia information retrieval. Search modes, types, algorithms. Quality measurement of an information retrieval system.
Week 13:
Digital Media Management Systems (DMMS) / Multimedia Asset Management. Structure of the systems: gathering, storing, displaying subsystems. Lifecycle attributes. Integration tools. Architecture of the media content management systems, and types of it: DAM, DM, KM, Web CMS, ECM. Overall model of systems.
Week 14:
Digital archiving: tasks, approaches, technics. Archiving strategies: On-line, near-line, off-line, off-site accessibility, levels. Record management.
In the practice sessions, the following topics (not exculsively and not fully) will be discussed: audio feature extraction, audio fingerprinting, GMM, automatic speech recognition, language modeling, applied deep neural nets in Keras, image annotation tasks, multimedia retrieval, visualization tools, video processing.
University, department
Dr. Magyar Gábor PhD
Dr. Szűcs Gábor PhD
Dr. Mihajlik Péter PhD
Dr. Gyires-Tóth Bálint PhD