Sapienza - University of  Rome

DIET -  Department of Information Engineering, Electronics and Telecommunications  

 

Course Info: 

Tecniche Audiovisive

Prof. Aurelio Uncini   (info: aurelio _._ uncini _AT_ uniroma1 _._ it)

Laurea Magistrale: Ing. Comunicazioni, Ing. Informatica, Ing. Elettronica

 

Possible prosecution for Thesis, (also in companies, or in collaboration with other research centers at foreign universities).
For information contact the Teacher or its collaborators  Dr. Simone Scardapane,  Dr. Michele Scarpiniti, Dr. Danilo Comminiello.

 

Procedures for the final examination:
he examination consists in the development of a project (home-work project) that refers to a specific topic related to the program.
The project comes with a final presentation valid as an oral test. .

 

Informations

 

Course beginning:

Sept. 29, 2020
Duration 13 weeks.

 

Lesson timetable

Tuesday

17:00 - 19:00

DIET 09, SPV


Thursday 

12:00 - 14:00

DIET 09, SPV

 

 

Objectives of the Course

The student acquires basic and specific knowledge to the discipline. In particular, it is able to define and implement, in relation to aspects of processing, complex systems for capturing, manipulating and generating audio signals in different operating environments.

Main topics

Part 1:  Modern Audio-Video Scenarios

  1. Immersive audio-video communication
  2. Virtual, augmented and mixed reality
  3. Modern media
  4.  …

 

Part 2: Machine Learning for Audio, Image and Video Analysis

  1. Machine Learning
  2. Bayesian Theory of Decision
  3. Clustering Methods
  4. Supervised Neural Networks
  5. RNN; CNN, GAN
  6. ……

 

Part 3: Multimedia Content Analysis

  1. Content-Based Video Description
  2. Content-Based Audio Description
  3. Gesture Recognition
  4. Action Recognition

 

Part 4: Sentiment and Emotion Analysis

  1. From Video
  2. From Audio
  3. Text (e.g. twetter, whatsapp, ..)

  

 

References

Textbooks

  • Camastra, Vinciarelli, Machine Learning for Audio, Image and Video Analysis, Springer 2015.
  • Signal Processing Magazine “Special Issue on Semantic Retreival Of Multimedia,” IEEE SP Magazine MARCH 2006
  •  Aurelio Uncini, “Audio Digitale”, McGraw-Hill, ISBN: 88 386 6317-3, 2006. • Z. Wu, Ti. Yao, Y. Fu, Y-G Jiang Deep Learning for Video Classification and Captioning, arXiv:1609.06782v2 [cs.CV] 22 Feb 2018
  • Aurelio Uncini, “Introduction to Neural Networks and Deep Learning”, Ed. 2020,  (free pdf available  for the students).