Michele SVANERA

AUDIO-VISUAL FEATURES RECONSTRUCTION BASED ON fMRI SIGNAL

There has been an increasing interest in how the human brain responds to natural stimuli such as video watching in the neuroimaging field. The goal to of this research is to find relationships between the audio-video stimuli and fMRI data recorded while watching these stimuli. Quantitative modeling of human brain activity can provide crucial insights about cortical representations and can form the basis for brain decoding devices. In addition, brain data can furnish a significant commitment to improving image-video algorithms (ex. saliency). The research is supported by the Department of Cognitive Neuroscience in Maastricht University (Netherlands), the Departments of Physiology and Pharmacology and Psychiatry in Tel-Aviv University (Israel), Department of Film Studies in ELTE University (Hungary), and (my) Department of Information Engineering in University of Brescia (Italy).

 
MULTIMEDIA CONTENT ANALYSIS FOR VIDEO RECOMMENDATION SYSTEMS

The submitted paper “Shot Scale Distribution on Art Films”, describes a framework that allows for extracting the second-based shot scales distribution (SSD) of a movie. The scale of shot, i.e. the apparent distance of the camera from the main subject of a scene, is one of the main stylistic and narrative functions of audiovisual products, conveying meaning and regulating the viewer’s emotional state. The statistical distribution of different shot scales in a film may be an important identifier of an individual film, an individual author, and of various narrative and affective functions of a film.
A particular shot is Over-the-shoulder (OtS). These types of shot in movies are able to convey a big dramatic tension on the viewers. In another branch of this research we proposed a methodology able to automatically detect this kind of shots by combining in a SVM learning scheme some state-of-the-art human presence detectors, with a set of saliency features based on colour and motion.

Foto_XXIX_Svanera

Curriculum: Telecommunication Engineering

Tutor: Sergio BENINI, Nicola ADAMI

email: m.svanera005@unibs.it

 

Link to the research group web page

Link to publication list

Link to personal page

 

linkedin facebook twitter