KEYWORD |
Analyzing gender bias in Close Ups from Movies
keywords COMPUTER VISION, DEEP LEARNING, GENDER-BIAS
Reference persons TANIA CERQUITELLI
External reference persons BARTOLOMEO VACCHETTI
Research Groups DAUIN - GR-04 - DATABASE AND DATA MINING GROUP - DBDM
Thesis type SPERIMENTALE APPLICATA
Description The close-up is a type of shot that tightly frames a person. Film Theories have long proposed that the vertical camera angle influences how the scene and character are interpreted. If the character is framed from below, its authority is increased, while if it is framed from above, its authority decreases. The aim of this project is to analyze gender bias in films by analyzing what kind of correlation there is between gender and vertical camera angle. The student will:
+ develop a solution to estimate the camera angle
+ create a dataset with close-ups and different camera angles
+ analyze the results
See also https://smartdata.polito.it/members/bartolomeo-vacchetti/
Required skills Data science methodologies, python, image processing
Deadline 28/11/2023
PROPONI LA TUA CANDIDATURA