Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/120256
Title: Deep learning for non-verbal personality analysis
Author: Pérez Quintana, Marc
Director: Escalera Guerrero, Sergio
Keywords: Visió per ordinador
Reconeixement de formes (Informàtica)
Programari
Treballs de fi de grau
Personalitat
Parla
Computer vision
Pattern recognition systems
Computer software
Bachelor's thesis
Personality
Speech
Issue Date: 22-Jun-2017
Abstract: [en] In this project, we present an up-to-date review of existing computer-vision based visual and multimodal approaches for apparent personality trait recognition and analysis. We describe main works and discuss their main features as well as future lines of research in the field. Current datasets and challenges organized to push the research in the field are also discussed. We also show which visual (face, body, and background regions) and audio features (speech properties) current CNN-based methods learn in order to discriminate among the Big Five personality traits in short video clips. In addition, we present a new web-based application users can interact with, in order to receive automatic feedback about their apparent personality and relating it to five different job profiles. This application was presented as a demonstrator at NIPS 2016.
Note: Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2016, Director: Sergio Escalera Guerrero
URI: http://hdl.handle.net/2445/120256
Appears in Collections:Treballs Finals de Grau (TFG) - Enginyeria Informàtica

Files in This Item:
File Description SizeFormat 
resum.pdfResum1.05 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons