| KEYWORD |
GR-09 - GRAphics and INtelligent Systems - GRAINS
Theses at Politecnico
Deep convolutional neural networks for object and scene description
Reference persons FABRIZIO LAMBERTI
Research Groups GR-09 - GRAphics and INtelligent Systems - GRAINS
Description Deep convolutional neural networks are the state of the art for object recognition and classification. The goal of this thesis proposal is to develop deep neural models for object and scene characterization in natural scene images. The student will implement models to classify the type of scene of an image (indoor vs. outdoor, etc.), the attributes of objects contained in an image (color, shape, etc.) or predict actions and relationship between objects. The student is expected to understand, implement and train models recently proposed in the literature. Skills possessed or to acquire: programming skills (Python, Keras/Tensorflow or other deep learning framework); precision, attention to details and analytical skills.
See also http://grains.polito.it/work.php
Deadline 13/02/2019
PROPONI LA TUA CANDIDATURA