Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Commenti Review1 #14

Open
mzanella opened this issue Oct 12, 2017 · 2 comments
Open

Commenti Review1 #14

mzanella opened this issue Oct 12, 2017 · 2 comments

Comments

@mzanella
Copy link
Member

mzanella commented Oct 12, 2017

The paper is very interesting. My only concern is about the evaluation stage. I think it is
very important to describe the subjects of the pictures used to evaluate the system. 
Indeed, authors only say that they asked participants to take 5 pictures, resulting in a 
benchmark of 150 pictures.
The knowledge of the characteristics of these pictures is fundamental to understand the 
obtained results. For instance, number of photos with text, number of photos with people, 
outdoor vs. indoor, etc. This would allow users to better appreciate the contribution.
@mzanella
Copy link
Member Author

Io propongo di spiegare che noi abbiamo tutte le foto e tutti i tag, ma che abbiamo lasciato come future work ricontrollare le foto e che non abbiamo cercato di proporlo come gioco per coinvolgere più gente possibile

@tfederico
Copy link
Contributor

I think it is very important to describe the subjects of the pictures used to evaluate the system. Indeed, authors only say that they asked participants to take 5 pictures, resulting in a benchmark of 150 pictures. The knowledge of the characteristics of these pictures is fundamental to understand the obtained results.

Qui penso che possiamo cavarcela dicendo che non ci sono stati particolari vincoli sui soggetti

For instance, number of photos with text, number of photos with people, outdoor vs. indoor, etc. This would allow users to better appreciate the contribution.

Per indoor vs outdoor potrebbe bastare un parsing dei tag, tendenzialmente ce n'erano diversi con il tag indoor o simili, per cui con uno script possiamo contarli e fare in modo che ci segnali le foto da controllare manualmente

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants