Open source image captioning project may be of interest:
Perhaps ideal for providing automatic captions to be corrected by the crowd
or professional curators.
An evaluation on arxiv gives examples:
Not completely accurate but they look like a good starting point.
---------- Forwarded message ----------
From: Dario Taraborelli <[log in to unmask]>
Date: Tue, Sep 27, 2016 at 4:08 PM
Subject: Re: [Wiki-research-l] Google open source research on automatic
To: Research into Wikimedia content and communities <
[log in to unmask]>
Cc: Wikimedia Foundation Multimedia Team <[log in to unmask]>,
Application of Artificial Intelligence and other advanced computing
strategies to Wikimedia Projects <[log in to unmask]>
I forwarded this separately to internally at WMF a few days ago. Clearly –
before thinking of building workflows for human contributors to generate
captions or rich descriptors of media files in Commons – we should look at
what's available in terms of off-the-shelf machine learning services and
#1 rule of sane citizen science/crowdsourcing projects: don't ask humans to
perform tedious tasks machines are pretty good at, get humans to curate
inputs and outputs of machines instead.
On Mon, Sep 26, 2016 at 5:55 PM, Pine W <[log in to unmask]> wrote:
> Perhaps of interest: "...We’re making the latest version of our image
> captioning system available as an open source model in TensorFlow."
> Wiki-research-l mailing list
> [log in to unmask]
*Dario Taraborelli *Head of Research, Wikimedia Foundation
wikimediafoundation.org • nitens.org • @readermeter
Wiki-research-l mailing list
[log in to unmask]