[CogSci] seeking letters of collaboration for automatic pupillometry software

[Samuel Mehr]

Dear CogSci,

My lab has been working on new software for automatic post-hoc pupillometry
measurement that takes as input a video of a study participant and produces
measures of relative changes in pupil size over the course of the video.
We've already made an MTurk tool for manual annotation of pupil size, which
is used for a secondary analysis in this preprint
https://psyarxiv.com/xcj52 (in
infants, pupils are less dilated during soothing lullabies than exciting
other songs). An automatic version, where MTurk workers are replaced with a
neural net, is giving promising results.

We are applying for some NSF funding to build a fully automatic version,
with an eye toward making the method feasible with webcam videos of the
sort that "participate-from-home" studies will produce. It should work in
adult, child, and infant participants. As part of the proposal, we plan to
release a private beta version of the software to a group of labs who will
try out the method on their own participant videos.

I'm writing to ask if you would be interested in being a beta tester, and
if so, to ask that you submit a Letter of Collaboration that we can include
in our NSF application.

The only expectation of beta testers is to do a pupillometry analysis of
your participant videos (in any type of experiment) using the beta software
and to let us know how it went: we would just ask for some feedback on the
software so that we can improve it, and possibly some summary statistics
describing the results (e.g., main effect size; comparison to other
measures you happened to use, like psychophysiology, or convergent validity
with pupillometry measured with an eye tracker).

*If you are interested in being a beta tester, please send an NSF-style
Letter of Collaboration to musiclab+pupils at g.harvard.edu
<musiclab%2Bpupils at g.harvard.edu>*. It needs to be a pdf, on your
letterhead, and signed, with the following text as the body of the letter:

> If the proposal submitted by Dr. Samuel Mehr entitled "Post-hoc
> pupillometry" is selected for funding by NSF, it is my intent to
> collaborate and/or commit resources as detailed in the Project Description
> or the Facilities, Equipment and Other Resources section of the proposal.


Happy to chat with anyone about this off-list and thanks in advance to
those who are interested in beta testing!

best,
Sam

--
Samuel Mehr
Department of Psychology
Harvard University
*Be a citizen scientist at themusiclab.org <https://themusiclab.org/>!*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cognitivesciencesociety.org/pipermail/announcements-cognitivesciencesociety.org/attachments/20200622/ed48e60d/attachment.html>