http://orcid.org/0000-0002-7347-1685
Reader Comments
Post a new comment on this article
Post Your Discussion Comment
Please follow our guidelines for comments and review our competing interests policy. Comments that do not conform to our guidelines will be promptly removed and the user account disabled. The following must be avoided:
- Remarks that could be interpreted as allegations of misconduct
- Unsupported assertions or statements
- Inflammatory or insulting language
Thank You!
Thank you for taking the time to flag this posting; we review flagged postings on a regular basis.
closeReference [25]
Posted by GonzaloPolavieja on 31 Oct 2018 at 17:25 GMT
The authors of this paper say 'However, the most relevant study, which involves organism re-identification, only does so over short (<1 min) time frames (IDTracker2.0 [25]). ' Let me note two mistakes: Reference [25] names its system as idtracker.ai, not IDTracker2.0. Also, the illustrative videos used in [25] are 10min long: there is no 1 min restriction.
RE: Reference [25]
jschneider102 replied to GonzaloPolavieja on 28 Nov 2018 at 20:18 GMT
We apologize for referring to idTracker.ai as idTracker2.0 (as in the second generation of idTracker). Additionally, we apologize for any miscommunication in that yes, idTracker.ai can be used on longer videos, and was published with videos on the order of minutes, but a key step in the method's overall accuracy seems to be to stitch together fragments that are separated by relatively few frames (crossing frames) and double checking that against realistic motion models. Ultimately, this study is interested in data separated by days.