Skeleton accuracy for test data subgroups and types of errors.

<p>(A) Root mean square deviation between model predictions and test data for ‘easy’ cases which were skeletonized by Tierpsy. By construction the number of failed predictions for Tierpsy is zero. (B) The same as A but using manually annotated skeletons as the test data. These data have more d...

Full description

Saved in:

Bibliographic Details
Main Author:	Weheliye H. Weheliye (22022140) (author)
Other Authors:	Javier Rodriguez (844971) (author), Luigi Feriani (7886267) (author), Avelino Javer (5622347) (author), Virginie Uhlmann (3576008) (author), André E. X. Brown (8985398) (author)
Published:	2025
Subjects:	Biochemistry Genetics Biotechnology Evolutionary Biology Immunology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified thin bacterial lawns still significant room reducing failure rates deeptangle algorithm developed deep learning approaches resolution posture tracking throughput worm imaging previously inaccessible behaviours outperforms existing methods free worm trajectories swimming worms using tracking crawling worms div >< p based tracking worm interactions involve worm complex behaviours classic methods worms overlap uniform backgrounds tierpsy tracker specifically collected phenotypic screens noise ratio less likely intersecting postures elegans </ drug screening difficult cases complex environments coils ). challenging conditions
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Skeleton accuracy for test data subgroups and types of errors.

Similar Items