Detailed behavioral analysis across animal species: spatial context in trainable detectors of behavioral acts
Received: 08 Oct 2026 Revised: 20 Oct 2026 Accepted: 10 Nov 2026
Published: 2026, vol. 30, issue 4, pp. 535–538
Abstract
We integrated a trainable rearing detector into the Sphynx behavioral-analysis platform, combining kinematic features with spatial information from arena annotation. On a public dataset, against the consensus of two experts, the detector achieved frame-level F1 = 0.84, compared with 0.54 for the original rule-based detector and 0.85 for the third expert. Spatial features contributed substantially to classification performance.
Keywords: behavioral analysis, pose estimation, behavioral annotation, gradient boosting.
BibTeX
@article{IS-Plusnin-Ivanova-Ivashkina-Pospelov-Rogozhnikova-Savelev-Toropova-Anokhin2026,
author = {Plusnin, Viktor Vladimirovich and Ivanova, Anna Andreevna and Ivashkina, Olga Igorevna and Pospelov, Nikita Andreevich and Rogozhnikova, Olga Sergeevna and Savelev, Nikita Pavlovich and Toropova, Ksenia Aleksandrovna and Anokhin, Konstantin Vladimirovich},
title = {{Detailed behavioral analysis across animal species: spatial context in trainable detectors of behavioral acts}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {535--538},
}
AMSBIB
\Bibitem{IS-Plusnin-Ivanova-Ivashkina-Pospelov-Rogozhnikova-Savelev-Toropova-Anokhin2026}
\by V.\,V.~Plusnin, A.\,A.~Ivanova, O.\,I.~Ivashkina, N.\,A.~Pospelov, O.\,S.~Rogozhnikova, N.\,P.~Savelev, K.\,A.~Toropova, K.\,V.~Anokhin
\paper Detailed behavioral analysis across animal species: spatial context in trainable detectors of behavioral acts
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 535--538
\lang In Russian
RU