AI Paper Atlas

Research map / Video / Action recognition

Of Mice and Mates: Automated Classification and Modelling of Mouse Behaviour in Groups Using a Single Model Across Cages

Michael P. J. Camilleri, Rasneer Sonia Bains, Christopher K. I. Williams

IJCV 2024 · Video › Action recognition · approach: Disentangled action recognition · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use logistic regression instead of naive Bayes as observability classifierObservability classifier · ABODE val, WASTE=8%UNREL count: 470 -> 381Improved
use LFB backbone instead of STLT for behaviour classifierBehaviour classifier · ABODE validationmacro-F1: 0.36 -> 0.61Improved
use LFB backbone instead of STLTBehaviour classifier · ABODE validationnormalised log-likelihood: -1.04 -> -2.27Hurt
use LFB backbone instead of STLTBehaviour classifier · ABODE validationaccuracy: 0.73 -> 0.74No clear effect
add lighting enhancement techniques to behaviour classifier input (ablation)STLT and LFB · ABODEaccuracyNo clear effect
full ALM versus prior-probability baseline on behaviourALM · ABODE testmacro-F1: 0.09 -> 0.54Improved
full ALM versus prior-probability baseline on observabilityALM · ABODE testmacro-F1: 0.48 -> 0.61Improved
full ALM versus baseline on observability accuracyALM · ABODE testaccuracy: 0.93 -> 0.88Hurt
full ALM versus baseline on UNREL samplesALM · ABODE testUNREL count: 1506 -> 996Improved
full ALM versus baseline on WASTE samplesALM · ABODE testWASTE count: 0 -> 1558Hurt
use a single global GBM instead of per-cage models (ablation)GBM · IMADGE adultsnormalised log-likelihood: average drop is just 4.8%Hurt
increase number of latent states beyond 7 (ablation)GBM per-cage model · IMADGE adultsnormalised log-likelihoodNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy