AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

MICE: Multi-animal Interaction Context Encoder — A Hierarchical Foundation Model for Mouse Behavior

Yen-Shuo Su, Weihan Li, Anqi Wu

NeurIPS 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MICE, a hierarchical self-supervised foundation model for mouse behavior from pose that encodes multi-animal social interactions.

Problem

Self-supervised pose models for mouse behavior encode each animal independently and thus fail to capture inherently multi-animal social behaviors such as aggression, courtship, mounting, and allogrooming.

Approach

A hierarchical encoder over multi-animal pose that models interaction context across animals, rather than encoding each animal in isolation, as a foundation model for mouse behavior.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add social encoder output to individual embedding (ablation)MICE · AdaptableSnail (combined)macro-F1 (%): 22.66 -> 26.76Improved
Add social encoder output to individual embedding (ablation)MICE · MABe22 (combined)macro-F1 (%): 67.85 -> 69.26Improved
Replace correct partners with mis-paired partners when training the social stage (ablation)MICE social stage · AdaptableSnailmacro-F1 (%): 26.76 -> 22.79Hurt
Remove partners from social stage (ablation)MICE social stage · CalMS21macro-F1 (%): 84.56 -> 81.00Hurt
Joint pretraining on six datasets instead of single-datasetMICE · AdaptableSnailmacro-F1 (%): 21.93 -> 26.76Improved
Joint pretraining on six datasets instead of single-datasetMICE · MouseLockboxmacro-F1 (%): 15.93 -> 13.68Hurt
Leave the target dataset out of pretraining (ablation)MICE · MABe22macro-F1 (%): 69.26 -> 64.28Hurt
Handle each mouse separately (MICE ind_cat) instead of stacking N animals (Progressive) (ablation)MICE individual encoder · MABe22 (combined)macro-F1 (%): 61.87 -> 67.85Improved
Widen attention windows across stages instead of multi-resolution supervision only (Multiscale) (ablation)MICE individual encoder · MABe22 (combined)macro-F1 (%): 63.68 -> 67.85Improved
Use MICE instead of hBehaveMAEunsupervised segmentation · 4 datasets avgARI (%): 31.32 -> 43.33Improved
Use MICE instead of hBehaveMAEunsupervised segmentation · 4 datasets avgBoundary-F1: 31.37 -> 31.57No 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