From pose to behavior: SABER integrates identity-resolved multi-animal pose tracking with language-model-based behavioral factor discovery
- 1Southern Medical University
Abstract
Quantifying social behavior requires accurately assigning posture and actions to individual animals, but close contact, occlusion, and identity switches often hinder this. Meanwhile, current behavioral recognition pipelines still lack stable predictive accuracy, especially when using a unified multi class model. Here we developed SABER, a locally deployable framework that couples multi animal pose estimation with identity preserving tracking, interpretable behavioral factor mining, and multiscale temporal behavior prediction from a single overhead video stream. Across spontaneous social interaction, mating, aggression, and four mouse recordings, SABER improved pose-estimation accuracy and tracking continuity relative to comparator pipelines. Its behavioral factor mining procedure identified interpretable kinematic, postural, and social descriptors, and temporal integration refined behavioral category classification. SABER offers an intuitive, open source interface to facilitate use. Applied to social defeat stress mice, SABER detected reduced approach behavior and a multivariate behavioral profile that distinguished depression susceptible from control animals. SABER outputs could also be synchronized with miniscope calcium recordings, enabling joint analysis of behavioral states and neuronal population activity. SABER therefore provides an accessible, identity resolved route from single view social interaction video to behavioral phenotyping and brain behavior analysis.
Related
- VirtualSkin integrates skin-cell identity with intervention-response prediction
- Spontaneous behavior predicts colony membership, individual identity, and rank in naked mole-rat societies
- Genome-resolved discovery of Candidatus Vitaminotrophota reveals carbon fixation and multi-vitamin biosynthetic potential in hot springs
- Impaired Control Symptoms in Alcohol Use Disorder Show Convergent Associations Across Behavioral and Neural Markers of Inhibitory Control and Drinking Behavior
- Probabilistic model discovery reveals distinct constitutive behavior of kidney cortex and medulla
BibTeX
@misc{zheng2026from,
title = {{From pose to behavior: SABER integrates identity-resolved multi-animal pose tracking with language-model-based behavioral factor discovery}},
author = {J. Zheng and C. Peng and S.-Y. Zhang and J. Wang and W.-N. Zhou and H.-M. Xue and T.-Q. Cai and Y.-W. Li and Z. Jiang and Y. Tan and X.-D. Sun},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.749007},
url = {https://www.biorxiv.org/content/10.64898/2026.09.02.749007v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - From pose to behavior: SABER integrates identity-resolved multi-animal pose tracking with language-model-based behavioral factor discovery
AU - J. Zheng
AU - C. Peng
AU - S.-Y. Zhang
AU - J. Wang
AU - W.-N. Zhou
AU - H.-M. Xue
AU - T.-Q. Cai
AU - Y.-W. Li
AU - Z. Jiang
AU - Y. Tan
AU - X.-D. Sun
PY - 2026
DA - 2026/09/02
PB - bioRxiv
DO - 10.64898/2026.09.02.749007
UR - https://www.biorxiv.org/content/10.64898/2026.09.02.749007v1
AB - Quantifying social behavior requires accurately assigning posture and actions to individual animals, but close contact, occlusion, and identity switches often hinder this. Meanwhile, current behavioral recognition pipelines still lack stable predictive accuracy, especially when using a unified multi class model. Here we developed SABER, a locally deployable framework that couples multi animal pose estimation with identity preserving tracking, interpretable behavioral factor mining, and multiscale temporal behavior prediction from a single overhead video stream. Across spontaneous social interaction, mating, aggression, and four mouse recordings, SABER improved pose-estimation accuracy and tracking continuity relative to comparator pipelines. Its behavioral factor mining procedure identified interpretable kinematic, postural, and social descriptors, and temporal integration refined behavioral category classification. SABER offers an intuitive, open source interface to facilitate use. Applied to social defeat stress mice, SABER detected reduced approach behavior and a multivariate behavioral profile that distinguished depression susceptible from control animals. SABER outputs could also be synchronized with miniscope calcium recordings, enabling joint analysis of behavioral states and neuronal population activity. SABER therefore provides an accessible, identity resolved route from single view social interaction video to behavioral phenotyping and brain behavior analysis.
ER -