Skip to content

Pose-assisted behavior analysis

BehaviorScope-X#

Turn animal-behavior recordings into reviewable temporal predictions while keeping annotation, data splits, pose features, model training, and evaluation visible at every step.

Desktop annotation 3 pose paths Explicit data splits Reviewable outputs
RESEARCH WORKFLOW
01
CURATElabel bouts · assign splits · quality control
02
TRAINbuild pose cache · train · validate · test

03
INTERPRETpredictions · ethograms · review videos

EVIDENCE READY FOR REVIEW

One interface, three pose paths#

Choose the representation that matches your study. Every path returns to the same temporal behavior workflow, so annotation, training, held-out testing, and output review remain comparable.

01 / DIRECT

YOLO-pose

Build caches, train the classifier, run inference, and create annotated review videos from the GUI-centered path.

Open workflow →
02 / COMPARISON

MobileNetV3

Use a controlled pose-and-backbone descriptor path with shared temporal modeling and evaluation.

Open workflow →

Research workflow#

The map follows the primary path from research recordings to evidence you can inspect. Open it separately for pan, zoom, and a larger canvas.

BEHAVIORSCOPE-X / END-TO-END Open interactive map ↗

Workflow map generated with Archify, an MIT-licensed interactive diagram renderer. Special thanks to Shaun Andrade for introducing the project to Archify and for assisting with pilot studies and architecture testing during the early builds of BehaviorScope. See Acknowledgments.

Keep the research decisions visible#

CURATE ONCE

Annotate bouts, record review state, and keep train, validation, held-out test, and excluded videos explicit.

TRAIN DELIBERATELY

Select a supported pose path, build compatible caches, and evaluate the temporal classifier on held-out data.

REVIEW THE EVIDENCE

Inspect prediction tables, ethograms, bout summaries, metrics, and optional annotated videos before interpretation.

Special thanks#

BehaviorScope-X gratefully acknowledges Shaun Andrade, an undergraduate Computer Science major at the University of Maryland, Baltimore County (UMBC), for assisting with pilot studies and architecture testing during the early builds of the BehaviorScope project. Shaun also introduced the project to Archify, the workflow-diagram repository used to generate this site's interactive research map.

Read the full acknowledgments

Start with the guided desktop workflow#

Install the application, annotate a first video, and follow one documented pose path through model training and output review.