AI Paper Atlas

Research map / Video / Video segmentation and tracking

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

Jennifer J. Sun, Markus Marks, Andrew Wesley Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Sebastian Oleszko, Zachary Partridge, Milan Peelman, Alice Robie and 11 more

ICML 2023 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 12 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
Pretraining on Kinetics400 (rhoBYOL) instead of training on animal data (ablation)rhoBYOL · Mouse Triplet and Ant Beetle manual behaviorsF1 manual behaviors: 0.2688 vs 0.1832 (mouse); 0.6967 vs 0.6178 (beetle)Improved
Pretraining on Kinetics400 for MAE and MaskFeat (ablation)MAE, MaskFeat · Mouse and beetle downstream tasksMSE and F1 across tasksHurt
Cube (spatiotemporal random) masking instead of frame or tube masking in MAE (ablation)MAE · Mouse TripletTime of Day MSE / Manual Behaviors F1: cube .0816 vs tube .0835 vs frame .0886 (time of day); cube .2309 vs tube .2249 vs frame .2020 (behaviors)Mixed
Cube masking instead of frame or tube masking in MAE (ablation)MAE · Ant BeetleDuration MSE / Manual Behaviors F1: cube .0283 vs frame .0301, tube .0285 (duration); cube .6444 vs frame .6169, tube .5802 (behaviors)Improved
Increasing number of positives in rhoBYOL from 2 to 4 (or 3 for beetle) (ablation)rhoBYOL · Mouse Triplet and Ant BeetleF1 / MSE across tasks: mouse best at 2 or 4 depending on task; beetle best at 3 positivesMixed
Adding hand-crafted keypoint features and SimCLR to pretrained BEiT (community method)Mouse video challenge method · Mouse TripletExp. Day MSE and Strain F1: Exp. Day .0093 vs .0102 for MAEImproved
Trajectory-only methods instead of video for miceTrajectory-BERT · Mouse TripletStrain F1: .7202 vs 1.0000 for MAEHurt
Perceiver masked modeling on trajectories vs GPT-style next-frame prediction for fliesFly group trajectory methods · Fly Group manual behaviorsF1 manual behaviors: Trajectory-GPT .246 vs Trajectory-Perceiver .197 on manual behaviors; Perceiver better on fly type and female vs maleMixed
Community hand-crafted features and pretrained-model features versus pure self-supervised video modelsCommunity methods on manual behaviors · Mouse and beetle manual behaviorsF1 manual behaviors: Vision Ensemble .2750 mouse; Multimodal MoCo/SimCLR .7299 beetle vs best SSL .2688 / .6967Improved

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