AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization

Xuhai Xu, Han Zhang, Yasaman S Sefidgar, Yiyi Ren, Xin Liu, Woosuk Seo, Jennifer Brown, Kevin Scott Kuehn, Mike A Merrill, Paula S Nurius, Shwetak Patel, Tim Althoff and 4 more

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 13 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
add Reorder order-reconstruction self-supervised pretext task to 1D-CNN backboneERM-1dCNN · Leave-one-dataset-out depression detectionbalanced accuracy: 0.510 -> 0.547Improved
add Reorder pretext task to 1D-CNN backboneERM-1dCNN · Single dataset past/futurebalanced accuracy: 0.568 -> 0.626Improved
add Mixup augmentation to ERMERM-1dCNN · Leave-one-dataset-outbalanced accuracy: 0.510 -> 0.501No clear effect
use person as domain in DANN instead of datasetDANN · Single dataset past/futurebalanced accuracy: 0.526 -> 0.502Hurt
move from single-dataset to cross-dataset evaluationXu et al.-I · depression detectionbalanced accuracy: 0.691 -> 0.502Hurt
move from single-dataset to cross-dataset evaluationReorder · depression detectionbalanced accuracy: 0.626 -> 0.547Hurt
apply domain generalization algorithms (IRM, DANN, CSD, MLDG, MASF) over ERMERM-1dCNN · Leave-one-dataset-outbalanced accuracy: 0.510 vs 0.506-0.521No clear effect
normalize features per individual before domain classificationRandom Forest · Name-the-dataset classificationaccuracyMixed

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