AI Paper Atlas

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

VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors

Li-wei H. Lehman, Benjamin E Moody, Harsh Deep, Feng Wu, Hasan Saeed, Lucas McCullum, Diane Perry, Tristan Struja, Qiao Li, Gari Clifford, Roger Mark

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 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 contrastive learning to 1-D CNNCNN · VTaC real-timeChallenge Score: 76.17 -> 79.07Improved
add contrastive learning to FCNFCN · VTaC real-timeChallenge Score: 80.08 -> 78.41Hurt
add contrastive learning to FCNFCN · VTaC retrospectiveChallenge Score: 75.84 -> 78.95Improved
add contrastive learning to CNNCNN · VTaC retrospectiveChallenge Score: 76.94 -> 78.85Improved
add 5 seconds of post-alarm data (retrospective vs real-time)CNN · VTaCChallenge Score: 76.17 -> 76.94No clear effect
add 5 seconds of post-alarm data (retrospective vs real-time)FCN+CL · VTaCChallenge Score: 78.41 -> 78.95Improved
add 5 seconds of post-alarm data (retrospective vs real-time)FCN · VTaCChallenge Score: 80.08 -> 75.84Hurt
replace rule-based method by FCNRule-based (Plesinger) · VTaC real-timeChallenge Score: 67.32 -> 80.08Improved
replace CNN by FCN as feature extractorCNN · VTaC real-timeAUC: 0.936 -> 0.949Improved
replace supervised CNN by Transformer encoderCNN · VTaC real-timeChallenge Score: 76.17 -> 62.73Hurt
use generative anomaly detection (Diffusion+CL) instead of supervised FCNFCN · VTaC real-timeChallenge Score: 80.08 -> 52.51Hurt
use autoencoder reconstruction loss (SAE) instead of plain MLPMLP · VTaC real-timeChallenge Score: 45.58 -> 68.77Improved

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