activity
20212024
most citedSelf-Damaging Contrastive Learning

14 citations · 18 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL2024

Realtime, multimodal invasive ventilation risk monitoring using language models and BoXHED

Arash Pakbin, Aaron Su, Donald K. K. Lee +1

Objective: realtime monitoring of invasive ventilation (iV) in intensive care units (ICUs) plays a crucial role in ensuring prompt interventions and better patient outcomes. Howeve…

eess.SP20222 cited

DynImp: Dynamic Imputation for Wearable Sensing Data Through Sensory and Temporal Relatedness

Zepeng Huo, Taowei Ji, Yifei Liang +4

In wearable sensing applications, data is inevitable to be irregularly sampled or partially missing, which pose challenges for any downstream application. An unique aspect of weara…

cs.LG20222 cited

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition

Randy Ardywibowo, Shahin Boluki, Zhangyang Wang +3

In many machine learning tasks, input features with varying degrees of predictive capability are acquired at varying costs. In order to optimize the performance-cost trade-off, one…

cs.LG2021

Growing Representation Learning

Ryan King, Bobak Mortazavi

Machine learning continues to grow in popularity due to its ability to learn increasingly complex tasks. However, for many supervised models, the shift in a data distribution or th…

cs.CV202114 cited

Self-Damaging Contrastive Learning

Ziyu Jiang, Tianlong Chen, Bobak Mortazavi +1

The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervised training on real-world data applications. However, unlabeled data in realit…