activity
20222024
most citedSecuring Deep Generative Models with Universal Adversarial Signature

2 citations · 4 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG2024

Deep State-Space Generative Model For Correlated Time-to-Event Predictions

Yuan Xue, Denny Zhou, Nan Du +4

Capturing the inter-dependencies among multiple types of clinically-critical events is critical not only to accurate future event prediction, but also to better treatment planning.…

cs.LG2024

Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction

Yuan Xue, Nan Du, Anne Mottram +2

We propose to meta-learn an a self-supervised patient trajectory forecast learning rule by meta-training on a meta-objective that directly optimizes the utility of the patient repr…

cs.LG2024

Discover Your Neighbors: Advanced Stable Test-Time Adaptation in Dynamic World

Qinting Jiang, Chuyang Ye, Dongyan Wei +3

Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality o…

cs.CV2023

3D-Aware Talking-Head Video Motion Transfer

Haomiao Ni, Jiachen Liu, Yuan Xue +1

Motion transfer of talking-head videos involves generating a new video with the appearance of a subject video and the motion pattern of a driving video. Current methodologies prima…

eess.IV2023

Efficient Annotation for Medical Image Analysis: A One-Pass Selective Annotation Approach

Yuli Wang, Peiyu Duan, Zhangxing Bian +2

Annotating biomedical images for supervised learning is a complex and labor-intensive task due to data diversity and its intricate nature. In this paper, we propose an innovative m…

cs.CV20231 cited

Synthetic Augmentation with Large-scale Unconditional Pre-training

Jiarong Ye, Haomiao Ni, Peng Jin +2

Deep learning based medical image recognition systems often require a substantial amount of training data with expert annotations, which can be expensive and time-consuming to obta…