Search Results for author: Xianyuan Liu

Found 6 papers, 1 papers with code

Channel-Temporal Attention for First-Person Video Domain Adaptation

no code implementations17 Aug 2021 Xianyuan Liu, Shuo Zhou, Tao Lei, Haiping Lu

Finally, we propose a Channel-Temporal Attention Network (CTAN) to integrate these blocks into existing architectures.

Action Recognition Unsupervised Domain Adaptation

Geometry-aware Line Graph Transformer Pre-training for Molecular Property Prediction

no code implementations1 Sep 2023 Peizhen Bai, Xianyuan Liu, Haiping Lu

Owing to the scarcity of labeled molecules, there has been growing interest in self-supervised learning methods that learn generalizable molecular representations from unlabeled data.

Molecular Property Prediction molecular representation +3

MeDSLIP: Medical Dual-Stream Language-Image Pre-training for Fine-grained Alignment

no code implementations15 Mar 2024 Wenrui Fan, Mohammod Naimul Islam Suvon, Shuo Zhou, Xianyuan Liu, Samer Alabed, Venet Osmani, Andrew Swift, Chen Chen, Haiping Lu

Moreover, a novel vision-language Prototypical Contr-astive Learning (ProtoCL) method is adopted in MeDSLIP to enhance the alignment within the anatomical and pathological streams.

Anatomy Contrastive Learning +1

Multimodal Variational Autoencoder for Low-cost Cardiac Hemodynamics Instability Detection

no code implementations20 Mar 2024 Mohammod N. I. Suvon, Prasun C. Tripathi, Wenrui Fan, Shuo Zhou, Xianyuan Liu, Samer Alabed, Venet Osmani, Andrew J. Swift, Chen Chen, Haiping Lu

In response to these limitations, we propose a novel multimodal variational autoencoder ($\text{CardioVAE}_\text{X, G}$) to integrate low-cost chest X-ray (CXR) and electrocardiogram (ECG) modalities with pre-training on a large unlabeled dataset.

Cannot find the paper you are looking for? You can Submit a new open access paper.