Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension

Kavli Affiliate: Cheng Peng | Authors: Cheng Peng, Xi Yang, Zehao Yu, Jiang Bian, William R. Hogan, Yonghui Wu | Summary: Objective: To develop a natural language processing system that solves both clinical concept extraction and relation extraction in a unified prompt-based machine reading comprehension (MRC) architecture with good generalizability for cross-institution applications. Methods: We […]


Continue.. Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension

DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images, which fails existing algorithms. To handle this, we propose a new RGB-NIR fusion algorithm called Dark […]


Continue.. DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

Normal-guided Garment UV Prediction for Human Re-texturing

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Clothes undergo complex geometric deformations, which lead to appearance changes. To edit human videos in a physically plausible way, a texture map must take into account not only the garment transformation induced by the body movements and clothes fitting, but […]


Continue.. Normal-guided Garment UV Prediction for Human Re-texturing

Boosting Open-Set Domain Adaptation with Threshold Self-Tuning and Cross-Domain Mixup

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Open-set domain adaptation (OSDA) aims to not only recognize target samples belonging to common classes shared by source and target domains but also perceive unknown class samples. Existing OSDA methods suffer from two obstacles. Firstly, a tedious process of manually […]


Continue.. Boosting Open-Set Domain Adaptation with Threshold Self-Tuning and Cross-Domain Mixup

Verus: Verifying Rust Programs using Linear Ghost Types (extended version)

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: The Rust programming language provides a powerful type system that checks linearity and borrowing, allowing code to safely manipulate memory without garbage collection and making Rust ideal for developing low-level, high-assurance systems. For such systems, formal verification can be useful […]


Continue.. Verus: Verifying Rust Programs using Linear Ghost Types (extended version)

DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation

Kavli Affiliate: Zheng Zhu | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that reformulates monocular depth estimation […]


Continue.. DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation

DiM: Distilling Dataset into Generative Model

Kavli Affiliate: Zheng Zhu | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider application: i). the synthetic images perform poorly on large […]


Continue.. DiM: Distilling Dataset into Generative Model

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

Kavli Affiliate: Zheng Zhu | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Semantic occupancy perception is essential for autonomous driving, as automated vehicles require a fine-grained perception of the 3D urban structures. However, existing relevant benchmarks lack diversity in urban scenes, and they only evaluate front-view predictions. Towards a comprehensive benchmarking of […]


Continue.. OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Various optimal gradient-based algorithms have been developed for smooth nonconvex optimization. However, many nonconvex machine learning problems do not belong to the class of smooth functions and therefore the existing algorithms are sub-optimal. Instead, these problems have been shown to […]


Continue.. Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization

DTAmetasa: an R shiny application for meta-analysis of diagnostic test accuracy and sensitivity analysis of publication bias

Kavli Affiliate: Yi Zhou | First 5 Authors: [#item_custom_name[1]], [#item_custom_name[2]], [#item_custom_name[3]], [#item_custom_name[4]], [#item_custom_name[5]] | Summary: Meta-analysis of diagnostic test accuracy (DTA) is the powerful statistical method for synthesizing and evaluating the diagnostic capacity of the medical tests and has been extensively used by clinical physicians and healthcare decision-makers. However, publication bias (PB) threatens the validity […]


Continue.. DTAmetasa: an R shiny application for meta-analysis of diagnostic test accuracy and sensitivity analysis of publication bias