An artificial intelligence platform for the multihospital collaborative management of congenital cataracts
…, J Chen, J Li, Q Cao, D Wang, X Liu, W Chen… - Nature biomedical …, 2017 - nature.com
Using artificial intelligence (AI) to prevent and treat diseases is an ultimate goal in computational
medicine. Although AI has been developed for screening and assisted decision-making …
medicine. Although AI has been developed for screening and assisted decision-making …
Deep-based ingredient recognition for cooking recipe retrieval
Retrieving recipes corresponding to given dish pictures facilitates the estimation of nutrition
facts, which is crucial to various health relevant applications. The current approaches mostly …
facts, which is crucial to various health relevant applications. The current approaches mostly …
Clean-label backdoor attacks on video recognition models
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor
triggers in DNNs by poisoning training data. A backdoored model behaves normally on …
triggers in DNNs by poisoning training data. A backdoored model behaves normally on …
Probabilistic forecasting of the masses and radii of other worlds
Mass and radius are two of the most fundamental properties of an astronomical object.
Increasingly, new planet discoveries are being announced with a measurement of one of these …
Increasingly, new planet discoveries are being announced with a measurement of one of these …
[HTML][HTML] Vedolizumab versus adalimumab for moderate-to-severe ulcerative colitis
…, L Jonaitis, B Abhyankar, J Chen… - … England Journal of …, 2019 - Mass Medical Soc
Background Biologic therapies are widely used in patients with ulcerative colitis. Head-to-head
trials of these therapies in patients with inflammatory bowel disease are lacking. Methods …
trials of these therapies in patients with inflammatory bowel disease are lacking. Methods …
Balanced contrastive learning for long-tailed visual recognition
Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples. …
occupy most of the data while most minority categories contain a limited number of samples. …
Dual-path transformer network: Direct context-aware modeling for end-to-end monaural speech separation
The dominant speech separation models are based on complex recurrent or convolution
neural network that model speech sequences indirectly conditioning on context, such as …
neural network that model speech sequences indirectly conditioning on context, such as …
Wilddeepfake: A challenging real-world dataset for deepfake detection
In recent years, the abuse of a face swap technique called deepfake has raised enormous
public concerns. So far, a large number of deepfake videos (known as "deepfakes") have …
public concerns. So far, a large number of deepfake videos (known as "deepfakes") have …
M2tr: Multi-modal multi-scale transformers for deepfake detection
The widespread dissemination of Deepfakes demands effective approaches that can detect
perceptually convincing forged images. In this paper, we aim to capture the subtle …
perceptually convincing forged images. In this paper, we aim to capture the subtle …
Therapeutic experience from 1428 patients with pediatric tracheobronchial foreign body
…, ZG Fugao, S Yan, ZK Niankai, CJ Jingjing - Journal of pediatric …, 2008 - Elsevier
PURPOSE: Tracheobronchial foreign body (TFB) aspiration is a life-threatening emergency
for children. Knowing how to reduce the incidence of complications and mortality during the …
for children. Knowing how to reduce the incidence of complications and mortality during the …