Imbalanced token distributions naturally exist in text documents, leadin...
General movement assessment (GMA) of infant movement videos (IMVs) is an...
The automatic generation of floorplans given user inputs has great poten...
Accurate infarct segmentation in non-contrast CT (NCCT) images is a cruc...
Class imbalance naturally exists when train and test models in different...
Classifying moral values in user-generated text from social media is cri...
Existing approaches to mitigate demographic biases evaluate on monolingu...
We present a novel framework named PlaneMVS for 3D plane reconstruction ...
Clinical notes in Electronic Health Records (EHR) present rich documente...
Augmented Reality (AR) is an emerging field ripe for experimentation,
es...
Depth-from-focus (DFF) is a technique that infers depth using the focus
...
Histopathological analysis is the present gold standard for precancerous...
Generative models have been applied in the medical imaging domain for va...
In an emergency room (ER) setting, the diagnosis of stroke is a common
c...
In many applications of computer graphics, art and design, it is desirab...
In this paper we propose ϵ-Consistent Mixup (ϵmu).
ϵmu is a data-based s...
Language varies across users and their interested fields in social media...
Synthesizing realistic medical images provides a feasible solution to th...
General movement assessment (GMA) of infant movement videos (IMVs) is an...
Existing research on fairness evaluation of document classification mode...
In this work, we propose to resolve the issue existing in current deep
l...
Advanced image synthesis methods can generate photo-realistic images for...
Supervised training of an automated medical image analysis system often
...
Building named entity recognition (NER) models for languages that do not...
Cervical intraepithelial neoplasia (CIN) grade of histopathology images ...
Objective: Ultrahigh-resolution optical coherence microscopy (OCM) has
r...
In this paper, we propose an Attentional Generative Adversarial Network
...
Although Generative Adversarial Networks (GANs) have shown remarkable su...
Inspired by classic generative adversarial networks (GAN), we propose a ...
Synthesizing high-quality images from text descriptions is a challenging...