Home /
Research
Showing 763 - 768 / 897
Learning Rolling Shutter Correction from Real Data without Camera Motion Assumption
JiaweiMo, MdJahidulIslam, JunaedSattar....
Published date-11/05/2020
StructurefromMotion
The rolling shutter mechanism in modern cameras generates distortions as the images are formed on the sensor through a row-by-row readout process; this is highly undesirable for photography and vision-based …
Context-Aware Answer Extraction in Question Answering
YeonSeonwoo, Ji-HoonKim, Jung-WooHa....
Published date-11/05/2020
Multi-TaskLearning, QuestionAnswering, ReadingComprehension
Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text …
Domain Adaptation Using Class Similarity for Robust Speech Recognition
HanZhu, JiangjiangZhao, YulingRen....
Published date-11/05/2020
DomainAdaptation, RobustSpeechRecognition, SpeechRecognition
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target …
CODER: Knowledge infused cross-lingual medical term embedding for term normalization
ZhengYuan, ZhengyunZhao, ShengYu....
Published date-11/05/2020
RelationClassification, SemanticSimilarity, SemanticTextualSimilarity, WordEmbeddings
We propose a novel medical term embedding method named CODER, which stands for mediCal knOwledge embeDded tErm Representation. CODER is designed for medical term normalization by providing close vector representations …
Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty
CamiloPestana, WeiLiu, DavidGlance....
Published date-11/05/2020
AdversarialAttack
Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the reported dataset than …
Intriguing Properties of Contrastive Losses
TingChen, LalaLi....
Published date-11/05/2020
ContrastiveLearning, DataAugmentation
Contrastive loss and its variants have become very popular recently for learning visual representations without supervision. In this work, we first generalize the standard contrastive loss based on cross entropy …