Home /

Research

Showing 763 - 768 / 897

Learning Rolling Shutter Correction from Real Data without Camera Motion Assumption


Authors:  JiaweiMo, MdJahidulIslam, JunaedSattar....
Published date-11/05/2020
Tasks:  StructurefromMotion

Abstract: 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


Authors:  YeonSeonwoo, Ji-HoonKim, Jung-WooHa....
Published date-11/05/2020
Tasks:  Multi-TaskLearning, QuestionAnswering, ReadingComprehension

Abstract: 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


Authors:  HanZhu, JiangjiangZhao, YulingRen....
Published date-11/05/2020
Tasks:  DomainAdaptation, RobustSpeechRecognition, SpeechRecognition

Abstract: 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


Authors:  ZhengYuan, ZhengyunZhao, ShengYu....
Published date-11/05/2020
Tasks:  RelationClassification, SemanticSimilarity, SemanticTextualSimilarity, WordEmbeddings

Abstract: 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


Authors:  CamiloPestana, WeiLiu, DavidGlance....
Published date-11/05/2020
Tasks:  AdversarialAttack

Abstract: 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


Authors:  TingChen, LalaLi....
Published date-11/05/2020
Tasks:  ContrastiveLearning, DataAugmentation

Abstract: 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 …

Filter by

Categories

Tags