Home /

Research

Showing 787 - 792 / 897

MK-SQuIT: Synthesizing Questions using Iterative Template-filling


Authors:  BenjaminA.Spiegel, VincentCheong, JamesE.Kaplan....
Published date-11/04/2020
Tasks:  MachineTranslation

Abstract: The aim of this work is to create a framework for synthetically generating question/query pairs with as little human input as possible. These datasets can be used to train machine …

Learning and Evaluating Representations for Deep One-class Classification


Authors:  KihyukSohn, Chun-LiangLi, JinsungYoon....
Published date-11/04/2020
Tasks:  ContrastiveLearning, DataAugmentation, DecisionMaking, One-classclassifier

Abstract: We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows …

Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment


Authors:  QiKuang, XinJin, QinpingZhao....
Published date-11/04/2020
Tasks:  VideoClassification

Abstract: Despite the growing number of unmanned aerial vehicles (UAVs) and aerial videos, there is a paucity of studies focusing on the aesthetics of aerial videos that can provide valuable information …

Deoscillated Graph Collaborative Filtering


Authors:  ZhiweiLiu, LinMeng, JiaweiZhang....
Published date-11/04/2020
Tasks:  RecommendationSystems

Abstract: Collaborative Filtering (CF) signals are crucial for a Recommender System~(RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modelled …

Re-Assessing the "Classify and Count" Quantification Method


Authors:  AlejandroMoreo, FabrizioSebastiani....
Published date-11/04/2020
Tasks:  SentimentAnalysis

Abstract: Learning to quantify (a.k.a.\ quantification) is a task concerned with training unbiased estimators of class prevalence via supervised learning. This task originated with the observation that "Classify and Count" (CC), …

Mutual Modality Learning for Video Action Classification


Authors:  StepanKomkov, MaksimDzabraev, AleksandrPetiushko....
Published date-11/04/2020
Tasks:  ActionClassification, ActionClassification, ActionRecognition, OpticalFlowEstimation

Abstract: The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different …

Filter by

Categories

Tags