Home /

Research

Showing 667 - 672 / 897

CapWAP: Captioning with a Purpose


Authors:  AdamFisch, KentonLee, Ming-WeiChang....
Published date-11/09/2020
Tasks:  ImageCaptioning, QuestionAnswering, VisualQuestionAnswering

Abstract: The traditional image captioning task uses generic reference captions to provide textual information about images. Different user populations, however, will care about different visual aspects of images. In this paper, …

MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem


Authors:  HieuTrongPhung, AnhTuanVu, TungDinhNguyen....
Published date-11/09/2020
Tasks:  DataAugmentation, ExtractiveTagsSummarization, Self-SupervisedLearning, UnsupervisedPre-training

Abstract: In this work, we study a new image annotation task named Extractive Tags Summarization (ETS). The goal is to extract important tags from the context lying in an image and …

Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling


Authors:  NathanGrinsztajn, OlivierBeaumont, EmmanuelJeannot....
Published date-11/09/2020
Tasks:  CombinatorialOptimization

Abstract: In practice, it is quite common to face combinatorial optimization problems which contain uncertainty along with non-determinism and dynamicity. These three properties call for appropriate algorithms; reinforcement learning (RL) is …

Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment


Authors:  GovindaM.Kamath, TavorZ.Baharav, IlanShomorony....
Published date-11/09/2020

Abstract: Pairwise alignment of DNA sequencing data is a ubiquitous task in bioinformatics and typically represents a heavy computational burden. State-of-the-art approaches to speed up this task use hashing to identify …

ConFuse: Convolutional Transform Learning Fusion Framework For Multi-Channel Data Analysis


Authors:  PoojaGupta, JyotiMaggu, AngshulMajumdar....
Published date-11/09/2020
Tasks:  TimeSeries, TimeSeriesAnalysis

Abstract: This work addresses the problem of analyzing multi-channel time series data %. In this paper, we by proposing an unsupervised fusion framework based on %the recently proposed convolutional transform learning. …

PAMS: Quantized Super-Resolution via Parameterized Max Scale


Authors:  HuixiaLi, ChenqianYan, ShaohuiLin....
Published date-11/09/2020
Tasks:  Quantization, SuperResolution, Super-Resolution, TransferLearning

Abstract: Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited …

Filter by

Categories

Tags