Home /
Research
Showing 667 - 672 / 897
CapWAP: Captioning with a Purpose
AdamFisch, KentonLee, Ming-WeiChang....
Published date-11/09/2020
ImageCaptioning, QuestionAnswering, VisualQuestionAnswering
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
HieuTrongPhung, AnhTuanVu, TungDinhNguyen....
Published date-11/09/2020
DataAugmentation, ExtractiveTagsSummarization, Self-SupervisedLearning, UnsupervisedPre-training
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
NathanGrinsztajn, OlivierBeaumont, EmmanuelJeannot....
Published date-11/09/2020
CombinatorialOptimization
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
GovindaM.Kamath, TavorZ.Baharav, IlanShomorony....
Published date-11/09/2020
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
PoojaGupta, JyotiMaggu, AngshulMajumdar....
Published date-11/09/2020
TimeSeries, TimeSeriesAnalysis
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
HuixiaLi, ChenqianYan, ShaohuiLin....
Published date-11/09/2020
Quantization, SuperResolution, Super-Resolution, TransferLearning
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 …