Home /

Research

Showing 319 - 324 / 897

Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation

Authors:  WoohwanJung, KyuseokShim....
Published date-11/24/2020
Tasks:  RelationExtraction

Abstract: Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models …
Paper Code

LaHAR: Latent Human Activity Recognition using LDA

Authors:  ZeydBoukhers, DannieneWete, SteffenStaab....
Published date-11/23/2020
Dimensionality Reduction
LDA
Tasks:  ActivityRecognition, Clustering

Abstract: Processing sequential multi-sensor data becomes important in many tasks due to the dramatic increase in the availability of sensors that can acquire sequential data over time. Human Activity Recognition (HAR) …
Paper Code

HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms

Authors:  MahmoudAfifi, MarcusA.Brubaker, MichaelS.Brown....
Published date-11/23/2020
Activation Functions
Adaptive Instance Normalization
Convolution
Convolutions
Dense Connections
Tasks:  ImageGeneration

Abstract: While generative adversarial networks (GANs) can successfully produce high-quality images, they can be challenging to control. Simplifying GAN-based image generation is critical for their adoption in graphic design and artistic …
Paper Code

Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Components

Authors:  JosephA.Vincent, MacSchwager....
Published date-11/23/2020
Activation Functions
ReLU

Abstract: We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety analysis of …
Paper Code

Ensemble- and Distance-Based Feature Ranking for Unsupervised Learning

Authors:  MatejPetković, DragiKocev, BlažŠkrlj....
Published date-11/23/2020
Tasks:  Clustering

Abstract: In this work, we propose two novel (groups of) methods for unsupervised feature ranking and selection. The first group includes feature ranking scores (Genie3 score, RandomForest score) that are computed …
Paper Code

Prior to Segment: Foreground Cues for Novel Objects in Partially Supervised Instance Segmentation

Authors:  DavidBiertimpel, SindiShkodrani, AnilS.Baslamisli....
Published date-11/23/2020
Convolution
Convolutions
Instance Segmentation Models
Mask R-CNN
Output Functions
Tasks:  InstanceSegmentation, SemanticSegmentation

Abstract: Instance segmentation methods require large datasets with expensive instance-level mask labels. This makes partially supervised learning appealing in settings where abundant box and limited mask labels are available. To improve …
Paper Code

Filter by

Categories

Tags