LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention

3 Apr 2020yinjunbo/3DVID

In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences.

VIDEO OBJECT DETECTION

2
03 Apr 2020

A Set of Recommendations for Assessing Human-Machine Parity in Language Translation

3 Apr 2020ZurichNLP/mt-parity-assessment-data

The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations.

MACHINE TRANSLATION

1
03 Apr 2020

Epitomic Variational Graph Autoencoder

3 Apr 2020RayyanRiaz/EVGAE

Variational autoencoder (VAE) is a widely used generative model for unsupervised learning of vector data.

0
03 Apr 2020

Context Prior for Scene Segmentation

3 Apr 2020ycszen/ContextPrior

Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior.

SCENE SEGMENTATION SCENE UNDERSTANDING

45
03 Apr 2020

DFNet: Discriminative feature extraction and integration network for salient object detection

3 Apr 2020Sina-Mohammadi/DFNet

To address the second challenge, we propose an Attention-based Multi-level Integrator Module to give the model the ability to assign different weights to multi-level feature maps.

SALIENCY DETECTION SALIENT OBJECT DETECTION

3
03 Apr 2020

Deep White-Balance Editing

3 Apr 2020mahmoudnafifi/WB_color_augmenter

The ISP rendering begins with a white-balance procedure that is used to remove the color cast of the scene's illumination.

22
03 Apr 2020

Multi-agent Reinforcement Learning for Networked System Control

ICLR 2020 cts198859/deeprl_network

This paper considers multi-agent reinforcement learning (MARL) in networked system control.

MULTI-AGENT REINFORCEMENT LEARNING

50
03 Apr 2020

Learning Pose-invariant 3D Object Reconstruction from Single-view Images

3 Apr 2020bomb2peng/learn3D

Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.

3D OBJECT RECONSTRUCTION DOMAIN ADAPTATION

2
03 Apr 2020

Towards Better Generalization: Joint Depth-Pose Learning without PoseNet

3 Apr 2020B1ueber2y/TrianFlow

In this work, we tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning.

DEPTH ESTIMATION OPTICAL FLOW ESTIMATION POSE ESTIMATION VISUAL ODOMETRY

21
03 Apr 2020

A Fast Fully Octave Convolutional Neural Network for Document Image Segmentation

3 Apr 2020ricardobnjunior/OctHU-PageScan

In this context, we investigated a method based on U-Net to detect the document edges and text regions in ID images.

SEMANTIC SEGMENTATION

1
03 Apr 2020