With Malice Towards None: Assessing Uncertainty via Equalized Coverage

15 Aug 2019yromano/cqr

An important factor to guarantee a fair use of data-driven recommendation systems is that we should be able to communicate their uncertainty to decision makers.

RECOMMENDATION SYSTEMS

3
15 Aug 2019

Beyond Cartesian Representations for Local Descriptors

15 Aug 2019cvlab-epfl/log-polar-descriptors

We demonstrate that this representation is particularly amenable to learning descriptors with deep networks.

2
15 Aug 2019

Learning Trajectory Dependencies for Human Motion Prediction

15 Aug 2019wei-mao-2019/LearnTrajDep

In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.

MOTION CAPTURE

3
15 Aug 2019

Temporal Collaborative Ranking Via Personalized Transformer

15 Aug 2019wuliwei9278/SSE-PT

Recent advances in deep learning, especially the discovery of various attention mechanisms and newer architectures in addition to widely used RNN and CNN in natural language processing, have allowed us to make better use of the temporal ordering of items that each user has engaged with.

COLLABORATIVE RANKING

1
15 Aug 2019

Raw-to-End Name Entity Recognition in Social Media

14 Aug 2019LiyuanLucasLiu/Raw-to-End

Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.

NAMED ENTITY RECOGNITION TOKENIZATION

3
14 Aug 2019

Deep Generalized Max Pooling

14 Aug 2019VChristlein/dgmp

Global pooling layers are an essential part of Convolutional Neural Networks (CNN).

0
14 Aug 2019

3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents

14 Aug 2019Uehwan/3-D-Scene-Graph

We claim the following characteristics for a versatile environment model: accuracy, applicability, usability, and scalability.

GRAPH CONSTRUCTION

4
14 Aug 2019

D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation

14 Aug 2019SZUHvern/D-UNet

This function adds a weighted focal coefficient and combines two traditional loss functions.

LESION SEGMENTATION MEDICAL DIAGNOSIS SEMANTIC SEGMENTATION

2
14 Aug 2019

Least Squares Approximation for a Distributed System

14 Aug 2019feng-li/dlsa

In this work we develop a distributed least squares approximation (DLSA) method, which is able to solve a large family of regression problems (e. g., linear regression, logistic regression, Cox's model) on a distributed system.

0
14 Aug 2019

Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT

14 Aug 2019emorynlp/bert-2019

This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT.

PART-OF-SPEECH TAGGING SEMANTIC PARSING

1
14 Aug 2019