Latest Research
With Malice Towards None: Assessing Uncertainty via Equalized Coverage
• yromano/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.
Beyond Cartesian Representations for Local Descriptors
• cvlab-epfl/log-polar-descriptors
We demonstrate that this representation is particularly amenable to learning descriptors with deep networks.
Learning Trajectory Dependencies for Human Motion Prediction
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.
Temporal Collaborative Ranking Via Personalized Transformer
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.
Raw-to-End Name Entity Recognition in Social Media
Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.
Deep Generalized Max Pooling
Global pooling layers are an essential part of Convolutional Neural Networks (CNN).
3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
We claim the following characteristics for a versatile environment model: accuracy, applicability, usability, and scalability.
D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation
This function adds a weighted focal coefficient and combines two traditional loss functions.
Least Squares Approximation for a Distributed System
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.
Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT
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.