-
A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task P...
Human comprehension of a video stream is naturally broad: in a few instants, we are able to understand what is happening, the relevance and relationship of objects, and... -
PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Prototype-based Efficient MaskFormer (PEM) is an efficient transformer-based architecture that can operate in multiple segmentation tasks. PEM proposes a novel prototype-based... -
Bringing Online Egocentric Action Recognition into the wild
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities. Egocentric vision seems to be a viable... -
Private ltlf2asp
Linear Temporal Logic over Finite Traces (LTLf) is a popular logic to reason about finite sequences of events. In LTLf, the (bounded) satisfiability problem refers to whether... -
Private Multi-Start Optimization Neural Networks
In this repository, we publish the codes necessary to implement the Multi-Start Optimization Neural Networks (MSO-NNs), presented fin the paper: Automatic... -
Graph-Informed Neural Networks
In this repository, we publish the codes necessary to implement the Graph-Informed Neural Networks (GINNs), presented for the first time in the paper: Graph-Informed Neural... -
Private Alternate Training for Multi-Task Neural Networks
In this repository, we publish the code used to implement the Alternate Training through the Epochs (ATE) procedure for training Multi-Task Neural Networks (MTNN) presented in... -
Private Dynamical Linear Upper Confidence Bound (DynLin-UCB)
The repository contains the code to run DynLin-UCB (Dynamical Linear Upper Confidence Bound). DynLin-UCB is an optimistic regret-minimization algorithm that can be used to... -
Online Learning of Order Flow and Market Impact (OLOFMI)
This library performs regime detection in the aggregated order flow time-series and market impact analysis. The required input file is in the format of the message file of the... -
Score-Driven Bayesian Online Change Point Detection (SD-BOCPD)
This code deals with Bayesian online detection in univariate time-series of changepoints, i.e. abrupt variations in the generative parameters of a data, and regimes, i.e.... -
Privlib
Privlib is a Python software package to manage privacy risk and discrimination in tabular and sequential data. It comprises methods to assess privacy risk (PRUDEnce) and... -
Debiaser for Multiple Variables (DEMV)
DEMV is a Debiaser for Multiple Variables that aims to increase Fairness in any given dataset, both binary and categorical, with one or more sensitive variables, while keeping...-
ipynb
The resource: 'Tutorial Notebook' is not accessible as guest user. You must login to access it!
-
ipynb
-
Reducing radicalizism in social networks by feeds prioritization - Rebalancin...
Code and description of the methodology of the paper "Rebalancing Social Feed to Minimize Polarization and Disagreement" funded by SoBigData ++ -
Gene-specific regularization for COPD partial-correlation estimation
We introduce a gene-specific regularization factor when computing the Partial Correlation score to make the indeterminate regression feasible. We decided to slightly modify... -
A New Topological Approach for the Prediction of Protein-Protein Interactions
We propose, Maximum-Proteins-Similarity(Topological)": MPS(T). MPS(T) is a topological three-length path method that scores the potential interaction between proteins by... -
A hybrid approach for PPI
We propose a new framework that can exploit topological and biological information to predict protein-protein interactions. The algorithm relies on the underlying hypothesis... -
EpiCID: A framework for discovering interactions between SNPs
Epistatic interactions (EIs) of gene loci often determine complex trait phenotypes. EIs may indicate the underlying molecular mechanisms of multifactorial traits and diseases.... -
Private Internal migration and mobile communication patterns among pairs with strong ...
Using large-scale call detail records of anonymised mobile phone service subscribers with demographic and location information, we investigate how a long-distance residential... -
Micro Project Methods: Academic Migration and Academic Networks
Methods used for the micro-project titled: Academic Migration and Academic Networks: Evidence from Scholarly Big Data and the Iron Curtain-
HTML
The resource: 'Methods ' is not accessible as guest user. You must login to access it!
-
HTML
-
Estimating countries' peace index with GDELT
We use news media attention from the Global Data of Events, Location and Tone (GDELT) database, as a proxy for estimating Global Peace Index (GPI), to complement the knowledge...
