-
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... -
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 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... -
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.... -
Epidemic Sentiment Analysis
This tool is a sentiment analysis framework inspired by models of epidemic spreading, which aims to extend sentiment-tagged lexicons. It is easily extendable to multiple... -
Prediction of next career moves from scientific profiles
This is a two-stage predictive model for the mobility of scientists. First, data mining is used to predict which researcher will move in the next year on the basis of their... -
Economic Integration Model
This model allows to understand the integration process of immigrants starting from retail data. Under development. -
Nowcasting migration stocks and flows
This method nowcasts migration stocks and flows by using Twitter data. Under development. -
Superdiversity and Sentiment
This method analysises the effect of the migration phenomena on the sentiment of a community. Under development. -
Modelling Scientific Migration
This method is an adaptation of the general migration models to understand scientific migration. Under development. -
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
-
Private Cybersecurity NER BERT-base-cased model
This method includes a Python script and files of a BERT-base-cased model fine-tuned on our Cybersecurity NER dataset. The method requires as input a list of sentences that... -
Cybersecurity NER RoBERTa-base model
This method includes a Python script and files of a RoBERTa-base model fine-tuned on our Cybersecurity NER dataset. The method requires as input a list of sentences that will...-
JSON
The resource: 'config' is not accessible as guest user. You must login to access it!
-
TXT
The resource: 'merges' is not accessible as guest user. You must login to access it!
-
BIN
The resource: 'model' is not accessible as guest user. You must login to access it!
-
JSON
The resource: 'model_args' is not accessible as guest user. You must login to access it!
-
ZIP
The resource: 'scheduler' is not accessible as guest user. You must login to access it!
-
JSON
The resource: 'special_tokens_map' is not accessible as guest user. You must login to access it!
-
JSON
The resource: 'tokenizer_config' is not accessible as guest user. You must login to access it!
-
ZIP
The resource: 'training_args' is not accessible as guest user. You must login to access it!
-
JSON
The resource: 'tokenizer' is not accessible as guest user. You must login to access it!
-
JSON
The resource: 'vocab' is not accessible as guest user. You must login to access it!
-
ZIP
The resource: 'optimizer' is not accessible as guest user. You must login to access it!
-
py
The resource: 'inference' is not accessible as guest user. You must login to access it!
-
JSON