This repository contains a the FairBench Python library, which performs comprehensive AI fairness exploration. The library can generate fairness reports and stamps, and can perform multivalue multiattribute fairness assessment across a wide range of measures constructed from base building blocks. It also supports integration with popular data science libraries, such as numpy, pandas, tensorflow, and pytorch.

Created by: Krasanakis Emmanouil

GitHub ReadTheDocs

This repository contains a the JGNN Java library, which can define, train, and run Graph Neural Networks (GNNs) under limited resources. The library is cross-platform and implements memory-efficient machine learning components without external dependencies. Model definition is simplified by parsing Python-like expressions, including interoperable dense and sparse matrix operations and inline parameter definitions. GNN models can be deployed on smart devices and trained on local data.

Created by: Krasanakis Emmanouil

GitHub

A framework for “learning” how to classify social content as truthful/reliable or not. Features are extracted from the tweet text (Tweet-based features TF) and the user who published it (User-based features UB). A two level classification model is trained.

Created by: Papadopoulou Olga

GitHub

This is an integrated framework for image forensic analysis. It includes a Java webservice, including seven splicing detection algorithm implementations, plus additional forensic tools and a Matlab algorithm evaluation framework, including implementations of a large number of splicing detection algorithms.

Created by: Zampoglou Markos

GitHub

This repository contains the implementation of the feature extraction process described in Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers. Given an input video, one frame per second is sampled and its visual descriptor is extracted from the activations of the intermediate convolution layers of a pre-trained Convolutional Neural Network. Then, the Maximum Activation of Convolutions (MAC) function is applied on the activation of each layer to generate a compact layer vector. Finally, the layer vector are concatenated to generate a single frame descriptor.

Created by: Kordopatis-Zilos Giorgos

GitHub

This repository contains the implementation of algorithms that estimate the geographic location of multimedia items based on their textual content. The approach is described in the paper Geotagging Text Content With Language Models and Feature Mining.

Created by: Kordopatis-Zilos Giorgos

GitHub

This repository contains the Tensorflow implementation of the paper Near-Duplicate Video Retrieval with Deep Metric Learning. It provides code for training and evalutation of a Deep Metric Learning (DML) network on the problem of Near-Duplicate Video Retrieval (NDVR). During training, the DML network is fed with video triplets, generated by a triplet generator. The network is trained based on the triplet loss function.

Created by: Kordopatis-Zilos Giorgos

GitHub

Implementation of community-based graph embedding for user classification.

Created by: No longer Maintained

GitHub

This repository contains the pygrank Python library, which comprises modular implementation of fast node ranking algorithms for large graphs. It provides algorithmic components, such as graph filters, post-processors, measures, benchmarks, and online tuning. Computations can be delegated to numpy, tensorflow, or pytorch backends and fit in back-propagation pipelines. Node algorithms declared through this package are interoperable.

Created by: Krasanakis Emmanouil

GitHub

This repository contains the Tensorflow implementation of the paper ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning. It provides code for the calculation of similarities between the query and database videos given by the user. Also, it contains an evaluation script to reproduce the results of the paper. The video similarity calculation is achieved by applying a frame-to-frame function that respects the spatial within-frame structure of videos and a learned video-to-video similarity function that also considers the temporal structure of videos.

Created by: Kordopatis-Zilos Giorgos

GitHub