raduionescu

ccmt

Cascaded Cross-Modal Transformer for Request and Complaint Detection

ssmctb

fast-aed

aed-mae

cl-mae

septr

RoDia

GUI-Medical-Images

GUI application for the medical images algorithms.

fiftyone

The open-source tool for building high-quality datasets and computer vision models

iQPP

Image Query Difficulty Prediction - Benchmark and Resources

FreCDo

FreCDo: A Large Corpus for French Cross-Domain Dialect Identification

MHCA

Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution

Dupin

Authorship detection and XAI tools for Transformers

Diffusion-Models-in-Vision-A-Survey

This repository categorizes the papers about diffusion models applied in computer vision according to their target task. The classifcation is based on our survey: https://arxiv.org/abs/2209.04747v1

fmi

Wiki for the Faculty of Computer Science and Mathematics from Bucharest

exemplar

A Generic and Model-Agnostic Exemplar Synthetization Framework for Explainable AI - Official implementation of the ECML 2020 paper

UBnormal

UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection

3d-super-res-cnn

sspcab

LiroBenchmark.github.io

Romanian benchmark leaderboard

arim-v2

coconv

[ICCV W] Contextual Convolutional Neural Networks (https://arxiv.org/pdf/2108.07387.pdf)

google-scholar-citation-scrapper

Simple scrapper for Google Scholar Data

LaRoSeDa

cycle-transformer

masked_faces

We propose a method for enhancing data sets containing faces without masks by creating synthetic masks and overlaying them on faces in the original images.

AED-SSMTL

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

AED

A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video

FreSaDa

The FreSaDa data set contains regular and satirical samples of text collected from the French news domain.

MOROCO-Tweets

The validation and test samples of the MOROCO-Tweets corpus.