fabiocarrara

nn-zero-to-hero

Neural Networks: Zero to Hero

ImageBind

ImageBind One Embedding Space to Bind Them All

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

concept-fusion

Code release for ConceptFusion [RSS 2023]

daeng-sherly-menikah

Wedding Invitation Landing Page - Pernikahan Sherly & Daeng

TERAN

Code and Resources for the Transformer Encoder Reasoning and Alignment Network (TERAN), accepted for publication in ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

QuaPy

A framework for Quantification written in Python

FG-OVD

[CVPR2024 Highlight] Official repository of the paper "The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding."

meye

A deep-learning-based web tool for translational and real-time pupillometry

visual-sentiment-analysis

PyTorch port of models for Visual Sentiment Analysis pre-trained on the T4SA dataset.

cbigan-ad

Code to reproduce 'Combining GANs and AutoEncoders for efficient anomaly detection'

mocap

Code to reproduce experiments in 'LSTM-based real-time action detection and prediction in human motion streams'

NoR-VDPNet

A no-reference version of HDR-VDP using deep-learning

HebbianLearning

Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.

ALADIN

Official implementation of the paper "ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval"

FG-CLIP

[CBMI2024 Best Paper] Official repository of the paper "Is CLIP the main roadblock for fine-grained open-world perception?".

visione

An AI-powered interactive video retrieval system

PassNet

A Computer Vision Approach for Pass Detection on Soccer Broadcast Video

PassNet

A Computer Vision Approach for Pass Detection on Soccer Broadcast Video

ics

Interactive Classification System

counting_perineuronal_nets

HoloLens2ResearchTools

The research tools developed for HoloLens2

trj-based-adversarials-detection

Detect adversarial attacks based on features trajectory for Face Recognition and toy datasets

nSimplex

Code to compute the nSimplex projection, that maps metric objects into a finite-dimensional Euclidean space

T4SA-2.0

This project creates the T4SA 2.0 dataset, i.e. a big set of data to train visual models for Sentiment Analysis in the Twitter domain using a cross-modal student-teacher approach.

diqm

fallen-people-detection

Thesis work in which we will study and develop visual techniques for automatic detection of fallen people that leverage the latest artificial intelligence and deep learning technologies.

VBS22-Post-Evaluation

A collection of notebooks and scripts for the log analysis of the VBS22 post-evaluation, where the top-3 scoring teams solved 50 visuell know-item-search tasks with four individual users per team.

running-experiments

Running experiments with confidence and sanity

conditioned-cooperative-training

Pytorch code for paper Conditioned Cooperative Training for Semi-supervised Weapon Detection.