Posts by Collection

VERIMEDIA - IJCNN 2025 Workshop - Local Arrangement Chair Permalink

I am the Local Arrangement Chair of the Verimedia workshop.

The workshop addresses the rising challenges of AI-generated content and deepfakes by exploring advancements in multimedia forensics, deepfake detection, adversarial machine learning, AI-generated media attribution, multimodal analysis. A key focus is lifelong media authentication, emphasizing AI’s role in safeguarding media integrity by analyzing diverse media types—text, images, videos, and speech. The session highlights the critical importance of combating disinformation and ensuring trustworthy information across fields like forensics, fake news debunking, cyberattack mitigation, and politics. The primary objective is to bring together experts from these varied fields, policy makers and stakeholders to share challenges and solutions and foster collaborative discussions.

Important Info:

• Date: July 3rd, 2025
• Venue: Pontificia Università Gregoriana, Piazza della Pilotta, 4, 00187 Roma, Italy

SQL & NOSQL Data Management Systems Permalink

📊 Modelling and querying of a countries-states-cities dataset with SQL (Postgresql) and NOSQL (Neo4j) approaches. Optimization of SQL and NOSQL queries to reduce the execution time.

Linux Top command reimplementation Permalink

⌨️ Reimplementation of Top Linux shell command.

Reinforcement Learning: Deep Q learning from Demonstrations Permalink

🕹 Implementation of DQfD tested on Pong Gym environment and Montezuma Revenge Gym environment (the latter with sparse reward).

Bachelor’s thesis: Gitlab project manager Permalink

🖥 This web app allows the rapid inizialitazion of projects on GitLab through a very simple user interface. By filling in the required fields, the project will be created directly on your GitLab account.

University exams reviews Web App Permalink

🔭 Web app allowing students to write reviews on some exams in order to help other students in preparing for those exams.

Geometric Algebra Transformer: A study on equivariance and optimization for transformers Permalink

📈 Implementation of the famous Geometric Algebra Transformer to deal with geometric data. A modification of its attention module has been performed to study the equivariance of the architecture.

DeForm: Mesh Shape Deformation through 2D Guidance Permalink

🖥 This project aims to deform the shape of an input mesh by following a set of 2D guidance images representing the desired output mesh. We use Pytorch3D and exploit a neural network to predict the shape deformation.

Grasping on the Move with Tiago Robot Permalink

🦿 A reactive architecture made up of three controllers allows Tiago Robot to grasp and place a static object on-the-move (i.e. without stopping). The results are more gracefulness in the entire task execution and a minor task execution time.

Hot topics in NLP (Visual Word Sense Disambiguation, explicit representation, keyword selection, sentence similarity) Permalink

📚 Implementation of homeworks for the Hot Topics in NLP course of the Master degree in Artificial Intelligence & Robotics at Sapienza University of Rome.

Multi-Robot Simulator Permalink

🦾 This project consists of a ROS support for a Multi-robot simulator written in C++.

Lagrangian neural network with PD controller gravity cancellation Permalink

🦾 Implementation of Lagrangian Neural Network tested on one-single link rigid robot and one-single link elastic robot.

Optimize Vision Transformers Architecture via Efficient Attention Modules: A Study on the Monocular Depth Estimation Task Permalink

🔋 Two modifications of METER attention module are proposed and implemented to build two more efficient versions: Meta-METER and Pyra-METER.

Uformer reimplementation Permalink

🧲 This project presents the architecture and application of the Uformer neural network.

Optimize Vision Transformer Architecture via Efficient Attention Modules: A Study on the Monocular Depth Estimation Task Permalink

Published in International Conference on Image Analysis and Processing, 2023

Recommended citation: Schiavella, C., Cirillo, L., Papa, L., Russo, P., & Amerini, I. (2023, September). Optimize Vision Transformer Architecture via Efficient Attention Modules: A Study on the Monocular Depth Estimation Task. In International Conference on Image Analysis and Processing (pp. 383-394). Cham: Springer Nature Switzerland.

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

This is a description of your tutorial, note the different field in type. This is a markdown files that can be all markdown-ified like any other post. Yay markdown!

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Computer Vision (held by Prof. Irene Amerini) Permalink

Master in Artificial Intelligence & Robotics, Sapienza University of Rome, Department of Computer, Automatic and Management Engineering (DIAG), 2025

Teacher Assistant of the Computer Vision course held by Prof. Irene Amerini.

I taught lessons for the Master students:

• Practical lesson on Image Processing –> Colab notebook
• Practical lesson on Feature Description –> Colab notebook
• Lesson on Adversarial Machine Learning –> slides
• Practical lesson on Deep Learning for MDE –> Colab notebook
• Practical lesson on Camera Calibration –> Colab notebook

For any information about the practical lessons and related Google Colab notebooks, contact me at cirillo@diag.uniroma1.it