• Depth Estimation

• RGB+Depth approaches

• Lightweight Convolutional Neural Networks and Vision Transformer for resource-constrained devices

• Resource-efficient techniques (e.g. Pruning, Knowledge Distillation)

• Depth/Image Completion

• 3D Object Detection

• Domain adaptation (real/synthetic data)

• Panoptic Segmentation

If you are interested in any of these topics or you have further ideas for developing a thesis in Computer Vision and Deep Learning areas, please contact Prof. Irene Amerini (amerini@diag.uniroma1.it) and Dr. Lorenzo Papa (papa@diag.uniroma1.it) to book a meeting.

• Diffusion model-generated content detection

• Deepfake video detection

• Person re-identification

• Ground to aerial image matching

• Detection of Synthetic Portrait Videos using Biological Signals

• Fake news detection: image/video and text analysis to detect or trace fake news

• Fake audio detection

• Multimodal and semantic forensics

• Forgery identification and source identification in the wild

• Adversarial (deep) machine learning

If you are interested in any of these topics or you have further ideas for developing a thesis in the Multimedia Forensics area, please contact Prof. Irene Amerini (amerini@diag.uniroma1.it) or Dr. Luca Maiano (maiano@diag.uniroma1.it) to book a meeting.

Within the context of Edge and Fog computing, we have the following open topics that are worth to be explored and studied for a MSc thesis:

• Load balancing and distributed scheduling algorithms for Fog and Edge Computing:

  • Targeting energy (Green Edge Computing);

  • QoS, performance metrics like latency/drop rate;

• Reinforcement Learning-based approaches for the previous point;

• Offloading algorithms for mobile-based applications, targeting energy and latency;

• Technologies-oriented solutions for container orchestration;

• Any other related topic that you want to deepen related to Edge, Fog and Cloud Computing;

If you are interested in any of these topics or you have further ideas for developing a thesis in the Edge or Fog computing area, please contact Prof. Roberto Beraldi (beraldi@diag.uniroma1.it) or Ing. Gabriele Proietti Mattia (proiettimattia@diag.uniroma1.it) [website] to book a meeting, or visit this website.