Simone Milani
YOU?
Author Swipe
View article: Point Cloud Geometry Scalable Coding Using a Resolution and Quality-conditioned Latents Probability Estimator
Point Cloud Geometry Scalable Coding Using a Resolution and Quality-conditioned Latents Probability Estimator Open
In the current age, users consume multimedia content in very heterogeneous scenarios in terms of network, hardware, and display capabilities. A naive solution to this problem is to encode multiple independent streams, each covering a diffe…
View article: Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator Open
In the current age, users consume multimedia content in very heterogeneous scenarios in terms of network, hardware, and display capabilities. A naive solution to this problem is to encode multiple independent streams, each covering a diffe…
View article: Effectiveness of learning-based image codecs on fingerprint storage
Effectiveness of learning-based image codecs on fingerprint storage Open
The success of learning-based coding techniques and the development of learning-based image coding standards, such as JPEG-AI, point towards the adoption of such solutions in different fields, including the storage of biometric data, like …
View article: Real or virtual: a video conferencing background manipulation-detection system
Real or virtual: a video conferencing background manipulation-detection system Open
In the past few years, the popularity and wide use of video conferencing software enjoyed exponential growth in market size. This technology enables participants in different geographic regions to have a virtual face-to-face meeting. Addit…
View article: Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics Open
Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable navigation even in challenging environments such as adverse weath…
View article: Fingerprint Membership and Identity Inference Against Generative Adversarial Networks
Fingerprint Membership and Identity Inference Against Generative Adversarial Networks Open
Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric m…
View article: Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator
Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator Open
The widespread usage of point clouds (PC) for immersive visual applications has resulted in the use of very heterogeneous receiving conditions and devices, notably in terms of network, hardware, and display capabilities. In this scenario, …
View article: Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders
Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders Open
Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…
View article: Learning From Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation
Learning From Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation Open
Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. Point cloud semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting direct…
View article: Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation
Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation Open
Digital reconstruction through Building Information Models (BIM) is a valuable methodology for documenting and ana- lyzing existing buildings. Its pipeline starts with geometric acquisition. (e.g., via photogrammetry or laser scanning) for…
View article: Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network
Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network Open
State-of-the-art multimodal semantic segmentation strategies combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. This strong assumption …
View article: All-for-One and One-For-All: Deep learning-based feature fusion for Synthetic Speech Detection
All-for-One and One-For-All: Deep learning-based feature fusion for Synthetic Speech Detection Open
Recent advances in deep learning and computer vision have made the synthesis and counterfeiting of multimedia content more accessible than ever, leading to possible threats and dangers from malicious users. In the audio field, we are witne…
View article: CACTUS: Content-Aware Compression and Transmission Using Semantics for Automotive LiDAR Data
CACTUS: Content-Aware Compression and Transmission Using Semantics for Automotive LiDAR Data Open
Many recent cloud or edge computing strategies for automotive applications require transmitting huge amounts of Light Detection and Ranging (LiDAR) data from terminals to centralized processing units. As a matter of fact, the development o…
View article: Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data Open
During the last few years, Continual Learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and selfinp…
View article: Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data Open
During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and self-in…
View article: Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation
Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation Open
Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on …
View article: A Distributed Rate-Control Approach to Reduce Communication Burdens in VSNs
A Distributed Rate-Control Approach to Reduce Communication Burdens in VSNs Open
In visual sensor networks, the analyze-then-compress paradigm, where each camera process data and extract local features, is proved to be an efficient approach to reduce the amount of transmitted information. The bitrate can be further red…
View article: The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection
The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection Open
The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and informat…
View article: The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection
The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection Open
The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and informat…
View article: A Workflow and Digital Filters for Correcting Speed and Equalization Errors on Digitized Audio Open-Reel Magnetic Tapes
A Workflow and Digital Filters for Correcting Speed and Equalization Errors on Digitized Audio Open-Reel Magnetic Tapes Open
This paper presents a workflow and digital filters for compensating speed and equalization errors that can impact digitized audio open-reel tapes. Thirty cases of mismatch between recording and reproducing speed (3.75, 7.5, 15, and 30 in/s…
View article: Responsible innovation at work: gamification, public engagement, and privacy by design
Responsible innovation at work: gamification, public engagement, and privacy by design Open
Public engagement is crucial to strengthen responsibility frameworks in highly innovative contexts, including as part of business organisations. One particular innovation that calls for public engagement is gamification. Gamification foste…
View article: Real or Virtual: A Video Conferencing Background Manipulation-Detection System
Real or Virtual: A Video Conferencing Background Manipulation-Detection System Open
Recently, the popularity and wide use of the last-generation video conferencing technologies created an exponential growth in its market size. Such technology allows participants in different geographic regions to have a virtual face-to-fa…
View article: Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview
Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview Open
Recent advancements in self-driving cars, robotics, and remote sensing have widened the range of applications for 3D Point Cloud (PC) data. This data format poses several new issues concerning noise levels, sparsity, and required storage s…
View article: A Study on the Impact of Multiview Distributed Feature Coding on a Multicamera Vehicle Tracking System at Roundabouts
A Study on the Impact of Multiview Distributed Feature Coding on a Multicamera Vehicle Tracking System at Roundabouts Open
Visual sensor networks are one potential enabler for the evolution of the Internet of things. Due to their limited resources in terms of energy and bandwidth, it is crucial to identify appropriate approaches that take into considerations s…
View article: Dataset for Real and Virtual Backgrounds of Video Calls
Dataset for Real and Virtual Backgrounds of Video Calls Open
Video conferencing applications play an important role in our day-to-day life. They enable people to meet, work, and collaborate remotely, especially in circumstances where physical meetings are not possible (e.g., pandemic scenarios, long…
View article: Hand Me Your PIN! Inferring ATM PINs of Users Typing with a Covered Hand
Hand Me Your PIN! Inferring ATM PINs of Users Typing with a Covered Hand Open
Automated Teller Machines (ATMs) represent the most used system for withdrawing cash. The European Central Bank reported more than 11 billion cash withdrawals and loading/unloading transactions on the European ATMs in 2019. Although ATMs h…
View article: Dataset for Real and Virtual Backgrounds of Video Calls
Dataset for Real and Virtual Backgrounds of Video Calls Open
Video conferencing applications play an important role in our day-to-day life. They enable people to meet, work, and collaborate remotely, especially in circumstances where physical meetings are not possible (e.g., pandemic scenarios, long…
View article: Do Not Deceive Your Employer with a Virtual Background: A Video Conferencing Manipulation-Detection System
Do Not Deceive Your Employer with a Virtual Background: A Video Conferencing Manipulation-Detection System Open
The last-generation video conferencing software allows users to utilize a virtual background to conceal their personal environment due to privacy concerns, especially in official meetings with other employers. On the other hand, users mayb…
View article: Aerial Segmentation Dataset
Aerial Segmentation Dataset Open
Contains 277 aerial images (extracted from Bing Maps) and their corresponding aerial segmentation (binary and colored). Segmentation is built automatically from segmentation data downloaded from OpenStreeMaps. Data was downloaded from 4 ci…