Search Results for author: Bruno Lepri

Found 46 papers, 22 papers with code

Efficient Training of Visual Transformers with Small Datasets

1 code implementation NeurIPS 2021 Yahui Liu, Enver Sangineto, Wei Bi, Nicu Sebe, Bruno Lepri, Marco De Nadai

This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce.

Inductive Bias

A Survey on Deep Learning for Human Mobility

1 code implementation4 Dec 2020 Massimiliano Luca, Gianni Barlacchi, Bruno Lepri, Luca Pappalardo

The study of human mobility is crucial due to its impact on several aspects of our society, such as disease spreading, urban planning, well-being, pollution, and more.

The economic value of neighborhoods: Predicting real estate prices from the urban environment

1 code implementation7 Aug 2018 Marco De Nadai, Bruno Lepri

In this paper, we use multiple sources of data to entangle the economic contribution of the neighborhood's characteristics such as walkability and security perception.

Computers and Society

Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach

1 code implementation10 Aug 2020 Yahui Liu, Marco De Nadai, Deng Cai, Huayang Li, Xavier Alameda-Pineda, Nicu Sebe, Bruno Lepri

Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation.

Attribute Image Captioning +3

Explaining the Explainers in Graph Neural Networks: a Comparative Study

2 code implementations27 Oct 2022 Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Liò, Bruno Lepri, Andrea Passerini

Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process.

Node Classification

Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps

1 code implementation12 Jul 2019 Yahui Liu, Marco De Nadai, Gloria Zen, Nicu Sebe, Bruno Lepri

In this work, we propose a novel GAN architecture that decouples the required annotations into a category label - that specifies the gesture type - and a simple-to-draw category-independent conditional map - that expresses the location, rotation and size of the hand gesture.

Gesture-to-Gesture Translation Translation

Are Safer Looking Neighborhoods More Lively? A Multimodal Investigation into Urban Life

1 code implementation1 Aug 2016 Marco De Nadai, Radu L. Vieriu, Gloria Zen, Stefan Dragicevic, Nikhil Naik, Michele Caraviello, Cesar A. Hidalgo, Nicu Sebe, Bruno Lepri

But in a world where the preference for safe looking neighborhoods is small, the connection between the perception of safety and liveliness will be either weak or nonexistent.

Computers and Society Social and Information Networks Physics and Society

Learning Mobility Flows from Urban Features with Spatial Interaction Models and Neural Networks

1 code implementation24 Apr 2020 Gevorg Yeghikyan, Felix L. Opolka, Mirco Nanni, Bruno Lepri, Pietro Lio'

A fundamental problem of interest to policy makers, urban planners, and other stakeholders involved in urban development projects is assessing the impact of planning and construction activities on mobility flows.

Social and Information Networks Physics and Society

ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation

1 code implementation26 Sep 2021 Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai

The ISF manipulates the semantics of an input latent code to make the image generated from it lying in the desired visual domain.

Image-to-Image Translation Translation

The Death and Life of Great Italian Cities: A Mobile Phone Data Perspective

1 code implementation13 Mar 2016 Marco De Nadai, Jacopo Staiano, Roberto Larcher, Nicu Sebe, Daniele Quercia, Bruno Lepri

This is mainly because it is hard to collect data about "city life".

Computers and Society Social and Information Networks Physics and Society

Semantic-Guided Inpainting Network for Complex Urban Scenes Manipulation

1 code implementation19 Oct 2020 Pierfrancesco Ardino, Yahui Liu, Elisa Ricci, Bruno Lepri, Marco De Nadai

Inspired by recent works on image inpainting, our proposed method leverages the semantic segmentation to model the content and structure of the image, and learn the best shape and location of the object to insert.

Image Inpainting Object +1

Click to Move: Controlling Video Generation with Sparse Motion

1 code implementation ICCV 2021 Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri, Elisa Ricci, Stéphane Lathuilière

This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene.

Video Generation

Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis

1 code implementation18 Jan 2022 Giovanni De Toni, Bruno Lepri, Andrea Passerini

Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unfavourable decision by a black-box machine learning model (e. g., being denied a loan request).

counterfactual Efficient Exploration +1

Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models

1 code implementation9 Oct 2023 Marco Bronzini, Carlo Nicolini, Bruno Lepri, Andrea Passerini, Jacopo Staiano

This poses a challenge in efficiently gathering and aligning the data into a unified framework to derive insights related to Corporate Social Responsibility (CSR).

In-Context Learning

Spatial Entropy as an Inductive Bias for Vision Transformers

1 code implementation9 Jun 2022 Elia Peruzzo, Enver Sangineto, Yahui Liu, Marco De Nadai, Wei Bi, Bruno Lepri, Nicu Sebe

In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training.

Inductive Bias Semantic Segmentation

Putting Context in Context: the Impact of Discussion Structure on Text Classification

1 code implementation5 Feb 2024 Nicolò Penzo, Antonio Longa, Bruno Lepri, Sara Tonelli, Marco Guerini

We also experiment with different amounts of training data and analyse the topology of local discussion networks in a privacy-compliant way.

Stance Detection text-classification +1

Trajectory Test-Train Overlap in Next-Location Prediction Datasets

1 code implementation7 Mar 2022 Massimiliano Luca, Luca Pappalardo, Bruno Lepri, Gianni Barlacchi

Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading.

Marketing

Personalized Algorithmic Recourse with Preference Elicitation

1 code implementation27 May 2022 Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri, Andrea Passerini

It is paramount that the sequence of actions does not require too much effort for users to implement.

Efficient Exploration

What your Facebook Profile Picture Reveals about your Personality

no code implementations3 Aug 2017 Cristina Segalin, Fabio Celli, Luca Polonio, Michal Kosinski, David Stillwell, Nicu Sebe, Marco Cristani, Bruno Lepri

We analyze the effectiveness of four families of visual features and we discuss some human interpretable patterns that explain the personality traits of the individuals.

General Classification

SALSA: A Novel Dataset for Multimodal Group Behavior Analysis

no code implementations23 Jun 2015 Xavier Alameda-Pineda, Jacopo Staiano, Ramanathan Subramanian, Ligia Batrinca, Elisa Ricci, Bruno Lepri, Oswald Lanz, Nicu Sebe

Studying free-standing conversational groups (FCGs) in unstructured social settings (e. g., cocktail party ) is gratifying due to the wealth of information available at the group (mining social networks) and individual (recognizing native behavioral and personality traits) levels.

Generalized Compression Dictionary Distance as Universal Similarity Measure

no code implementations21 Oct 2014 Andrey Bogomolov, Bruno Lepri, Fabio Pianesi

We present a new similarity measure based on information theoretic measures which is superior than Normalized Compression Distance for clustering problems and inherits the useful properties of conditional Kolmogorov complexity.

Clustering feature selection +1

Modeling Taxi Drivers' Behaviour for the Next Destination Prediction

no code implementations21 Jul 2018 Alberto Rossi, Gianni Barlacchi, Monica Bianchini, Bruno Lepri

In this paper, we study how to model taxi drivers' behaviour and geographical information for an interesting and challenging task: the next destination prediction in a taxi journey.

RAMBLE ON: Tracing Movements of Popular Historical Figures

no code implementations EACL 2017 Stefano Menini, Rachele Sprugnoli, Giovanni Moretti, Enrico Bignotti, Sara Tonelli, Bruno Lepri

We present RAMBLE ON, an application integrating a pipeline for frame-based information extraction and an interface to track and display movement trajectories.

The invisible power of fairness. How machine learning shapes democracy

no code implementations22 Mar 2019 Elena Beretta, Antonio Santangelo, Bruno Lepri, Antonio Vetrò, Juan Carlos De Martin

In this paper, we provide an overview of the most widespread definitions of fairness in the field of machine learning, arguing that the ideas highlighting each formalization are closely related to different ideas of justice and to different interpretations of democracy embedded in our culture.

BIG-bench Machine Learning Cultural Vocal Bursts Intensity Prediction +1

PocketCare: Tracking the Flu with Mobile Phones using Partial Observations of Proximity and Symptoms

no code implementations7 May 2019 Wen Dong, Tong Guan, Bruno Lepri, Chunming Qiao

Mobile phones provide a powerful sensing platform that researchers may adopt to understand proximity interactions among people and the diffusion, through these interactions, of diseases, behaviors, and opinions.

GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling

1 code implementation15 Mar 2020 Yahui Liu, Marco De Nadai, Jian Yao, Nicu Sebe, Bruno Lepri, Xavier Alameda-Pineda

Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images.

Attribute Translation +1

Detecting discriminatory risk through data annotation based on Bayesian inferences

no code implementations27 Jan 2021 Elena Beretta, Antonio Vetrò, Bruno Lepri, Juan Carlos De Martin

For this reason, we propose a method of data annotation based on Bayesian statistical inference that aims to warn about the risk of discriminatory results of a given data set.

BIG-bench Machine Learning Decision Making +1

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

no code implementations CVPR 2021 Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Wei Wang, Marco De Nadai

In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation.

Translation Unsupervised Image-To-Image Translation

Generating Synthetic Mobility Networks with Generative Adversarial Networks

no code implementations22 Feb 2022 Giovanni Mauro, Massimiliano Luca, Antonio Longa, Bruno Lepri, Luca Pappalardo

We conduct extensive experiments on public datasets of bike and taxi rides to show that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks.

Data Augmentation

Reprogramming FairGANs with Variational Auto-Encoders: A New Transfer Learning Model

no code implementations11 Mar 2022 Beatrice Nobile, Gabriele Santin, Bruno Lepri, Pierpaolo Brutti

Fairness-aware GANs (FairGANs) exploit the mechanisms of Generative Adversarial Networks (GANs) to impose fairness on the generated data, freeing them from both disparate impact and disparate treatment.

Fairness Transfer Learning

A Framework for Verifiable and Auditable Federated Anomaly Detection

no code implementations15 Mar 2022 Gabriele Santin, Inna Skarbovsky, Fabiana Fournier, Bruno Lepri

Federated Leaning is an emerging approach to manage cooperation between a group of agents for the solution of Machine Learning tasks, with the goal of improving each agent's performance without disclosing any data.

Anomaly Detection Ensemble Learning

Rethinking the Learning Paradigm for Facial Expression Recognition

no code implementations30 Sep 2022 Weijie Wang, Nicu Sebe, Bruno Lepri

Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation.

Facial Expression Recognition Facial Expression Recognition (FER)

BIASeD: Bringing Irrationality into Automated System Design

no code implementations1 Oct 2022 Aditya Gulati, Miguel Angel Lozano, Bruno Lepri, Nuria Oliver

Human perception, memory and decision-making are impacted by tens of cognitive biases and heuristics that influence our actions and decisions.

Decision Making

T2TD: Text-3D Generation Model based on Prior Knowledge Guidance

no code implementations25 May 2023 Weizhi Nie, Ruidong Chen, Weijie Wang, Bruno Lepri, Nicu Sebe

Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model.

3D Reconstruction Causal Inference

Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection

no code implementations3 Sep 2023 Weijie Wang, Zhengyu Zhao, Nicu Sebe, Bruno Lepri

Although effective deepfake detectors have been proposed, they are substantially vulnerable to adversarial attacks.

DeepFake Detection Face Swapping

Zero-Shot Point Cloud Registration

no code implementations5 Dec 2023 Weijie Wang, Guofeng Mei, Bin Ren, Xiaoshui Huang, Fabio Poiesi, Luc van Gool, Nicu Sebe, Bruno Lepri

The cornerstone of ZeroReg is the novel transfer of image features from keypoints to the point cloud, enriched by aggregating information from 3D geometric neighborhoods.

Point Cloud Registration

A Characterization Theorem for Equivariant Networks with Point-wise Activations

no code implementations17 Jan 2024 Marco Pacini, Xiaowen Dong, Bruno Lepri, Gabriele Santin

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains.

The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models

no code implementations13 Mar 2024 Carlo Nicolini, Jacopo Staiano, Bruno Lepri, Raffaele Marino

A substantial gap persists in understanding the reasons behind the exceptional performance of the Transformer architecture in NLP.

Cannot find the paper you are looking for? You can Submit a new open access paper.