80 citations · 114 across the 18 of their papers we have counts for
25 papers
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
Niccolò Niccoli, Silvia Dani, Marco Mistretta +3
World-level image geolocalization is an increasingly important task, yet the biases of current models remain poorly understood. Prior work has identified coarse dataset imbalances…
R2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot Interaction
Gabriele Magrini, Riccardo Catalini, Federico Becattini +4
Understanding and modeling interactions between autonomous agents is a fundamental challenge in robotics, with broad implications for collaborative systems, social robotics, and hu…
Defending from GeoLocalization through Adversarial Road Trips
Niccolò Niccoli, Federico Becattini, Lorenzo Seidenari
Retrieval-based image geolocalization has emerged as a powerful technique for determining the location of a query image by matching it against a large, geotagged database. The succ…
Prompt-based Consistent Video Colorization
Silvia Dani, Tiberio Uricchio, Lorenzo Seidenari
Existing video colorization methods struggle with temporal flickering or demand extensive manual input. We propose a novel approach automating high-fidelity video colorization usin…
Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Matteo Trippodo, Federico Becattini, Lorenzo Seidenari
Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversaria…
Attacking Attention of Foundation Models Disrupts Downstream Tasks
Hondamunige Prasanna Silva, Federico Becattini, Lorenzo Seidenari
Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high acc…
Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB
Alessandro Simoni, Francesco Marchetti, Guido Borghi +6
Despite the recent advances in computer vision research, estimating the 3D human pose from single RGB images remains a challenging task, as multiple 3D poses can correspond to the…
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
Luca Cultrera, Federico Becattini, Lorenzo Seidenari +2
Conditional Imitation learning is a common and effective approach to train autonomous driving agents. However, two issues limit the full potential of this approach: (i) the inertia…
FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures
Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari +1
Forecasting motion and spatial positions of objects is of fundamental importance, especially in safety-critical settings such as autonomous driving. In this work, we address the is…
Deepfake detection by exploiting surface anomalies: the SurFake approach
Andrea Ciamarra, Roberto Caldelli, Federico Becattini +2
The ever-increasing use of synthetically generated content in different sectors of our everyday life, one for all media information, poses a strong need for deepfake detection tool…
DiffDefense: Defending against Adversarial Attacks via Diffusion Models
Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto Del Bimbo
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any mod…
3D Pose Nowcasting: Forecast the Future to Improve the Present
Alessandro Simoni, Francesco Marchetti, Guido Borghi +4
Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component use…
Forecasting Future Instance Segmentation with Learned Optical Flow and Warping
Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari +1
For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This…
Online Deep Clustering with Video Track Consistency
Alessandra Alfani, Federico Becattini, Lorenzo Seidenari +1
Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets. Their main drawback however is…
SMEMO: Social Memory for Trajectory Forecasting
Francesco Marchetti, Federico Becattini, Lorenzo Seidenari +1
Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories. Each individual, with its motion, influences surrounding ag…
Learning Group Activities from Skeletons without Individual Action Labels
Fabio Zappardino, Tiberio Uricchio, Lorenzo Seidenari +1
To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions. Hierarchical models obtain the best results i…
Multiple Future Prediction Leveraging Synthetic Trajectories
Lorenzo Berlincioni, Federico Becattini, Lorenzo Seidenari +1
Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuri…
Explaining Autonomous Driving by Learning End-to-End Visual Attention
Luca Cultrera, Lorenzo Seidenari, Federico Becattini +2
Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular…
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
Francesco Marchetti, Federico Becattini, Lorenzo Seidenari +1
Autonomous vehicles are expected to drive in complex scenarios with several independent non cooperating agents. Path planning for safely navigating in such environments can not jus…
Text-to-Image Synthesis Based on Machine Generated Captions
Marco Menardi, Alex Falcon, Saida S. Mohamed +4
Text to Image Synthesis refers to the process of automatic generation of a photo-realistic image starting from a given text and is revolutionizing many real-world applications. In…
Semantic Road Layout Understanding by Generative Adversarial Inpainting
Lorenzo Berlincioni, Federico Becattini, Leonardo Galteri +2
Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in. The ability to discern static environment an…
Am I Done? Predicting Action Progress in Videos
Federico Becattini, Tiberio Uricchio, Lorenzo Seidenari +2
In this paper we deal with the problem of predicting action progress in videos. We argue that this is an extremely important task since it can be valuable for a wide range of inter…
Deep Generative Adversarial Compression Artifact Removal
Leonardo Galteri, Lorenzo Seidenari, Marco Bertini +1
Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small str…
Segmentation Free Object Discovery in Video
Giovanni Cuffaro, Federico Becattini, Claudio Baecchi +2
In this paper we present a simple yet effective approach to extend without supervision any object proposal from static images to videos. Unlike previous methods, these spatio-tempo…