3 citations · 7 across the 28 of their papers we have counts for
34 papers
Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning
Tommaso Galliena, Stefano Rosa, Tommaso Apicella +3
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic…
Frequency-Decomposed Avatar Representation for Varying Camera Distances
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present a CloseUpAvatar - a novel approach for articulated human avatar representation supporting a wider range of camera motions, while preserving rendering quality for close-u…
E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework
Adeela Islam, Stefano Fiorini, Manuel Lecha +4
3D reassembly is a fundamental geometric problem, and in recent years it has increasingly been challenged by deep learning methods rather than classical optimization. While learnin…
Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction
Matteo Tiezzi, Tommaso Apicella, Carlos Cardenas-Perez +5
Evaluating and comparing the performance of autonomous Humanoid Robots is challenging, as success rate metrics are difficult to reproduce and fail to capture the complexity of robo…
Sheaves Reloaded: A Directional Awakening
Stefano Fiorini, Hakan Aktas, Iulia Duta +4
Sheaf Neural Networks (SNNs) represent a powerful generalization of Graph Neural Networks (GNNs) that significantly improve our ability to model complex relational data. While dire…
ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction
Adeela Islam, Stefano Fiorini, Stuart James +2
The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation o…
Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding
Manuel Lecha, Andrea Cavallo, Francesca Dominici +5
Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses thi…
Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions
Tommaso Galliena, Tommaso Apicella, Stefano Rosa +3
We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, a…
AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics
Yao Wei, Matteo Toso, Pietro Morerio +3
This paper presents a framework for generating 3D indoor scenes from text prompts. Existing methods often formulate scene synthesis as an object layout prediction problem condition…
A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation
Dario Serez, Marco Cristani, Alessio Del Bue +2
In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer…
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
Dario Serez, Marco Cristani, Alessio Del Bue +2
Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative net…
Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving
Theodore Tsesmelis, Luca Palmieri, Marina Khoroshiltseva +20
This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dat…
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable te…
DLGNet: Hyperedge Classification through Directed Line Graphs for Chemical Reactions
Stefano Fiorini, Giulia M. Bovolenta, Stefano Coniglio +4
Graphs and hypergraphs provide powerful abstractions for modeling interactions among a set of entities of interest and have been attracting a growing interest in the literature tha…
Model Debiasing by Learnable Data Augmentation
Pietro Morerio, Ruggero Ragonesi, Vittorio Murino
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual ta…
XBG: End-to-end Imitation Learning for Autonomous Behaviour in Human-Robot Interaction and Collaboration
Carlos Cardenas-Perez, Giulio Romualdi, Mohamed Elobaid +6
This paper presents XBG (eXteroceptive Behaviour Generation), a multimodal end-to-end Imitation Learning (IL) system for a whole-body autonomous humanoid robot used in real-world H…
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation
Mattia Litrico, Davide Talon, Sebastiano Battiato +3
Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source…
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gauss…
DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly
Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari +2
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context, we posit that a general unified model…
Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
Julio Ivan Davila Carrazco, Pietro Morerio, Alessio Del Bue +1
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most chall…
Person Re-Identification without Identification via Event Anonymization
Shafiq Ahmad, Pietro Morerio, Alessio Del Bue
Wide-scale use of visual surveillance in public spaces puts individual privacy at stake while increasing resource consumption (energy, bandwidth, and computation). Neuromorphic vis…
Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos
Sanket Thakur, Cigdem Beyan, Pietro Morerio +2
Objects are crucial for understanding human-object interactions. By identifying the relevant objects, one can also predict potential future interactions or actions that may occur w…
Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
Sanket Thakur, Cigdem Beyan, Pietro Morerio +2
Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Exi…
Guided Attention for Next Active Object @ EGO4D STA Challenge
Sanket Thakur, Cigdem Beyan, Pietro Morerio +2
In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge. It combines the object…