Indro Spinelli
YOU?
Author Swipe
View article: MonSTeR: a Unified Model for Motion, Scene, Text Retrieval
MonSTeR: a Unified Model for Motion, Scene, Text Retrieval Open
Intention drives human movement in complex environments, but such movement can only happen if the surrounding context supports it. Despite the intuitive nature of this mechanism, existing research has not yet provided tools to evaluate the…
View article: Adaptive token selection for scalable point cloud transformers
Adaptive token selection for scalable point cloud transformers Open
The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud transform…
View article: Spatio-temporal transformers for decoding neural movement control
Spatio-temporal transformers for decoding neural movement control Open
Objective . Deep learning tools applied to high-resolution neurophysiological data have significantly progressed, offering enhanced decoding, real-time processing, and readability for practical applications. However, the design of artifici…
View article: Social EgoMesh Estimation
Social EgoMesh Estimation Open
Accurately estimating the 3D pose of the camera wearer in egocentric video sequences is crucial to modeling human behavior in virtual and augmented reality applications. The task presents unique challenges due to the limited visibility of …
View article: OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras
OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras Open
Event cameras, known for low-latency operation and superior performance in challenging lighting conditions, are suitable for sensitive computer vision tasks such as semantic segmentation in autonomous driving. However, challenges arise due…
View article: Length-Aware Motion Synthesis via Latent Diffusion
Length-Aware Motion Synthesis via Latent Diffusion Open
The target duration of a synthesized human motion is a critical attribute that requires modeling control over the motion dynamics and style. Speeding up an action performance is not merely fast-forwarding it. However, state-of-the-art tech…
View article: MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization
MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization Open
Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability …
View article: Spatio-temporal transformers for decoding neural movement control
Spatio-temporal transformers for decoding neural movement control Open
Deep learning tools applied to high-resolution neurophysiological data have significantly progressed, offering enhanced decoding, real-time processing, and readability for practical applications. However, the design of artificial neural ne…
View article: Following the Human Thread in Social Navigation
Following the Human Thread in Social Navigation Open
The success of collaboration between humans and robots in shared environments relies on the robot's real-time adaptation to human motion. Specifically, in Social Navigation, the agent should be close enough to assist but ready to back up t…
View article: TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
TopoX: A Suite of Python Packages for Machine Learning on Topological Domains Open
We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial co…
View article: Adaptive Point Transformer
Adaptive Point Transformer Open
The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud transform…
View article: GATSY: Graph Attention Network for Music Artist Similarity
GATSY: Graph Attention Network for Music Artist Similarity Open
The artist similarity quest has become a crucial subject in social and scientific contexts, driven by the desire to enhance music discovery according to user preferences. Modern research solutions facilitate music discovery according to us…
View article: Drop edges and adapt: A fairness enforcing fine-tuning for graph neural networks
Drop edges and adapt: A fairness enforcing fine-tuning for graph neural networks Open
The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social impac…
View article: From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module Open
Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have a (noisy, incomplete, improvable, ...) input graph to rewir…
View article: pyt-team/TopoModelX: TopoModelX 0.0.1
pyt-team/TopoModelX: TopoModelX 0.0.1 Open
Topological Deep Learning
View article: Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability
Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability Open
Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or wit…
View article: Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks
Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks Open
The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social impac…
View article: Explainability in subgraphs-enhanced Graph Neural Networks
Explainability in subgraphs-enhanced Graph Neural Networks Open
Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman isomorphism test. Th…
View article: Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability
Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability Open
Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or wit…
View article: Explainability in subgraphs-enhanced Graph Neural Networks
Explainability in subgraphs-enhanced Graph Neural Networks Open
Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman isomorphism test. Th…
View article: Reidentification of Objects From Aerial Photos With Hybrid Siamese Neural Networks
Reidentification of Objects From Aerial Photos With Hybrid Siamese Neural Networks Open
In this paper, we consider the task of re-identifying the same object in different photos taken from separate positions and angles during aerial reconnaissance, which is a crucial task for the maintenance and surveillance of critical large…
View article: A Meta-Learning Approach for Training Explainable Graph Neural Networks
A Meta-Learning Approach for Training Explainable Graph Neural Networks Open
In this article, we investigate the degree of explainability of graph neural networks (GNNs). The existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained…
View article: FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning Open
Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting in smart grids. In several applications, ensuring the fairness of the node (or graph) representat…
View article: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning.
Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning. Open
Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting in smart grids. In several applications, ensuring the fairness of the node (or graph) representat…
View article: Adaptive Propagation Graph Convolutional Network
Adaptive Propagation Graph Convolutional Network Open
Graph convolutional networks (GCNs) are a family of neural network models that perform inference on graph data by interleaving vertexwise operations and message-passing exchanges across nodes. Concerning the latter, two key questions arise…
View article: Distributed Graph Convolutional Networks.
Distributed Graph Convolutional Networks. Open
The aim of this work is to develop a fully-distributed algorithmic framework for training graph convolutional networks (GCNs). The proposed method is able to exploit the meaningful relational structure of the input data, which are collecte…