18 citations · 91 across the 28 of their papers we have counts for
32 papers
Staged Contact-Aware Global Human Motion Forecasting
Luca Scofano, Alessio Sampieri, Elisabeth Schiele +3
Scene-aware global human motion forecasting is critical for manifold applications, including virtual reality, robotics, and sports. The task combines human trajectory and pose fore…
Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation
Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni +3
Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in vary…
Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection
Alessandro Flaborea, Luca Collorone, Guido D'Amely +3
Anomalies are rare and anomaly detection is often therefore framed as One-Class Classification (OCC), i.e. trained solely on normalcy. Leading OCC techniques constrain the latent r…
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
Luca Franco, Paolo Mandica, Konstantinos Kallidromitis +4
We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the h…
Best Practices for 2-Body Pose Forecasting
Muhammad Rameez Ur Rahman, Luca Scofano, Edoardo De Matteis +3
The task of collaborative human pose forecasting stands for predicting the future poses of multiple interacting people, given those in previous frames. Predicting two people in int…
About latent roles in forecasting players in team sports
Luca Scofano, Alessio Sampieri, Giuseppe Re +3
Forecasting players in sports has grown in popularity due to the potential for a tactical advantage and the applicability of such research to multi-agent interaction systems. Team…
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
Luca Franco, Paolo Mandica, Bharti Munjal +1
Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the train…
Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection
Alessandro Flaborea, Guido D'Amely, Stefano D'Arrigo +3
Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex sin…
Are we certain it's anomalous?
Alessandro Flaborea, Bardh Prenkaj, Bharti Munjal +4
The progress in modelling time series and, more generally, sequences of structured data has recently revamped research in anomaly detection. The task stands for identifying abnorma…
Query-Guided Networks for Few-shot Fine-grained Classification and Person Search
Bharti Munjal, Alessandro Flaborea, Sikandar Amin +2
Few-shot fine-grained classification and person search appear as distinct tasks and literature has treated them separately. But a closer look unveils important similarities: both t…
Pose Forecasting in Industrial Human-Robot Collaboration
Alessio Sampieri, Guido D'Amely, Andrea Avogaro +5
Pushing back the frontiers of collaborative robots in industrial environments, we propose a new Separable-Sparse Graph Convolutional Network (SeS-GCN) for pose forecasting. For the…
CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni +3
3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to impro…
GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
Cristiano Saltori, Evgeny Krivosheev, Stéphane Lathuilière +5
3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when…
Under the Hood of Transformer Networks for Trajectory Forecasting
Luca Franco, Leonardo Placidi, Francesco Giuliari +3
Transformer Networks have established themselves as the de-facto state-of-the-art for trajectory forecasting but there is currently no systematic study on their capability to model…
Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress
Laura Laurenti, Elisa Tinti, Fabio Galasso +2
Earthquake forecasting and prediction have long and in some cases sordid histories but recent work has rekindled interest based on advances in early warning, hazard assessment for…
Space-Time-Separable Graph Convolutional Network for Pose Forecasting
Theodoros Sofianos, Alessio Sampieri, Luca Franco +1
Human pose forecasting is a complex structured-data sequence-modelling task, which has received increasing attention, also due to numerous potential applications. Research has main…
Cluster-driven Graph Federated Learning over Multiple Domains
Debora Caldarola, Massimiliano Mancini, Fabio Galasso +3
Federated Learning (FL) deals with learning a central model (i.e. the server) in privacy-constrained scenarios, where data are stored on multiple devices (i.e. the clients). The ce…
Adversarial Branch Architecture Search for Unsupervised Domain Adaptation
Luca Robbiano, Muhammad Rameez Ur Rahman, Fabio Galasso +2
Unsupervised Domain Adaptation (UDA) is a key issue in visual recognition, as it allows to bridge different visual domains enabling robust performances in the real world. To date,…
SF-UDA: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection
Cristiano Saltori, Stéphane Lathuiliére, Nicu Sebe +2
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due…
Class Interference Regularization
Bharti Munjal, Sikandar Amin, Fabio Galasso
Contrastive losses yield state-of-the-art performance for person re-identification, face verification and few shot learning. They have recently outperformed the cross-entropy loss…
Joint Detection and Tracking in Videos with Identification Features
Bharti Munjal, Abdul Rafey Aftab, Sikandar Amin +3
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-r…
An integrated light management system with real-time light measurement and human perception
Theodore Tsesmelis, Irtiza Hasan, Marco Cristani +2
Illumination is important for well-being, productivity and safety across several environments, including offices, retail shops and industrial warehouses. Current techniques for set…
Transformer Networks for Trajectory Forecasting
Francesco Giuliari, Irtiza Hasan, Marco Cristani +1
Most recent successes on forecasting the people motion are based on LSTM models and all most recent progress has been achieved by modelling the social interaction among people and…
Knowledge Distillation for End-to-End Person Search
Bharti Munjal, Fabio Galasso, Sikandar Amin
We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identificat…