Search Results for author: Fabio Galasso

Found 35 papers, 15 papers with code

Staged Contact-Aware Global Human Motion Forecasting

1 code implementation16 Sep 2023 Luca Scofano, Alessio Sampieri, Elisabeth Schiele, Edoardo De Matteis, Laura Leal-Taixé, Fabio Galasso

So far, only Mao et al. NeurIPS'22 have addressed scene-aware global motion, cascading the prediction of future scene contact points and the global motion estimation.

Human Pose Forecasting Motion Estimation +2

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

1 code implementation28 Aug 2023 Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni, Nicu Sebe, Fabio Poiesi, Elisa Ricci

In this study, we introduce compositional semantic mixing for point cloud domain adaptation, representing the first unsupervised domain adaptation technique for point cloud segmentation based on semantic and geometric sample mixing.

Point Cloud Completion Point Cloud Segmentation +2

Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

1 code implementation ICCV 2023 Alessandro Flaborea, Luca Collorone, Guido D'Amely, Stefano D'arrigo, Bardh Prenkaj, Fabio Galasso

Leading OCC techniques constrain the latent representations of normal motions to limited volumes and detect as abnormal anything outside, which accounts satisfactorily for the openset'ness of anomalies.

2D Human Pose Estimation Human Pose Forecasting +2

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

no code implementations19 Jun 2023 Luca Franco, Paolo Mandica, Konstantinos Kallidromitis, Devin Guillory, Yu-Teng Li, Trevor Darrell, Fabio Galasso

In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known.

Active Learning Domain Adaptation +2

About latent roles in forecasting players in team sports

no code implementations17 Apr 2023 Luca Scofano, Alessio Sampieri, Giuseppe Re, Matteo Almanza, Alessandro Panconesi, Fabio Galasso

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.

Best Practices for 2-Body Pose Forecasting

1 code implementation12 Apr 2023 Muhammad Rameez Ur Rahman, Luca Scofano, Edoardo De Matteis, Alessandro Flaborea, Alessio Sampieri, Fabio Galasso

The task of collaborative human pose forecasting stands for predicting the future poses of multiple interacting people, given those in previous frames.

Human Pose Forecasting motion prediction +1

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

1 code implementation10 Mar 2023 Luca Franco, Paolo Mandica, Bharti Munjal, Fabio Galasso

We propose to use hyperbolic uncertainty to determine the algorithmic learning pace, under the assumption that less uncertain samples should be more strongly driving the training, with a larger weight and pace.

Action Recognition Domain Adaptation +2

Are we certain it's anomalous?

1 code implementation16 Nov 2022 Alessandro Flaborea, Bardh Prenkaj, Bharti Munjal, Marco Aurelio Sterpa, Dario Aragona, Luca Podo, Fabio Galasso

By using uncertainty, HypAD may assess whether it is certain about the input signal but it fails to reconstruct it because this is anomalous; or whether the reconstruction error does not necessarily imply anomaly, as the model is uncertain, e. g. a complex but regular input signal.

Anomaly Detection Time Series +1

Pose Forecasting in Industrial Human-Robot Collaboration

1 code implementation24 Jul 2022 Alessio Sampieri, Guido D'Amely, Andrea Avogaro, Federico Cunico, Geri Skenderi, Francesco Setti, Marco Cristani, Fabio Galasso

Pushing back the frontiers of collaborative robots in industrial environments, we propose a new Separable-Sparse Graph Convolutional Network (SeS-GCN) for pose forecasting.

Human Pose Forecasting

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

2 code implementations20 Jul 2022 Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni, Nicu Sebe, Elisa Ricci, Fabio Poiesi

We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing.

3D Unsupervised Domain Adaptation Autonomous Driving +5

Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress

no code implementations24 Mar 2022 Laura Laurenti, Elisa Tinti, Fabio Galasso, Luca Franco, Chris Marone

We demonstrate that DL models based on Long-Short Term Memory (LSTM) and Convolution Neural Networks predict labquakes under several conditions, and that fault zone stress can be predicted with fidelity, confirming that acoustic energy is a fingerprint of fault zone stress.

Earthquake prediction

Under the Hood of Transformer Networks for Trajectory Forecasting

no code implementations22 Mar 2022 Luca Franco, Leonardo Placidi, Francesco Giuliari, Irtiza Hasan, Marco Cristani, Fabio Galasso

This paper proposes the first in-depth study of Transformer Networks (TF) and Bidirectional Transformers (BERT) for the forecasting of the individual motion of people, without bells and whistles.

Trajectory Forecasting

Space-Time-Separable Graph Convolutional Network for Pose Forecasting

1 code implementation ICCV 2021 Theodoros Sofianos, Alessio Sampieri, Luca Franco, Fabio Galasso

For the first time, STS-GCN models the human pose dynamics only with a graph convolutional network (GCN), including the temporal evolution and the spatial joint interaction within a single-graph framework, which allows the cross-talk of motion and spatial correlations.

Human Pose Forecasting STS +2

Cluster-driven Graph Federated Learning over Multiple Domains

no code implementations29 Apr 2021 Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, Barbara Caputo

Clustering may reduce heterogeneity by identifying the domains, but it deprives each cluster model of the data and supervision of others.

Clustering Federated Learning

Adversarial Branch Architecture Search for Unsupervised Domain Adaptation

1 code implementation12 Feb 2021 Luca Robbiano, Muhammad Rameez Ur Rahman, Fabio Galasso, Barbara Caputo, Fabio Maria Carlucci

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.

Model Selection Neural Architecture Search +1

SF-UDA$^{3D}$: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection

1 code implementation16 Oct 2020 Cristiano Saltori, Stéphane Lathuiliére, Nicu Sebe, Elisa Ricci, Fabio Galasso

In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e. g., point density variations).

3D Object Detection Object +2

Class Interference Regularization

no code implementations4 Sep 2020 Bharti Munjal, Sikandar Amin, Fabio Galasso

In experimental evaluation, the combination of CIR and a plain Siamese-net with triplet loss yields best few-shot learning performance on the challenging tieredImageNet.

Face Verification Few-Shot Learning +2

An integrated light management system with real-time light measurement and human perception

no code implementations17 Apr 2020 Theodore Tsesmelis, Irtiza Hasan, Marco Cristani, Alessio Del Bue, Fabio Galasso

Illumination is important for well-being, productivity and safety across several environments, including offices, retail shops and industrial warehouses.

Management

Transformer Networks for Trajectory Forecasting

1 code implementation18 Mar 2020 Francesco Giuliari, Irtiza Hasan, Marco Cristani, Fabio Galasso

In particular, the TF model without bells and whistles yields the best score on the largest and most challenging trajectory forecasting benchmark of TrajNet.

Trajectory Forecasting

Knowledge Distillation for End-to-End Person Search

1 code implementation3 Sep 2019 Bharti Munjal, Fabio Galasso, Sikandar Amin

We employ this to supervise the detector of our person search model at various levels using a specialized detector.

Knowledge Distillation Model Compression +3

Query-guided End-to-End Person Search

1 code implementation CVPR 2019 Bharti Munjal, Sikandar Amin, Federico Tombari, Fabio Galasso

We extend this with i. a query-guided Siamese squeeze-and-excitation network (QSSE-Net) that uses global context from both the query and gallery images, ii.

Human Detection Person Search +1

Human-centric light sensing and estimation from RGBD images: The invisible light switch

no code implementations30 Jan 2019 Theodore Tsesmelis, Irtiza Hasan, Marco Cristani, Alessio Del Bue, Fabio Galasso

ILS may therefore dim those luminaires, which are not seen by the user, resulting in an effective energy saving, especially in large open offices (where light may otherwise be ON everywhere for a single person).

RGBD2lux: Dense light intensity estimation with an RGBD sensor

no code implementations20 Sep 2018 Theodore Tsesmelis, Irtiza Hasan, Marco Cristani, Fabio Galasso, Alessio Del Bue

The proposed method uses both depth data and images from the sensor to provide a dense measure of light intensity in the field of view of the camera.

MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses

no code implementations CVPR 2018 Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Alessio Del Bue, Fabio Galasso, Marco Cristani

Recent approaches on trajectory forecasting use tracklets to predict the future positions of pedestrians exploiting Long Short Term Memory (LSTM) architectures.

Trajectory Forecasting

Adversarial Network Compression

no code implementations28 Mar 2018 Vasileios Belagiannis, Azade Farshad, Fabio Galasso

Neural network compression has recently received much attention due to the computational requirements of modern deep models.

Neural Network Compression Transfer Learning

Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation

no code implementations CVPR 2014 Fabio Galasso, Margret Keuper, Thomas Brox, Bernt Schiele

In contrast to previous work, the reduced graph is reweighted such that the resulting segmentation is equivalent, under certain assumptions, to that of the full graph.

Clustering Segmentation +3

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