no code implementations • 6 May 2024 • Massimiliano Pappa, Luca Collorone, Giovanni Ficarra, Indro Spinelli, Fabio Galasso
Instead, it should be confined within the boundaries of text-aligned and realistic generations.
1 code implementation • 17 Apr 2024 • Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, Lamberto Ballan, Fabio Galasso
We propose the first Social Dynamics Adaptation model (SDA) based on the robot's state-action history to infer the social dynamics.
1 code implementation • 2 Apr 2024 • Alessandro Flaborea, Guido Maria D'Amely di Melendugno, Leonardo Plini, Luca Scofano, Edoardo De Matteis, Antonino Furnari, Giovanni Maria Farinella, Fabio Galasso
We propose PREGO, the first online one-class classification model for mistake detection in PRocedural EGOcentric videos.
1 code implementation • 16 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.
Ranked #1 on Human Pose Forecasting on GTA-IM Dataset
1 code implementation • 28 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.
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.
Ranked #1 on Video Anomaly Detection on HR-UBnormal
1 code implementation • 19 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.
Ranked #1 on Source-Free Domain Adaptation on GTA5 to Cityscapes
no code implementations • 17 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.
1 code implementation • 12 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.
1 code implementation • 10 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.
Ranked #61 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • 23 Jan 2023 • Alessandro Flaborea, Guido D'Amely, Stefano D'arrigo, Marco Aurelio Sterpa, Alessio Sampieri, Fabio Galasso
Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls.
Ranked #3 on Video Anomaly Detection on HR-UBnormal
1 code implementation • 16 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.
no code implementations • 21 Sep 2022 • Bharti Munjal, Alessandro Flaborea, Sikandar Amin, Federico Tombari, Fabio Galasso
Few-shot fine-grained classification and person search appear as distinct tasks and literature has treated them separately.
1 code implementation • 24 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.
2 code implementations • 20 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.
2 code implementations • 20 Jul 2022 • Cristiano Saltori, Evgeny Krivosheev, Stéphane Lathuilière, Nicu Sebe, Fabio Galasso, Giuseppe Fiameni, Elisa Ricci, Fabio Poiesi
Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds.
no code implementations • 24 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.
no code implementations • 22 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.
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.
Ranked #1 on Human Pose Forecasting on 3DPW
no code implementations • 29 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.
1 code implementation • 12 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.
1 code implementation • 16 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).
no code implementations • 4 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.
no code implementations • 21 May 2020 • Bharti Munjal, Abdul Rafey Aftab, Sikandar Amin, Meltem D. Brandlmaier, Federico Tombari, Fabio Galasso
Notably, our joint optimization maintains the detector performance, a typical multi-task challenge.
no code implementations • 17 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.
1 code implementation • 18 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.
Ranked #11 on Trajectory Prediction on ETH/UCY
1 code implementation • 3 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.
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.
no code implementations • 30 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).
no code implementations • 7 Jan 2019 • Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, Fabio Galasso
In this work, we explore the correlation between people trajectories and their head orientations.
no code implementations • 20 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.
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.
no code implementations • 28 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.
no code implementations • IEEE Winter Conference on Applications of Computer Vision (WACV) 2018 • Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Alessio Del Bue, Marco Cristani, Fabio Galasso
In this paper we show the importance of the head pose estimation in the task of trajectory forecasting.
no code implementations • 3 Sep 2016 • Wei-Chen Chiu, Fabio Galasso, Mario Fritz
Are we ready to segment consumer stereo videos?
no code implementations • 12 May 2016 • Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele
Graph-based video segmentation methods rely on superpixels as starting point.
no code implementations • CVPR 2015 • Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele
Video segmentation has become an important and active research area with a large diversity of proposed approaches.
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.