65 citations · 135 across the 18 of their papers we have counts for
19 papers · 1 filter
Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation
Federico Nocentini, Claudio Ferrari, Stefano Berretti
This paper presents a novel approach for generating 3D talking heads from raw audio inputs. Our method grounds on the idea that speech related movements can be comprehensively and…
4DSR-GCN: 4D Video Point Cloud Upsampling using Graph Convolutional Networks
Lorenzo Berlincioni, Stefano Berretti, Marco Bertini +1
Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e.g., LiDAR in autonomous or assisted driving).…
CAD 3D Model classification by Graph Neural Networks: A new approach based on STEP format
L. Mandelli, S. Berretti
In this paper, we introduce a new approach for retrieval and classification of 3D models that directly performs in the Computer-Aided Design (CAD) format without any conversion to…
The Florence 4D Facial Expression Dataset
F. Principi, S. Berretti, C. Ferrari +3
Human facial expressions change dynamically, so their recognition / analysis should be conducted by accounting for the temporal evolution of face deformations either in 2D or 3D. W…
Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matrices
Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti +3
We propose an automatic method to estimate self-reported pain based on facial landmarks extracted from videos. For each video sequence, we decompose the face into four different re…
Generating Multiple 4D Expression Transitions by Learning Face Landmark Trajectories
Naima Otberdout, Claudio Ferrari, Mohamed Daoudi +2
In this work, we address the problem of 4D facial expressions generation. This is usually addressed by animating a neutral 3D face to reach an expression peak, and then get back to…
What makes you, you? Analyzing Recognition by Swapping Face Parts
Claudio Ferrari, Matteo Serpentoni, Stefano Berretti +1
Deep learning advanced face recognition to an unprecedented accuracy. However, understanding how local parts of the face affect the overall recognition performance is still mostly…
Sparse to Dense Dynamic 3D Facial Expression Generation
Naima Otberdout, Claudio Ferrari, Mohamed Daoudi +2
In this paper, we propose a solution to the task of generating dynamic 3D facial expressions from a neutral 3D face and an expression label. This involves solving two sub-problems:…
Modelling the Statistics of Cyclic Activities by Trajectory Analysis on the Manifold of Positive-Semi-Definite Matrices
Ettore Maria Celozzi, Luca Ciabini, Luca Cultrera +4
In this paper, a model is presented to extract statistical summaries to characterize the repetition of a cyclic body action, for instance a gym exercise, for the purpose of checkin…
Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics
Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti +3
We propose an automatic method for pain intensity measurement from video. For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points.…
A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces
Claudio Ferrari, Stefano Berretti, Pietro Pala +1
The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face shapes. To build a 3DMM, a training set of face scans in full point-to-point correspondence is…
Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition
Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti +3
In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences. Our approach lies in the continuity of recent works representing vid…
Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
Naima Otberdout, Mohamed Daoudi, Anis Kacem +2
In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image. We propose to exploit the face geometry by modeling…
Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection
Bilal Taha, Munawar Hayat, Stefano Berretti +1
This paper proposes an approach to learn generic multi-modal mesh surface representations using a novel scheme for fusing texture and geometric data. Our approach defines an invers…
Additional Baseline Metrics for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification"
Claudio Ferrari, Stefano Berretti, Alberto Del Bimbo
In this report, we provide additional and corrected results for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification". After further investig…
Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories
Naima Otberdout, Anis Kacem, Mohamed Daoudi +2
In this paper, we propose a new approach for facial expression recognition using deep covariance descriptors. The solution is based on the idea of encoding local and global Deep Co…
A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding
Anis Kacem, Mohamed Daoudi, Boulbaba Ben Amor +2
In this paper, we propose a novel space-time geometric representation of human landmark configurations and derive tools for comparison and classification. We model the temporal evo…
Deep Covariance Descriptors for Facial Expression Recognition
Naima Otberdout, Anis Kacem, Mohamed Daoudi +2
In this paper, covariance matrices are exploited to encode the deep convolutional neural networks (DCNN) features for facial expression recognition. The space geometry of the covar…
Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices
Mohamed Daoudi, Stefano Berretti, Pietro Pala +2
Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations. Much of the Computer Vision research in this field has focuse…