Search Results for author: Boulbaba Ben Amor

Found 11 papers, 1 papers with code

G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation

no code implementations22 Jun 2021 Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang

In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

no code implementations22 Jun 2021 Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang

Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.

Time Series Time Series Alignment

ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks

no code implementations16 Feb 2021 Boulbaba Ben Amor, Sylvain Arguillère, Ling Shao

In deformable registration, the geometric framework - large deformation diffeomorphic metric mapping or LDDMM, in short - has inspired numerous techniques for comparing, deforming, averaging and analyzing shapes or images.

Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition

no code implementations8 Aug 2019 Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor

The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors.

Action Recognition Dictionary Learning +4

A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding

no code implementations29 Jun 2018 Anis Kacem, Mohamed Daoudi, Boulbaba Ben Amor, Stefano Berretti, Juan Carlos Alvarez-Paiva

We derived then geometric and computational tools for rate-invariant analysis and adaptive re-sampling of trajectories, grounding on the Riemannian geometry of the underlying manifold.

Action Recognition Emotion Recognition +3

Coding Kendall's Shape Trajectories for 3D Action Recognition

no code implementations CVPR 2018 Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor

Grounding on the Riemannian geometry of the shape space, an intrinsic sparse coding and dictionary learning formulation is proposed for static skeletal shapes to overcome the inherent non-linearity of the manifold.

3D Action Recognition Dictionary Learning +2

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