activity
20172025
most citedExploring the Representational Power of Graph Autoencoder

6 citations · 14 across the 7 of their papers we have counts for

collaborators

8 papers

cs.LG20251 cited

A Geometric Perspective for High-Dimensional Multiplex Graphs

Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa

High-dimensional multiplex graphs are characterized by their high number of complementary and divergent dimensions. The existence of multiple hierarchical latent relations between…

cs.CV2022

Graph Attention Network for Camera Relocalization on Dynamic Scenes

Mohamed Amine Ouali, Mohamed Bouguessa, Riadh Ksantini

We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previou…

cs.LG20211 cited

TopoDetect: Framework for Topological Features Detection in Graph Embeddings

Maroun Haddad, Mohamed Bouguessa

TopoDetect is a Python package that allows the user to investigate if important topological features, such as the Degree of the nodes, their Triangle Count, or their Local Clusteri…

cs.LG20216 cited

Exploring the Representational Power of Graph Autoencoder

Maroun Haddad, Mohamed Bouguessa

While representation learning has yielded a great success on many graph learning tasks, there is little understanding behind the structures that are being captured by these embeddi…

cs.CV2021

Context Matters: Self-Attention for Sign Language Recognition

Fares Ben Slimane, Mohamed Bouguessa

This paper proposes an attentional network for the task of Continuous Sign Language Recognition. The proposed approach exploits co-independent streams of data to model the sign lan…

cs.LG20196 cited

Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift

Nairouz Mrabah, Mohamed Bouguessa, Riadh Ksantini

Clustering using deep autoencoders has been thoroughly investigated in recent years. Current approaches rely on simultaneously learning embedded features and clustering the data po…