Multimédia [MM]

Recherche

Les sujets principaux de recherche sont :

• Codage video linéaire
• Représentation de scènes rich-média
• Multimedia distribution networks
• Adaptation du contenu multimédia
• IA Frugale et efficace
• Geometric deep learning
• Apprentissage multimodale

Membres de l’équipe

• Enzo Tartaglione, Maître de Conférences avec HDR, responsable d’équipe
• Stephan Alaniz, Maître de Conférences
• Jhony Giraldo, Maître de Conférences
• Jean Le Feuvre, Directeur d’Etudes/Professeur
• Jean-Claude Moissinac, Maître de Conférences

Mots-clés

• Compression images et vidéo
• Transport et orchestration des contenus multimédia
• Médias immersifs et interactivité
• Apprentissage profond et modèles génératifs
• IA Frugale et efficace
• Geometric deep learning
• Apprentissage multimodale

News

[Avr 25] Article accepté pour publication à Nature Scientific Reports : Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications. Leonardo Olivi, Edoardo Santero-Mormile, Enzo Tartaglione.

[Avr 25] Article accepté pour publication à TMLR : Piecewise Constant Spectral Graph Neural Network. Vahan Martirosyan, Jhony H. Giraldo, Fragkiskos D. Malliaros. Transactions on Machine Learning Research.

[Avr 25] Stephan Alaniz nous a rejoints en tant que nouveau MdC !

[Mar 25] Article accepté pour publication à IEEE International Conference on Multimedia & Expo (ICME) : Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates. Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo, Marco Grangetto, Wei Hu, Giuseppe Valenzise, Attilio Fiandrotti, Enzo Tartaglione

[Fev 25] Article accepté pour publication:
A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning. Amadou Siaka Sangare, Nicolas Dunou, Jhony H. Giraldo, Fragkiskos D. Malliaros. Transactions on Machine Learning Research.

[Jan 25] Article accepté pour publication:
Graph-based Moving Object Segmentation for underwater videos using semi-supervised learning. Meghna Kapoor, Wieke Prummel, Jhony H. Giraldo, Badri Narayan Subudhi, Anastasia Zakharova, Thierry Bouwmans, Ankur Bansal. Computer Vision and Image Understanding.

[Jan 25] Article accepté pour publication:
STanH: Parametric Quantization for Variable Rate Learned Image Compression. Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti, Marco Grangetto. IEEE Transactions on Image Processing.

[Dec 24] Jhony Giraldo a reçu une allocation GPU par NVIDIA.

[Dec 24] Nous avons eu 2x articles acceptés à la AAAI Conference on Artificial Intelligence (AAAI 25):

• Hygene: A Diffusion-based Hypergraph Generation Method. Dorian Gailhard, Enzo Tartaglione, Lirida Naviner Barros, Jhony H. Giraldo 
• Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers. Zhu Liao, Nour Hezbri, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

[Nov 24] Article accepté pour publication:
Unsupervised Learning of Unbiased Visual Representations. Carlo Alberto Barbano, Enzo Tartaglione, Marco Grangetto. IEEE Transactions on Artificial Intelligence.

[Nov 24] Article accepté pour publication:
Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks. Jhony H. Giraldo, Aref Einizade, Andjela Todorovic, Jhon A. Castro-Correa,  Mohsen Badiey, Thierry Bouwmans, Fragkiskos D. Malliaros. IEEE Transactions on Signal and Information Processing over Networks.

[Oct 24] Nous avons eu 4x articles acceptés à la IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025):

• WiGNet: Windowed Vision Graph Neural Network. Gabriele Spadaro, Marco Grangetto, Attilio Fiandrotti, Enzo Tartaglione, Jhony H. Giraldo
  
• ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting. Muhammad Salman Ali, Sung-Ho Bae, Enzo Tartaglione
• CATALOG: A Camera Trap Language-guided Contrastive Learning Model. Julian Santamaria, Claudia Isaza, Jhony H. Giraldo
• Efficient Progressive Image Compression with Variance-aware Masking. Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti, Marco Grangetto, Pamela Cosman

[Sep 24] Nous avons eu 3x articles acceptés à la 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024):

• An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching. Hugo Malard, Michel Olvera, Stéphane Lathuilière, Slim Essid
• Continuous Product Graph Neural Networks. Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo
• Activation Map Compression through Tensor Decomposition for Deep Learning. Le-Trung Nguyen, Aël Quélennec, Enzo Tartaglione, Samuel Tardieu, Van-Tam Nguyen

Les publications de l’équipe