37 citations · 146 across the 33 of their papers we have counts for
10 papers · 1 filter
Closing the Modality Gap Aligns Group-Wise Semantics
Eleonora Grassucci, Giordano Cicchetti, Emanuele Frasca +2
In multimodal learning, CLIP has been recognized as the \textit{de facto} method for learning a shared latent space across multiple modalities, placing similar representations clos…
A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
Giordano Cicchetti, Eleonora Grassucci, Danilo Comminiello
Multimodal learning plays a pivotal role in advancing artificial intelligence systems by incorporating information from multiple modalities to build a more comprehensive representa…
Training-Free Multimodal Guidance for Video to Audio Generation
Eleonora Grassucci, Giuliano Galadini, Giordano Cicchetti +3
Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, an…
Semantic Compression via Multimodal Representation Learning
Eleonora Grassucci, Giordano Cicchetti, Aurelio Uncini +1
Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also in…
Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning
Danilo Comminiello, Eleonora Grassucci, Danilo P. Mandic +1
Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their super…
PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functions
Matteo Mancanelli, Eleonora Grassucci, Aurelio Uncini +1
Neural models based on hypercomplex algebra systems are growing and prolificating for a plethora of applications, ranging from computer vision to natural language processing. Hand…
Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview
Eleonora Grassucci, Yuki Mitsufuji, Ping Zhang +1
Semantic communication is poised to play a pivotal role in shaping the landscape of future AI-driven communication systems. Its challenge of extracting semantic information from th…
PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
Eleonora Grassucci, Aston Zhang, Danilo Comminiello
Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently,…
Quaternion Generative Adversarial Networks
Eleonora Grassucci, Edoardo Cicero, Danilo Comminiello
Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring e…
A Quaternion-Valued Variational Autoencoder
Eleonora Grassucci, Danilo Comminiello, Aurelio Uncini
Deep probabilistic generative models have achieved incredible success in many fields of application. Among such models, variational autoencoders (VAEs) have proved their ability in…