Search Results for author:
Found 46 papers, 24 papers with code
Stable-V2A: Synthesis of Synchronized Sound Effects with Temporal and Semantic Controls
Sound designers and Foley artists usually sonorize a scene, such as from a movie or video game, by manually annotating and sonorizing each action of interest in the video.
Gramian Multimodal Representation Learning and Alignment
These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities.
Ranked #1 on
Zero-Shot Audio Retrieval
on AudioCaps
A Wavelet Diffusion GAN for Image Super-Resolution
In recent years, diffusion models have emerged as a superior alternative to generative adversarial networks (GANs) for high-fidelity image generation, with wide applications in text-to-image generation, image-to-image translation, and super-resolution.
Lightweight Diffusion Models for Resource-Constrained Semantic Communication
Despite their impressive ability to regenerate content from the compressed semantic information received, generative models pose crucial challenges for communication systems in terms of high memory footprints and heavy computational load.
Guess What I Think: Streamlined EEG-to-Image Generation with Latent Diffusion Models
Generating images from brain waves is gaining increasing attention due to its potential to advance brain-computer interface (BCI) systems by understanding how brain signals encode visual cues.
Hierarchical Hypercomplex Network for Multimodal Emotion Recognition
Then, a hypercomplex fusion module learns inter-modal relations among the embeddings of the different modalities.
Rethinking Multi-User Semantic Communications with Deep Generative Models
In recent years, novel communication strategies have emerged to face the challenges that the increased number of connected devices and the higher quality of transmitted information are posing.
Language-Oriented Semantic Latent Representation for Image Transmission
In the new paradigm of semantic communication (SC), the focus is on delivering meanings behind bits by extracting semantic information from raw data.
Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning
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 superior results when dealing with multidimensional signals in real-world 3D and 4D paradigms.
Concrete Dense Network for Long-Sequence Time Series Clustering
Time series clustering is fundamental in data analysis for discovering temporal patterns.
JOSENet: A Joint Stream Embedding Network for Violence Detection in Surveillance Videos
Compared to other action recognition tasks, violence detection in surveillance videos presents additional issues, such as the wide variety of real fight scenes.
NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement
Real-world documents may suffer various forms of degradation, often resulting in lower accuracy in optical character recognition (OCR) systems.
Ranked #1 on
Binarization
on DIBCO 2019
Ship in Sight: Diffusion Models for Ship-Image Super Resolution
In this context, our method explores in depth the problem of ship image super resolution, which is crucial for coastal and port surveillance.
Ranked #1 on
Image Super-Resolution
on ShipSpotting
Towards Explaining Hypercomplex Neural Networks
To achieve this, we define a type of cosine-similarity transform within the parameterized hypercomplex domain.
Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality
The primary goal of the L3DAS23 Signal Processing Grand Challenge at ICASSP 2023 is to promote and support collaborative research on machine learning for 3D audio signal processing, with a specific emphasis on 3D speech enhancement and 3D Sound Event Localization and Detection in Extended Reality applications.
Audio Signal Processing
Sound Event Localization and Detection
+1
Generative AI Meets Semantic Communication: Evolution and Revolution of Communication Tasks
Disclosing generative models capabilities in semantic communication paves the way for a paradigm shift with respect to conventional communication systems, which has great potential to reduce the amount of data traffic and offers a revolutionary versatility to novel tasks and applications that were not even conceivable a few years ago.
GATSY: Graph Attention Network for Music Artist Similarity
The artist similarity quest has become a crucial subject in social and scientific contexts.
SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality.
Generalizing Medical Image Representations via Quaternion Wavelet Networks
The proposed quaternion wavelet network (QUAVE) can be easily integrated with any pre-existing medical image analysis or synthesis task, and it can be involved with real, quaternion, or hypercomplex-valued models, generalizing their adoption to single-channel data.
Hypercomplex Multimodal Emotion Recognition from EEG and Peripheral Physiological Signals
Multimodal emotion recognition from physiological signals is receiving an increasing amount of attention due to the impossibility to control them at will unlike behavioral reactions, thus providing more reliable information.
PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functions
Neural models based on hypercomplex algebra systems are growing and prolificating for a plethora of applications, ranging from computer vision to natural language processing.
Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling
To overcome these limitations, we employ a dual quaternion representation of rigid motions in the 3D space that jointly describes rotations and translations of point sets, processing each of the points as a single entity.
Attention-Map Augmentation for Hypercomplex Breast Cancer Classification
In this step, a parameterized hypercomplex neural network (PHNN) is employed to perform breast cancer classification.
Breast Cancer Histology Image Classification
Breast Tumour Classification
+4
Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview
Semantic communication is poised to play a pivotal role in shaping the landscape of future AI-driven communication systems.
Generative Semantic Communication: Diffusion Models Beyond Bit Recovery
We prove, through an in-depth assessment of multiple scenarios, that our method outperforms existing solutions in generating high-quality images with preserved semantic information even in cases where the received content is significantly degraded.
StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation
We test our model on aerial images of the DroneVeichle dataset containing RGB-IR paired images.
Hypercomplex Image-to-Image Translation
Image-to-image translation (I2I) aims at transferring the content representation from an input domain to an output one, bouncing along different target domains.
Ranked #3 on
Image-to-Image Translation
on CelebA-HQ
Multi-View Hypercomplex Learning for Breast Cancer Screening
To overcome such limitations, in this paper, we propose a methodological approach for multi-view breast cancer classification based on parameterized hypercomplex neural networks.
Ranked #1 on
Cancer-no cancer per breast classification
on InBreast
(using extra training data)
Learning Speech Emotion Representations in the Quaternion Domain
On the one hand, the classifier permits to optimize each latent axis of the embeddings for the classification of a specific emotion-related characteristic: valence, arousal, dominance and overall emotion.
Dual Quaternion Ambisonics Array for Six-Degree-of-Freedom Acoustic Representation
We show that our dual quaternion SELD model with temporal convolution blocks (DualQSELD-TCN) achieves better results with respect to real and quaternion-valued baselines thanks to our augmented representation of the sound field.
Ranked #1 on
Sound Event Localization and Detection
on L3DAS21
L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment
The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like environments.
PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
In this paper, we define the parameterization of hypercomplex convolutional layers and introduce the family of parameterized hypercomplex neural networks (PHNNs) that are lightweight and efficient large-scale models.
Ranked #1 on
Sound Event Detection
on L3DAS21
A New Class of Efficient Adaptive Filters for Online Nonlinear Modeling
In order to make this class of functional link adaptive filters (FLAFs) efficient, we propose low-complexity expansions and frequency-domain adaptation of the parameters.
Quaternion Generative Adversarial Networks
Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring extensive computational capabilities.
Ranked #1 on
Image Generation
on Oxford 102 Flowers 128x128
L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing
The L3DAS21 Challenge is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization and detection (SELD).
A Quaternion-Valued Variational Autoencoder
Deep probabilistic generative models have achieved incredible success in many fields of application.
Combined Sparse Regularization for Nonlinear Adaptive Filters
Nonlinear adaptive filters often show some sparse behavior due to the fact that not all the coefficients are equally useful for the modeling of any nonlinearity.
A Multimodal Deep Network for the Reconstruction of T2W MR Images
In this paper, we present a deep learning method that is able to reconstruct subsampled MR images obtained by reducing the k-space data, while maintaining a high image quality that can be used to observe brain lesions.
Compressing deep quaternion neural networks with targeted regularization
To this end, we investigate two extensions of l1 and structured regularization to the quaternion domain.
Widely Linear Kernels for Complex-Valued Kernel Activation Functions
Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain.
Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events
Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity.
Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions
Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data.
Improving Graph Convolutional Networks with Non-Parametric Activation Functions
Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e. g., citation networks or knowledge graphs.
Group Sparse Regularization for Deep Neural Networks
In this paper, we consider the joint task of simultaneously optimizing (i) the weights of a deep neural network, (ii) the number of neurons for each hidden layer, and (iii) the subset of active input features (i. e., feature selection).
Effective Blind Source Separation Based on the Adam Algorithm
In this paper, we derive a modified InfoMax algorithm for the solution of Blind Signal Separation (BSS) problems by using advanced stochastic methods.
Learning activation functions from data using cubic spline interpolation
Neural networks require a careful design in order to perform properly on a given task.
