ABaldrati
Ph.D. student at Media Integration and Communication Center (@miccunifi ) - University of Pisa/University of Florence
University of Florence - MICC, University of PisaFlorence, Italy
Pinned Repositories
AugmentBrain
In AugmentBrain we investigate the performance of different data augmentation methods for the classification of Motor Imagery (MI) data using a Convolutional Neural Network tailored for EEG named EEGNet.
CLIP4Cir
[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
CLIP4CirDemo
[CVPR 2022 - Demo Track] - Effective conditioned and composed image retrieval combining CLIP-based features
dawntime
https://reddeadrecovery.gitlab.io/dawntime/ In dawntime we implement a volumetric light scattering effect based on the postprocessing technique described by Kenny Mitchell.
facestretch
In facestretch we describe how we exploited the dlib’s facial landmarks in order to measure face deformation and perform an expression recognition task. We implemented multiple approaches, based metric learning, neural networks and geodesic distances
MT-BERT
In MT-BERT we reproduce a neural language understanding model which implements a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple NLU tasks.
SupeRAuGAN
In SupeRAuGAN we implement a novel data augmentation technique tailored to Generative Adversarial Networks in order to reduce discriminator overfitting and stabilize training
multimodal-garment-designer
This is the official repository for the paper "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing". ICCV 2023
ladi-vton
This is the official repository for the paper "LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On". ACM Multimedia 2023
SEARLE
[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion
ABaldrati's Repositories
ABaldrati/CLIP4Cir
[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
ABaldrati/CLIP4CirDemo
[CVPR 2022 - Demo Track] - Effective conditioned and composed image retrieval combining CLIP-based features
ABaldrati/AugmentBrain
In AugmentBrain we investigate the performance of different data augmentation methods for the classification of Motor Imagery (MI) data using a Convolutional Neural Network tailored for EEG named EEGNet.
ABaldrati/MT-BERT
In MT-BERT we reproduce a neural language understanding model which implements a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple NLU tasks.
ABaldrati/dawntime
https://reddeadrecovery.gitlab.io/dawntime/ In dawntime we implement a volumetric light scattering effect based on the postprocessing technique described by Kenny Mitchell.
ABaldrati/facestretch
In facestretch we describe how we exploited the dlib’s facial landmarks in order to measure face deformation and perform an expression recognition task. We implemented multiple approaches, based metric learning, neural networks and geodesic distances
ABaldrati/SupeRAuGAN
In SupeRAuGAN we implement a novel data augmentation technique tailored to Generative Adversarial Networks in order to reduce discriminator overfitting and stabilize training