Andrea Prati

HTR-MB: Combining Mamba and BiLSTM for Handwritten Text Recognition

Filippo Botti, Vittorio Bernuzzi, Tomaso Fontanini, Massimo Bertozzi et autres

Handwritten Text Recognition (HTR) aims to automatically transcribe text from manuscript images. The current state-of-the-art methods leverage Transformers for this task. Nevertheless, Transformers have quadratic complexity w.r.t. sequence length and the non-monotonic nature of self-attention conflicts with the inherently left-to-right, monotonic alignment …

it (code pays fourni par la source)

Machine learning-assisted development of a fast Mechanochemical Johnson–Corey–Chaykovsky reaction

Francesco Mele, Ana Maria Constantin, Marco Barezzi, Leonardo Rossi et autres

Herein, we combine Bayesian Optimization and mechanochemistry to develop a rapid, solvent-free protocol for the Johnson–Corey–Chaykovsky (JCC) cyclopropanation and epoxidation. By prioritizing efficiency and sustainability, Machine Learning quickly identified a new set of reaction conditions for this venerable reaction that diverge from …

it (code pays fourni par la source)

Machine learning-assisted development of a fast Mechanochemical Johnson–Corey–Chaykovsky reaction

Francesco Mele, Ana M. Constantin, Marco Barezzi, Leonardo Rossi et autres

Abstract The Johnson-Corey-Chaykovsky reaction stands as an elegant approach for the synthesis of cyclopropanes and epoxides. However, most procedures still rely on the original NaH/DMSO conditions, which pose notable safety and handling issues especially in view of industrial applications. Herein, we combine …

SISMA: Semantic Face Image Synthesis with Mamba

Filippo Botti, Alex Ergasti, Tomaso Fontanini, Claudio Ferrari et autres

it (code pays fourni par la source)

Revisiting Text-Guided Style Transfer Through Mamba: A Fast and Memory-Efficient Architecture

Filippo Botti, Teresa Calzetti, Alex Ergasti, Tomaso Fontanini et autres

Text-guided style transfer aims to stylize a content image according to a textual description while preserving the image structure. Unfortunately, many recent approaches rely on either attention-based fusion or diffusion backbones. On one hand, transformers require high memory consumption due to their …

it (code pays fourni par la source)

TECMO: Efficient Te mporal C ross-Interaction Mo dule for Long Synchronized Audio-Video Generation

Alex Ergasti, Giuseppe Tarollo, Filippo Botti, Tomaso Fontanini et autres

it (code pays fourni par la source)

Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search

Alex Ergasti, Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi et autres

it (code pays fourni par la source)

Mcgm-styler: free-form styler for mask conditional text-to-image generative model

Rami Skaik, Leonardo Rossi, Tomaso Fontanini, Andrea Prati

Abstract Generative models for text-to-image synthesis have made significant advancements in recent years, enabling the creation of highly detailed and stylistically diverse images. In this work, we introduce MCGM-Styler, an extension of our previous MCGM as reported (MCGM: Mask conditional text-to-image generative …

it (code pays fourni par la source)

SISMA: Semantic Face Image Synthesis with Mamba

Filippo Botti, Alex Ergasti, Tomaso Fontanini, Claudio Ferrari et autres

Diffusion Models have become very popular for Semantic Image Synthesis (SIS) of human faces. Nevertheless, their training and inference is computationally expensive and their computational requirements are high due to the quadratic complexity of attention layers. In this paper, we propose a …

U-Shape Mamba: State Space Model for Faster Diffusion

Alex Ergasti, Filippo Botti, Tomaso Fontanini, Claudio Ferrari et autres

Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion model that leverages Mamba-based layers within a U-Net-like …

it (code pays fourni par la source)

$^R$FLAV: Rolling Flow matching for infinite Audio Video generation

Alex Ergasti, Giuseppe Tarollo, Filippo Botti, Tomaso Fontanini et autres

Joint audio-video (AV) generation is still a significant challenge in generative AI, primarily due to three critical requirements: quality of the generated samples, seamless multimodal synchronization and temporal coherence, with audio tracks that match the visual data and vice versa, and limitless …

MARS: Paying More Attention to Visual Attributes for Text-Based Person Search

Alex Ergasti, Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi et autres

Text-Based Person Search (TBPS) is a problem that gained significant interest within the research community. The task is that of retrieving one or more images of a specific individual based on a textual description. The multi-modal nature of the task requires learning …

it (code pays fourni par la source)