Mattia Gatti

Dr. Mattia Gatti

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Mattia GattiMattia Gatti
Mattia Gatti
ARAnwar Ur Rehman
Anwar Ur Rehman
IGNAZIO GALLOIGNAZIO GALLO
IGNAZIO GALLO
This study addresses the challenge of ensuring order accuracy in the dynamic environment of industrial food packaging through a novel zero-shot learning framework. The fundamental limitations of conventional systems, which rely heavily on pre-defined food categories, require a flexible approach capable of adapting to unseen and new food items. Our approach leverages the CLIP model for its efficient capability to semantically match text descriptions with image content, alongside YOLO’s robust object detection abilities, to ensure accurate order fulfilment without prior knowledge of the food items. To assess the effectiveness of this approach, we introduced the Food Recognition dataset, comprising multi-compartment food packages with annotated food items, uniquely representing a variety of complex Italian recipes. Our CLIP-based approach can understand if a specific food name is represented by an image with a precision of 92.92% and a recall of 76.65% on the FR dataset, showcasing the model’s effectiveness in recognizing and validating diverse food items in real-time scenarios. Furthermore, experiments conducted on 1000 entire food packages showed that our framework can detect whether a user’s order matches the package contents with an accuracy of 85.86%. These results underline the potential of employing semantic image-text matching approaches to improve the efficiency of food packaging processes.

18 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Mattia GattiMattia Gatti
Mattia Gatti
ARAnwar Ur Rehman
Anwar Ur Rehman
IGNAZIO GALLOIGNAZIO GALLO
IGNAZIO GALLO
This study addresses the challenge of ensuring order accuracy in the dynamic environment of industrial food packaging through a novel zero-shot learning framework. The fundamental limitations of conventional systems, which rely heavily on pre-defined food categories, require a flexible approach capable of adapting to unseen and new food items. Our approach leverages the CLIP model for its efficient capability to semantically match text descriptions with image content, alongside YOLO’s robust object detection abilities, to ensure accurate order fulfilment without prior knowledge of the food items. To assess the effectiveness of this approach, we introduced the Food Recognition dataset, comprising multi-compartment food packages with annotated food items, uniquely representing a variety of complex Italian recipes. Our CLIP-based approach can understand if a specific food name is represented by an image with a precision of 92.92% and a recall of 76.65% on the FR dataset, showcasing the model’s effectiveness in recognizing and validating diverse food items in real-time scenarios. Furthermore, experiments conducted on 1000 entire food packages showed that our framework can detect whether a user’s order matches the package contents with an accuracy of 85.86%. These results underline the potential of employing semantic image-text matching approaches to improve the efficiency of food packaging processes.

16 July 2026 in Journal of Computational Social Science
Verified
Journal Article
Open access
PDF file
Mattia GattiMattia Gatti
Mattia Gatti
IGNAZIO GALLOIGNAZIO GALLO
IGNAZIO GALLO
GMGiuseppe Muti
Giuseppe Muti
This study investigates the Italian odonymic landscape through the lens of critical toponymy, employing computational methods for semantic classification to examine gendered patterns of commemoration in street naming. A national-scale database is constructed by integrating official toponymic registers with rule-based heuristic procedures and large language model-based classification. This hybrid infrastructure enables the systematic identification and categorization of odonyms dedicated to individual and collective persons, with particular attention to gender representation. The combined classification approach reliably detects personal commemorations and infers gender attributes, yielding results that closely align with manually curated datasets. The study also advances critical toponymy by showing how computational methods can operationalize analyses of collective memory and symbolic power in urban space. The results reveal the persistent gender asymmetries in Italian commemorative odonymy.

9 September 2026 in Intelligence-Based Medicine
Verified
Journal Article
Open access
IGNAZIO GALLOIGNAZIO GALLO
IGNAZIO GALLO
Mattia GattiMattia Gatti
Mattia Gatti
LSLeonardo Sgroi
Leonardo Sgroi
Silvia Elena CorchsSilvia Elena Corchs
Silvia Elena Corchs