Filippo Principi

Dr. Filippo Principi

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
15 April 2024
Verified
Conference Paper
Open access
PRPavan Kartheek Rachabatuni
Pavan Kartheek Rachabatuni
FPFilippo Principi
Filippo Principi
PMPaolo Mazzanti
Paolo Mazzanti
Marco BertiniMarco Bertini
Marco Bertini
Multi-modal Large Language Models (MLLMs) are currently an extremely active research topic for the multimedia and computer vision communities, and show a significant impact in visual analysis and text generation tasks. MLLM's are well-versed in integrated understanding, analysis of complex data from cross modalities (i.e. text-image) and text generation with chat abilities. Almost all MLLM's, focus on alignment of image features to textual features for downstream text generation tasks includes detailed image description, visual question answering, stories and poems generation, phrase grounding, etc.. However, when focusing on visual question answering, questions that are highly relevant to the context of an image may not be answered correctly with the existing MLLM's, contrary to questions that are related to visual aspects. Moreover, generating meta data (context) for an image using present day MLLM's is hard task due to hallucinating characteristic of underlying Large Language Models (LLM's), and adequate contextual information cannot be directly derived from an image based perspective. Considering the cultural heritage domain, these issues hamper the introduction of multimedia chatbots as tools to support learning and understanding artworks, since contextual information is typically needed to better understand the content of the artworks themselves, and museum curators require that scientifically accurate information is provided to the users of such systems. In this paper we present a system that combines contextual description of the artworks to enhance the contextual visual question answering task.

14 July 2025 in Heritage
Verified
Journal Article
Open access
PDF file
PMPaolo Mazzanti
Paolo Mazzanti
AFAndrea Ferracani
Andrea Ferracani
Marco BertiniMarco Bertini
Marco Bertini
FPFilippo Principi
Filippo Principi
This paper presents the ReInHerit Toolkit, a collection of open-source interactive applications developed as part of the H2020 ReInHerit project. Informed by extensive surveys and focus groups with cultural professionals across Europe, the toolkit addresses key needs in the heritage sector by leveraging computer vision and artificial intelligence to enrich museum experiences through engaging, personalized interactions that enhance visitor learning. Designed to bridge the technology gap between larger institutions and smaller organizations, the ReInHerit Toolkit also promotes a sustainable, people-centered approach to digital innovation, supported by shared resources, training, and collaborative development opportunities accessible through the project’s Digital Hub.

28 October 2024
Verified
Conference Paper
Open access
AFAndrea Ferracani
Andrea Ferracani
Marco BertiniMarco Bertini
Marco Bertini
PPPietro Pala
Pietro Pala
GNGabriele Nannotti
Gabriele Nannotti
FPFilippo Principi
Filippo Principi
GBGiuseppe Becchi
Giuseppe Becchi
This paper presents a mobile application that exploits interactive narrative storytelling through GPT-4 and a custom image generative pipeline to improve cultural tourism experiences. The application helps tourists visiting cities to program and personalize cultural city tours creating stories with the user as the protagonist. The app guides the users to choose Point-Of-Interests (POIs) and narrative genres of the narrative while the image generation pipeline provides them with visual and coherent representations of their actions in the story contributing to a more immersive and personalized experience. Technical challenges include producing coherent stories and real-time and quality images, maintaining visual composition and person identity, including multiple concepts, through prompt engineering. We validate the effectiveness of the application and the image generative pipeline through users studies which evaluate the educational potential of our approach.

4 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
PMPaolo Mazzanti
Paolo Mazzanti
AFAndrea Ferracani
Andrea Ferracani
Marco BertiniMarco Bertini
Marco Bertini
FPFilippo Principi
Filippo Principi
This paper presents the ReInHerit Toolkit, a collection of open-source interactive applications developed as part of the H2020 ReInHerit project. Informed by extensive surveys and focus groups with cultural professionals across Europe, the toolkit addresses key needs in the heritage sector by leveraging computer vision and artificial intelligence to enrich museum experiences through engaging, personalized interactions that enhance visitor learning. Designed to bridge the technology gap between larger institutions and smaller organizations, the ReInHerit Toolkit also promotes a sustainable, peoplecentered approach to digital innovation, supported by shared resources, training, and collaborative development opportunities accessible through the project’s Digital Hub.

11 December 2024
Verified
Book Chapter
Closed access
PDF file
PRPavan K. Rachabathuni
Pavan K. Rachabathuni
PMPaolo Mazzanti
Paolo Mazzanti
FPFilippo Principi
Filippo Principi
AFAndrea Ferracani
Andrea Ferracani
Marco BertiniMarco Bertini
Marco Bertini