Niccolò Biondi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Niccolò Biondi has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Alberto Del Bimbo
University of Florence, Florence, Italy
10 shared publications - Federico Pernici
University of Florence
8 shared publications - Simone Ricci
University of Florence
5 shared publications - Marco Bertini
MICC, University of Florence, Florence, Italy
4 shared publications - Matteo Bruni
Università degli studi di Firenze
4 shared publications - Dimosthenis Karatzas
Computer Vision Center
3 shared publications
Latest Publications
- Open Access
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 229-240
Improving Generalization in AI-Generated Facial Image Detection via Explainable Recovery
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 229-240
Open AccessImproving Generalization in AI-Generated Facial Image Detection via Explainable Recovery
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-13
A Stationary (And Therefore Compatible) Representation is All You Need
Learning compatible representations aims to learn feature representations that can be used interchangeably over time whenever a model undergoes updates. In this paper, we demonstrate that stationary representations learned by $d$-Simplex fixed classifiers imply compatibility as in its formal definition. This result establishes a foundation for future works and can be directly exploited in practical learning scenarios. We address the challenge of learning compatibility using $d$-Simplex fixed classifiers when the model is sequentially fine-tuned. Learning according to a $d$-Simplex fixed classifier with the cross-entropy loss aligns feature distributions at the first-order statistics. Consequently, it may not fully capture higher-order dependencies in the representation between model updates. To address this issue, we demonstrate that training the model using a $d$-Simplex fixed classifier through a convex combination of the cross-entropy loss and a contrastive loss not only captures higher-order dependencies, but is also equivalent to learning with the cross-entropy under the compatibility constraints. We confirm our findings with extensive experiments also considering a new scenario where a pre-trained model is sequentially fine-tuned and occasionally replaced with an improved model. We show that stationary representations enable uninterrupted retrieval services (without reprocessing gallery images) while improving performance during model updates and replacements, achieving state-of-the-art.
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-13
A Stationary (And Therefore Compatible) Representation is All You Need
Learning compatible representations aims to learn feature representations that can be used interchangeably over time whenever a model undergoes updates. In this paper, we demonstrate that stationary representations learned by $d$-Simplex fixed classifiers imply compatibility as in its formal definition. This result establishes a foundation for future works and can be directly exploited in practical learning scenarios. We address the challenge of learning compatibility using $d$-Simplex fixed classifiers when the model is sequentially fine-tuned. Learning according to a $d$-Simplex fixed classifier with the cross-entropy loss aligns feature distributions at the first-order statistics. Consequently, it may not fully capture higher-order dependencies in the representation between model updates. To address this issue, we demonstrate that training the model using a $d$-Simplex fixed classifier through a convex combination of the cross-entropy loss and a contrastive loss not only captures higher-order dependencies, but is also equivalent to learning with the cross-entropy under the compatibility constraints. We confirm our findings with extensive experiments also considering a new scenario where a pre-trained model is sequentially fine-tuned and occasionally replaced with an improved model. We show that stationary representations enable uninterrupted retrieval services (without reprocessing gallery images) while improving performance during model updates and replacements, achieving state-of-the-art.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13170-13176
FRED: The Florence RGB-Event Drone Dataset
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13170-13176
Open AccessFRED: The Florence RGB-Event Drone Dataset
- Open Access
FRED: The Florence RGB-Event Drone Dataset
Small, fast, and lightweight drones present significant challenges for traditional RGB cameras due to their limitations in capturing fast-moving objects, especially under challenging lighting conditions. Event cameras offer an ideal solution, providing high temporal definition and dynamic range, yet existing benchmarks often lack fine temporal resolution or drone-specific motion patterns, hindering progress in these areas. This paper introduces the Florence RGB-Event Drone dataset (FRED), a novel multimodal dataset specifically designed for drone detection, tracking, and trajectory forecasting, combining RGB video and event streams. FRED features more than 7 hours of densely annotated drone trajectories, using 5 different drone models and including challenging scenarios such as rain and adverse lighting conditions. We provide detailed evaluation protocols and standard metrics for each task, facilitating reproducible benchmarking. The authors hope FRED will advance research in high-speed drone perception and multimodal spatiotemporal understanding.
Open AccessFRED: The Florence RGB-Event Drone Dataset
Small, fast, and lightweight drones present significant challenges for traditional RGB cameras due to their limitations in capturing fast-moving objects, especially under challenging lighting conditions. Event cameras offer an ideal solution, providing high temporal definition and dynamic range, yet existing benchmarks often lack fine temporal resolution or drone-specific motion patterns, hindering progress in these areas. This paper introduces the Florence RGB-Event Drone dataset (FRED), a novel multimodal dataset specifically designed for drone detection, tracking, and trajectory forecasting, combining RGB video and event streams. FRED features more than 7 hours of densely annotated drone trajectories, using 5 different drone models and including challenging scenarios such as rain and adverse lighting conditions. We provide detailed evaluation protocols and standard metrics for each task, facilitating reproducible benchmarking. The authors hope FRED will advance research in high-speed drone perception and multimodal spatiotemporal understanding.
- 30 May 2025
- Published by Springer Nature
- p. 281-294
An AI-Powered Multimodal Interaction System for Engaging with Digital Art: A Human-Centered Approach to HCI
- 30 May 2025
- Published by Springer Nature
- p. 281-294
An AI-Powered Multimodal Interaction System for Engaging with Digital Art: A Human-Centered Approach to HCI
- 12 May 2025
- Published by Springer Nature
- p. 56-67
ComiCap: A VLMs Pipeline for Dense Captioning of Comic Panels
- 12 May 2025
- Published by Springer Nature
- p. 56-67
ComiCap: A VLMs Pipeline for Dense Captioning of Comic Panels
- 12 May 2025
- Published by Springer Nature
- p. 451-464
Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
- 12 May 2025
- Published by Springer Nature
- p. 451-464
Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11287-11288
Learning Backward Compatible Representations
In today's multimedia-rich environment, the rapid growth of data poses significant challenges for developing efficient multi-modal retrieval systems essential for retrieving text, images, audio, and video. As data expands, newer, scalable, and high-performance retrieval systems are increasingly necessary. Embedding-based deep neural networks (DNNs) have become key solutions, transforming high-dimensional data into lower-dimensional embeddings for easy comparison and retrieval. However, updating DNNs changes the internal feature representations, necessitating the extraction of new feature vectors for all gallery data, which is costly, especially with gallery sets comprising billions of data. Learning backward-compatible representations addresses this by allowing new representation to be matched with old gallery data without recalculating features. This tutorial aims to equip participants with the knowledge and tools to apply backward-compatible representations, enhancing multimedia retrieval systems' efficiency and scalability. Participants will learn the importance of compatible representations, basic methods and techniques, and explore challenging open questions that are becoming increasingly relevant to multimedia and cross-modal retrieval.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11287-11288
Open AccessLearning Backward Compatible Representations
In today's multimedia-rich environment, the rapid growth of data poses significant challenges for developing efficient multi-modal retrieval systems essential for retrieving text, images, audio, and video. As data expands, newer, scalable, and high-performance retrieval systems are increasingly necessary. Embedding-based deep neural networks (DNNs) have become key solutions, transforming high-dimensional data into lower-dimensional embeddings for easy comparison and retrieval. However, updating DNNs changes the internal feature representations, necessitating the extraction of new feature vectors for all gallery data, which is costly, especially with gallery sets comprising billions of data. Learning backward-compatible representations addresses this by allowing new representation to be matched with old gallery data without recalculating features. This tutorial aims to equip participants with the knowledge and tools to apply backward-compatible representations, enhancing multimedia retrieval systems' efficiency and scalability. Participants will learn the importance of compatible representations, basic methods and techniques, and explore challenging open questions that are becoming increasingly relevant to multimedia and cross-modal retrieval.
- Open Access
ComiCap: A VLMs pipeline for dense captioning of Comic Panels
The comic domain is rapidly advancing with the development of single- and multi-page analysis and synthesis models. Recent benchmarks and datasets have been introduced to support and assess models' capabilities in tasks such as detection (panels, characters, text), linking (character re-identification and speaker identification), and analysis of comic elements (e.g., dialog transcription). However, to provide a comprehensive understanding of the storyline, a model must not only extract elements but also understand their relationships and generate highly informative captions. In this work, we propose a pipeline that leverages Vision-Language Models (VLMs) to obtain dense, grounded captions. To construct our pipeline, we introduce an attribute-retaining metric that assesses whether all important attributes are identified in the caption. Additionally, we created a densely annotated test set to fairly evaluate open-source VLMs and select the best captioning model according to our metric. Our pipeline generates dense captions with bounding boxes that are quantitatively and qualitatively superior to those produced by specifically trained models, without requiring any additional training. Using this pipeline, we annotated over 2 million panels across 13,000 books, which will be available on the project page https://github.com/emanuelevivoli/ComiCap.
Open AccessComiCap: A VLMs pipeline for dense captioning of Comic Panels
The comic domain is rapidly advancing with the development of single- and multi-page analysis and synthesis models. Recent benchmarks and datasets have been introduced to support and assess models' capabilities in tasks such as detection (panels, characters, text), linking (character re-identification and speaker identification), and analysis of comic elements (e.g., dialog transcription). However, to provide a comprehensive understanding of the storyline, a model must not only extract elements but also understand their relationships and generate highly informative captions. In this work, we propose a pipeline that leverages Vision-Language Models (VLMs) to obtain dense, grounded captions. To construct our pipeline, we introduce an attribute-retaining metric that assesses whether all important attributes are identified in the caption. Additionally, we created a densely annotated test set to fairly evaluate open-source VLMs and select the best captioning model according to our metric. Our pipeline generates dense captions with bounding boxes that are quantitatively and qualitatively superior to those produced by specifically trained models, without requiring any additional training. Using this pipeline, we annotated over 2 million panels across 13,000 books, which will be available on the project page https://github.com/emanuelevivoli/ComiCap.
- 11 September 2024
- Published by Springer Nature
- p. 154-167
Comics Datasets Framework: Mix of Comics Datasets for Detection Benchmarking
- 11 September 2024
- Published by Springer Nature
- p. 154-167
Comics Datasets Framework: Mix of Comics Datasets for Detection Benchmarking