279 citations · 364 across the 24 of their papers we have counts for
25 papers · 1 filter
Agentic Multimodal Models for Environmental Hyperspectral Unmixing
Michał Cholewa, Luca Ciampi, Nicola Messina +2
Hyperspectral unmixing is a key task in remote sensing that aims to decompose mixed pixels in hyperspectral images into their constituent material signatures, or endmembers, and th…
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Giacomo Pacini, Luca Ciampi, Nicola Messina +3
Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language prompts. However, current ev…
One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara +3
Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption…
Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations
Nicola Messina, Rosario Leonardi, Luca Ciampi +4
Pixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitori…
CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones
Giacomo Pacini, Lorenzo Bianchi, Luca Ciampi +3
Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods…
Towards Identity-Aware Cross-Modal Retrieval: a Dataset and a Baseline
Nicola Messina, Lucia Vadicamo, Leo Maltese +1
Recent advancements in deep learning have significantly enhanced content-based retrieval methods, notably through models like CLIP that map images and texts into a shared embedding…
Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
Luca Barsellotti, Lorenzo Bianchi, Nicola Messina +5
Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP…
Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting
Luca Ciampi, Nicola Messina, Matteo Pierucci +3
Recently, object counting has shifted towards class-agnostic counting (CAC), which counts instances of arbitrary object classes never seen during model training. With advancements…
Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval
Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi +1
Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective conten…
Is CLIP the main roadblock for fine-grained open-world perception?
Lorenzo Bianchi, Fabio Carrara, Nicola Messina +1
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains…
The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Lorenzo Bianchi, Fabio Carrara, Nicola Messina +2
Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during infer…
Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language
Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi +1
Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportuniti…
Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Paweł Foszner, Agnieszka Szczęsna, Luca Ciampi +7
Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or othe…
CrowdSim2: an Open Synthetic Benchmark for Object Detectors
Paweł Foszner, Agnieszka Szczęsna, Luca Ciampi +7
Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systemati…
A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Marco Avvenuti, Marco Bongiovanni, Luca Ciampi +3
Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer…
ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
Nicola Messina, Matteo Stefanini, Marcella Cornia +4
Image-text matching is gaining a leading role among tasks involving the joint understanding of vision and language. In literature, this task is often used as a pre-training objecti…
Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching
Nicola Messina, Davide Alessandro Coccomini, Andrea Esuli +1
With the increased accessibility of web and online encyclopedias, the amount of data to manage is constantly increasing. In Wikipedia, for example, there are millions of pages writ…
Recurrent Vision Transformer for Solving Visual Reasoning Problems
Nicola Messina, Giuseppe Amato, Fabio Carrara +2
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired…
Generative Adversarial Networks for Astronomical Images Generation
Davide Coccomini, Nicola Messina, Claudio Gennaro +1
Space exploration has always been a source of inspiration for humankind, and thanks to modern telescopes, it is now possible to observe celestial bodies far away from us. With a gr…
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
Davide Coccomini, Nicola Messina, Claudio Gennaro +1
Deepfakes are the result of digital manipulation to forge realistic yet fake imagery. With the astonishing advances in deep generative models, fake images or videos are nowadays ob…
Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features
Nicola Messina, Giuseppe Amato, Fabrizio Falchi +2
Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different…
Solving the Same-Different Task with Convolutional Neural Networks
Nicola Messina, Giuseppe Amato, Fabio Carrara +2
Deep learning demonstrated major abilities in solving many kinds of different real-world problems in computer vision literature. However, they are still strained by simple reasonin…
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
Nicola Messina, Giuseppe Amato, Andrea Esuli +3
Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-m…
Transformer Reasoning Network for Image-Text Matching and Retrieval
Nicola Messina, Fabrizio Falchi, Andrea Esuli +1
Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matchi…