Publications

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 can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks.

Industry 4.0 has driven the development of important technologies for industrial applications, but the focus has often been on technological advancement rather than on how operators interact with these systems. With the emergence of Industry 5.0, attention has shifted toward the role of the operators and their interaction with emerging technologies. This paper explores the automation of a fully manual operation in the logistics field while adopting a human-centered approach to reduce risky tasks and enhance the operator’s well-being. A motion capture system and digital human simulation software are utilized to create a digital twin of a real-world industrial case study. This approach enables the virtual testing of various automation solutions to identify the optimal scenario that meets the performance indicator parameters. This study highlights the importance of integrating ergonomic considerations into automation strategies.

This paper tackles the domain of multimodal prompting for visual recognition, specifically when dealing with missing modalities through multimodal Transformers. It presents two main contributions: (i) we introduce a novel prompt learning module which is designed to produce sample-specific prompts and (ii) we show that modality-agnostic prompts can effectively adjust to diverse missing modality scenarios. Our model, termed SCP, exploits the semantic representation of available modalities to query a learnable memory bank, which allows the generation of prompts based on the semantics of the input. Notably, SCP distinguishes itself from existing methodologies for its capacity of self-adjusting to both the missing modality scenario and the semantic context of the input, without prior knowledge about the specific missing modality and the number of modalities. Through extensive experiments, we show the effectiveness of the proposed prompt learning framework and demonstrate enhanced performance and robustness across a spectrum of missing modality cases.

The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of Continual Learning is crucial. While numerous studies focus on skeleton-based action recognition from a traditional offline perspective, only a handful venture into online approaches. In this respect, we introduce CHARON (Continual Human Action Recognition On skeletoNs), which maintains consistent performance while operating within an efficient framework. Through techniques like uniform sampling, interpolation, and a memory-efficient training stage based on masking, we achieve improved recognition accuracy while minimizing computational overhead. Our experiments on Split NTU-60 and the proposed Split NTU-120 datasets demonstrate that CHARON sets a new benchmark in this domain. The code is available at https://github.com/Sperimental3/CHARON.

Barcodes, despite their long history, remain an essential technology in supply chain management. In addition, barcodes have found extensive use in industrial engineering, particularly in warehouse automation, component tracking, and robot guidance. To detect a barcode in an image, multiple algorithms have been proposed in the literature, with a significant increase of interest in the topic since the rise of deep learning. However, research in the field suffers from many limitations, including the scarcity of public datasets and code implementations which hinders the reproducibility and reliability of published results. For this reason, we developed ``BarBeR'' (Barcode Benchmark Repository), a benchmark designed for testing and comparing barcode detection algorithms. This benchmark includes the code implementation of various detection algorithms for barcodes, along with a suite of useful metrics. Among the supported localization methods, there are multiple deep-learning detection models, that will be used to assess the recent contributions of Artificial Intelligence to this field. In addition, we provide a large, annotated dataset of 8748 barcode images, combining multiple public barcode datasets with standardized annotation formats for both detection and segmentation tasks. Finally, we provide a thorough summary of the history and literature on barcode localization and share the results obtained from running the benchmark on our dataset, offering valuable insights into the performance of different algorithms when applied to real-world problems.

Testicular ultrasound imaging is vital for assessing male infertility, with testicular inhomogeneity serving as a key biomarker. However, subjective interpretation and the scarcity of publicly available datasets pose challenges to automated classification. In this study, we explore supervised and unsupervised pretraining strategies using a ResNet-based architecture, supplemented by diffusion-based generative models to synthesize realistic ultrasound images. Our results demonstrate that pretraining significantly enhances classification performance compared to training from scratch, and synthetic data can effectively substitute real images in the pretraining process, alleviating data-sharing constraints. These methods offer promising advancements toward robust, clinically valuable automated analysis of male infertility. The source code is publicly available at https://github.com/AImageLab-zip/TesticulUS/.

Predicting human gaze scanpaths is crucial for understanding visual attention, with applications in human-computer interaction, autonomous systems, and cognitive robotics. While deep learning models have advanced scanpath prediction, most existing approaches generate averaged behaviors, failing to capture the variability of human visual exploration. In this work, we present ScanDiff, a novel architecture that combines diffusion models with Vision Transformers to generate diverse and realistic scanpaths. Our method explicitly models scanpath variability by leveraging the stochastic nature of diffusion models, producing a wide range of plausible gaze trajectories. Additionally, we introduce textual conditioning to enable task-driven scanpath generation, allowing the model to adapt to different visual search objectives. Experiments on benchmark datasets show that ScanDiff surpasses state-of-the-art methods in both free-viewing and task-driven scenarios, producing more diverse and accurate scanpaths. These results highlight its ability to better capture the complexity of human visual behavior, pushing forward gaze prediction research.

The sixth-century Basilica of San Vitale in Ravenna, Italy, once featured intricate circular colored glass windows that illuminated its interior. Although these windows are now lost, several fragments were recovered during recent restorations. Unfortunately, reconstructing the original glass windows from these fragments is extremely complex and time-consuming, requiring the use of specialized expertise. Therefore, the development of automatic reconstruction techniques based on Artificial Intelligence is particularly important and challenging, due to, for instance, the presence of uniform color, damaged glass edges, and many fragment outliers. In this direction, the San Vitale Challenge was organized to gather the best methods and algorithms, as described and summarized in this paper. The challenge, split into several sub-tracks of increasing difficulty and realism, received the submission of several solutions, ranging from more classical computer vision algorithms to purely deep learning-based approaches, whose results are quantitatively evaluated and compared. In the last part of the paper, directions for future developments of such systems are discussed.