Fabrizio Falchi

Nicola Messina, Matteo Stefanini, Marcella Cornia et al.

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 objective to forge architectures able to jointly deal with images and texts. Nonetheless, it has a direct downstream application: cross-modal retrieval, which consists in finding images related to a given query text or vice-versa. Solving this task is of critical importance in cross-modal search engines. Many recent methods proposed effective solutions to the image-text matching problem, mostly using recent large vision-language (VL) Transformer networks. However, these models are often computationally expensive, especially at inference time. This prevents their adoption in large-scale cross-modal retrieval scenarios, where results should be provided to the user almost instantaneously. In this paper, we propose to fill in the gap between effectiveness and efficiency by proposing an ALign And DIstill Network (ALADIN). ALADIN first produces high-effective scores by aligning at fine-grained level images and texts. Then, it learns a shared embedding space - where an efficient kNN search can be performed - by distilling the relevance scores obtained from the fine-grained alignments. We obtained remarkable results on MS-COCO, showing that our method can compete with state-of-the-art VL Transformers while being almost 90 times faster. The code for reproducing our results is available at https://github.com/mesnico/ALADIN.

Davide Alessandro Coccomini, Giorgos Kordopatis Zilos, Giuseppe Amato et al.

In this paper, we introduce MINTIME, a video deepfake detection approach that captures spatial and temporal anomalies and handles instances of multiple people in the same video and variations in face sizes. Previous approaches disregard such information either by using simple a-posteriori aggregation schemes, i.e., average or max operation, or using only one identity for the inference, i.e., the largest one. On the contrary, the proposed approach builds on a Spatio-Temporal TimeSformer combined with a Convolutional Neural Network backbone to capture spatio-temporal anomalies from the face sequences of multiple identities depicted in a video. This is achieved through an Identity-aware Attention mechanism that attends to each face sequence independently based on a masking operation and facilitates video-level aggregation. In addition, two novel embeddings are employed: (i) the Temporal Coherent Positional Embedding that encodes each face sequence's temporal information and (ii) the Size Embedding that encodes the size of the faces as a ratio to the video frame size. These extensions allow our system to adapt particularly well in the wild by learning how to aggregate information of multiple identities, which is usually disregarded by other methods in the literature. It achieves state-of-the-art results on the ForgeryNet dataset with an improvement of up to 14% AUC in videos containing multiple people and demonstrates ample generalization capabilities in cross-forgery and cross-dataset settings. The code is publicly available at https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection.

Davide Alessandro Coccomini, Andrea Esuli, Fabrizio Falchi et al.

This paper explores the task of detecting images generated by text-to-image diffusion models. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable Diffusion and GLIDE. Our experiments show that it is possible to detect the generated images using simple Multi-Layer Perceptrons (MLPs), starting from features extracted by CLIP, or traditional Convolutional Neural Networks (CNNs). We also observe that models trained on images generated by Stable Diffusion can detect images generated by GLIDE relatively well, however, the reverse is not true. Lastly, we find that incorporating the associated textual information with the images rarely leads to significant improvement in detection results but that the type of subject depicted in the image can have a significant impact on performance. This work provides insights into the feasibility of detecting generated images, and has implications for security and privacy concerns in real-world applications. The code to reproduce our results is available at: https://github.com/davide-coccomini/Detecting-Images-Generated-by-Diffusers

Luca Ciampi, Nicola Messina, Matteo Pierucci et al.

Recently, object counting has shifted towards class-agnostic counting (CAC), which counts instances of arbitrary object classes never seen during model training. With advancements in robust vision-and-language foundation models, there is a growing interest in prompt-based CAC, where object categories are specified using natural language. However, we identify significant limitations in current benchmarks for evaluating this task, which hinder both accurate assessment and the development of more effective solutions. Specifically, we argue that the current evaluation protocols do not measure the ability of the model to understand which object has to be counted. This is due to two main factors: (i) the shortcomings of CAC datasets, which primarily consist of images containing objects from a single class, and (ii) the limitations of current counting performance evaluators, which are based on traditional class-specific counting and focus solely on counting errors. To fill this gap, we introduce the Prompt-Aware Counting (PrACo) benchmark. It comprises two targeted tests coupled with evaluation metrics specifically designed to quantitatively measure the robustness and trustworthiness of existing prompt-based CAC models. We evaluate state-of-the-art methods and demonstrate that, although some achieve impressive results on standard class-specific counting metrics, they exhibit a significant deficiency in understanding the input prompt, indicating the need for more careful training procedures or revised designs. The code for reproducing our results is available at https://github.com/ciampluca/PrACo.

Davide Alessandro Coccomini, Roberto Caldelli, Giuseppe Amato et al.

Deepfake technology is rapidly advancing, posing significant challenges to the detection of manipulated media content. Parallel to that, some adversarial attack techniques have been developed to fool the deepfake detectors and make deepfakes even more difficult to be detected. This paper explores the application of super resolution techniques as a possible adversarial attack in deepfake detection. Through our experiments, we demonstrate that minimal changes made by these methods in the visual appearance of images can have a profound impact on the performance of deepfake detection systems. We propose a novel attack using super resolution as a quick, black-box and effective method to camouflage fake images and/or generate false alarms on pristine images. Our results indicate that the usage of super resolution can significantly impair the accuracy of deepfake detectors, thereby highlighting the vulnerability of such systems to adversarial attacks. The code to reproduce our experiments is available at: https://github.com/davide-coccomini/Adversarial-Magnification-to-Deceive-Deepfake-Detection-through-Super-Resolution

Davide Alessandro Coccomini, Roberto Caldelli, Fabrizio Falchi et al.

Deepfake Generation Techniques are evolving at a rapid pace, making it possible to create realistic manipulated images and videos and endangering the serenity of modern society. The continual emergence of new and varied techniques brings with it a further problem to be faced, namely the ability of deepfake detection models to update themselves promptly in order to be able to identify manipulations carried out using even the most recent methods. This is an extremely complex problem to solve, as training a model requires large amounts of data, which are difficult to obtain if the deepfake generation method is too recent. Moreover, continuously retraining a network would be unfeasible. In this paper, we ask ourselves if, among the various deep learning techniques, there is one that is able to generalise the concept of deepfake to such an extent that it does not remain tied to one or more specific deepfake generation methods used in the training set. We compared a Vision Transformer with an EfficientNetV2 on a cross-forgery context based on the ForgeryNet dataset. From our experiments, It emerges that EfficientNetV2 has a greater tendency to specialize often obtaining better results on training methods while Vision Transformers exhibit a superior generalization ability that makes them more competent even on images generated with new methodologies.

Donato Cafarelli, Luca Ciampi, Lucia Vadicamo et al.

Modern Unmanned Aerial Vehicles (UAV) equipped with cameras can play an essential role in speeding up the identification and rescue of people who have fallen overboard, i.e., man overboard (MOB). To this end, Artificial Intelligence techniques can be leveraged for the automatic understanding of visual data acquired from drones. However, detecting people at sea in aerial imagery is challenging primarily due to the lack of specialized annotated datasets for training and testing detectors for this task. To fill this gap, we introduce and publicly release the MOBDrone benchmark, a collection of more than 125K drone-view images in a marine environment under several conditions, such as different altitudes, camera shooting angles, and illumination. We manually annotated more than 180K objects, of which about 113K man overboard, precisely localizing them with bounding boxes. Moreover, we conduct a thorough performance analysis of several state-of-the-art object detectors on the MOBDrone data, serving as baselines for further research.

Lorenzo Bianchi, Fabio Carrara, Nicola Messina et al.

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 inference. In this paper, we aim to probe the state-of-the-art methods for open-vocabulary object detection to determine to what extent they understand fine-grained properties of objects and their parts. To this end, we introduce an evaluation protocol based on dynamic vocabulary generation to test whether models detect, discern, and assign the correct fine-grained description to objects in the presence of hard-negative classes. We contribute with a benchmark suite of increasing difficulty and probing different properties like color, pattern, and material. We further enhance our investigation by evaluating several state-of-the-art open-vocabulary object detectors using the proposed protocol and find that most existing solutions, which shine in standard open-vocabulary benchmarks, struggle to accurately capture and distinguish finer object details. We conclude the paper by highlighting the limitations of current methodologies and exploring promising research directions to overcome the discovered drawbacks. Data and code are available at https://lorebianchi98.github.io/FG-OVD/.

Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro et al.

For a long time, biology and neuroscience fields have been a great source of inspiration for computer scientists, towards the development of Artificial Intelligence (AI) technologies. This survey aims at providing a comprehensive review of recent biologically-inspired approaches for AI. After introducing the main principles of computation and synaptic plasticity in biological neurons, we provide a thorough presentation of Spiking Neural Network (SNN) models, and we highlight the main challenges related to SNN training, where traditional backprop-based optimization is not directly applicable. Therefore, we discuss recent bio-inspired training methods, which pose themselves as alternatives to backprop, both for traditional and spiking networks. Bio-Inspired Deep Learning (BIDL) approaches towards advancing the computational capabilities and biological plausibility of current models.

Marco Avvenuti, Marco Bongiovanni, Luca Ciampi et al.

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 vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark.

Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro et al.

Recently emerged technologies based on Deep Learning (DL) achieved outstanding results on a variety of tasks in the field of Artificial Intelligence (AI). However, these encounter several challenges related to robustness to adversarial inputs, ecological impact, and the necessity of huge amounts of training data. In response, researchers are focusing more and more interest on biologically grounded mechanisms, which are appealing due to the impressive capabilities exhibited by biological brains. This survey explores a range of these biologically inspired models of synaptic plasticity, their application in DL scenarios, and the connections with models of plasticity in Spiking Neural Networks (SNNs). Overall, Bio-Inspired Deep Learning (BIDL) represents an exciting research direction, aiming at advancing not only our current technologies but also our understanding of intelligence.

Gabriele Lagani, Davide Bacciu, Claudio Gallicchio et al.

Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired \textit{Hebbian} learning algorithms have shown promises for DNN training. In this contribution, we study the performance of such algorithms in the development of feature extractors for CBIR tasks. Specifically, we consider a semi-supervised learning strategy in two steps: first, an unsupervised pre-training stage is performed using Hebbian learning on the image dataset; second, the network is fine-tuned using supervised Stochastic Gradient Descent (SGD) training. For the unsupervised pre-training stage, we explore the nonlinear Hebbian Principal Component Analysis (HPCA) learning rule. For the supervised fine-tuning stage, we assume sample efficiency scenarios, in which the amount of labeled samples is just a small fraction of the whole dataset. Our experimental analysis, conducted on the CIFAR10 and CIFAR100 datasets shows that, when few labeled samples are available, our Hebbian approach provides relevant improvements compared to various alternative methods.

Nicola Messina, Davide Alessandro Coccomini, Andrea Esuli et al.

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 written in multiple languages. These pages contain images that often lack the textual context, remaining conceptually floating and therefore harder to find and manage. In this work, we present the system we designed for participating in the Wikipedia Image-Caption Matching challenge on Kaggle, whose objective is to use data associated with images (URLs and visual data) to find the correct caption among a large pool of available ones. A system able to perform this task would improve the accessibility and completeness of multimedia content on large online encyclopedias. Specifically, we propose a cascade of two models, both powered by the recent Transformer model, able to efficiently and effectively infer a relevance score between the query image data and the captions. We verify through extensive experimentation that the proposed two-model approach is an effective way to handle a large pool of images and captions while maintaining bounded the overall computational complexity at inference time. Our approach achieves remarkable results, obtaining a normalized Discounted Cumulative Gain (nDCG) value of 0.53 on the private leaderboard of the Kaggle challenge.

Alessio Serra, Fabio Carrara, Maurizio Tesconi et al.

Trends and opinion mining in social media increasingly focus on novel interactions involving visual media, like images and short videos, in addition to text. In this work, we tackle the problem of visual sentiment analysis of social media images -- specifically, the prediction of image sentiment polarity. While previous work relied on manually labeled training sets, we propose an automated approach for building sentiment polarity classifiers based on a cross-modal distillation paradigm; starting from scraped multimodal (text + images) data, we train a student model on the visual modality based on the outputs of a textual teacher model that analyses the sentiment of the corresponding textual modality. We applied our method to randomly collected images crawled from Twitter over three months and produced, after automatic cleaning, a weakly-labeled dataset of $\sim$1.5 million images. Despite exploiting noisy labeled samples, our training pipeline produces classifiers showing strong generalization capabilities and outperforming the current state of the art on five manually labeled benchmarks for image sentiment polarity prediction.

Fabio Carrara, Fabrizio Falchi, Maria Girardi et al.

Thanks to recent advancements in numerical methods, computer power, and monitoring technology, seismic ambient noise provides precious information about the structural behavior of old buildings. The measurement of the vibrations produced by anthropic and environmental sources and their use for dynamic identification and structural health monitoring of buildings initiated an emerging, cross-disciplinary field engaging seismologists, engineers, mathematicians, and computer scientists. In this work, we employ recent deep learning techniques for time-series forecasting to inspect and detect anomalies in the large dataset recorded during a long-term monitoring campaign conducted on the San Frediano bell tower in Lucca. We frame the problem as an unsupervised anomaly detection task and train a Temporal Fusion Transformer to learn the normal dynamics of the structure. We then detect the anomalies by looking at the differences between the predicted and observed frequencies.

Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi et al.

Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a challenging problem. In this paper, we focus on the recently introduced text-motion retrieval tasks, which aim to search for database motions that are the most relevant to a specified natural-language textual description (text-to-motion) and vice-versa (motion-to-text). Despite recent efforts to explore these promising avenues, a primary challenge remains the insufficient data available to train robust text-motion models effectively. To address this issue, we propose to investigate joint-dataset learning - where we train on multiple text-motion datasets simultaneously - together with the introduction of a Cross-Consistent Contrastive Loss function (CCCL), which regularizes the learned text-motion common space by imposing uni-modal constraints that augment the representation ability of the trained network. To learn a proper motion representation, we also introduce a transformer-based motion encoder, called MoT++, which employs spatio-temporal attention to process sequences of skeleton data. We demonstrate the benefits of the proposed approaches on the widely-used KIT Motion-Language and HumanML3D datasets. We perform detailed experimentation on joint-dataset learning and cross-dataset scenarios, showing the effectiveness of each introduced module in a carefully conducted ablation study and, in turn, pointing out the limitations of state-of-the-art methods.

Lorenzo Bianchi, Fabio Carrara, Nicola Messina et al.

Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require the ability to respond to open-world stimuli. A key ingredient is the ability to identify objects based on free-form textual queries defined at inference time - a task known as open-vocabulary object detection. Multimodal backbones like CLIP are the main enabling technology for current open-world perception solutions. Despite performing well on generic queries, recent studies highlighted limitations on the fine-grained recognition capabilities in open-vocabulary settings - i.e., for distinguishing subtle object features like color, shape, and material. In this paper, we perform a detailed examination of these open-vocabulary object recognition limitations to find the root cause. We evaluate the performance of CLIP, the most commonly used vision-language backbone, against a fine-grained object-matching benchmark, revealing interesting analogies between the limitations of open-vocabulary object detectors and their backbones. Experiments suggest that the lack of fine-grained understanding is caused by the poor separability of object characteristics in the CLIP latent space. Therefore, we try to understand whether fine-grained knowledge is present in CLIP embeddings but not exploited at inference time due, for example, to the unsuitability of the cosine similarity matching function, which may discard important object characteristics. Our preliminary experiments show that simple CLIP latent-space re-projections help separate fine-grained concepts, paving the way towards the development of backbones inherently able to process fine-grained details. The code for reproducing these experiments is available at https://github.com/lorebianchi98/FG-CLIP.

Luca Ciampi, Gabriele Lagani, Giuseppe Amato et al.

We propose a novel bio-inspired semi-supervised learning approach for training downsampling-upsampling semantic segmentation architectures. The first stage does not use backpropagation. Rather, it exploits the Hebbian principle ``fire together, wire together'' as a local learning rule for updating the weights of both convolutional and transpose-convolutional layers, allowing unsupervised discovery of data features. In the second stage, the model is fine-tuned with standard backpropagation on a small subset of labeled data. We evaluate our methodology through experiments conducted on several widely used biomedical datasets, deeming that this domain is paramount in computer vision and is notably impacted by data scarcity. Results show that our proposed method outperforms SOTA approaches across different levels of label availability. Furthermore, we show that using our unsupervised stage to initialize the SOTA approaches leads to performance improvements. The code to replicate our experiments can be found at https://github.com/ciampluca/hebbian-bootstraping-semi-supervised-medical-imaging

Luca Ciampi, Gabriele Lagani, Giuseppe Amato et al.

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits its scalability in clinical settings. To address this challenge, semi-supervised learning is a well-established approach that leverages both labeled and unlabeled data. In this paper, we introduce a novel semi-supervised teacher-student framework for biomedical image segmentation, inspired by the recent success of generative models. Our approach leverages denoising diffusion probabilistic models (DDPMs) to generate segmentation masks by progressively refining noisy inputs conditioned on the corresponding images. The teacher model is first trained in an unsupervised manner using a cycle-consistency constraint based on noise-corrupted image reconstruction, enabling it to generate informative semantic masks. Subsequently, the teacher is integrated into a co-training process with a twin-student network. The student learns from ground-truth labels when available and from teacher-generated pseudo-labels otherwise, while the teacher continuously improves its pseudo-labeling capabilities. Finally, to further enhance performance, we introduce a multi-round pseudo-label generation strategy that iteratively improves the pseudo-labeling process. We evaluate our approach on multiple biomedical imaging benchmarks, spanning multiple imaging modalities and segmentation tasks. Experimental results show that our method consistently outperforms state-of-the-art semi-supervised techniques, highlighting its effectiveness in scenarios with limited annotated data. The code to replicate our experiments can be found at https://github.com/ciampluca/diffusion_semi_supervised_biomedical_image_segmentation

Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi et al.

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 opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at https://github.com/mesnico/text-to-motion-retrieval.

Davide Coccomini, Nicola Messina, Claudio Gennaro et al.

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 growing number of real and imaginary images of space available on the web and exploiting modern deep Learning architectures such as Generative Adversarial Networks, it is now possible to generate new representations of space. In this research, using a Lightweight GAN, a dataset of images obtained from the web, and the Galaxy Zoo Dataset, we have generated thousands of new images of celestial bodies, galaxies, and finally, by combining them, a wide view of the universe. The code for reproducing our results is publicly available at https://github.com/davide-coccomini/GAN-Universe, and the generated images can be explored at https://davide-coccomini.github.io/GAN-Universe/.

Fabio Carrara, Giuseppe Amato, Luca Brombin et al.

In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fairly good modeling power and reconstruction consistency capability. We evaluate the proposed method on MVTec AD -- a real-world benchmark for unsupervised anomaly detection on high-resolution images -- and compare against standard baselines and state-of-the-art approaches. Experiments show that the proposed method improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. We also observe that our model is particularly effective in texture-type anomaly detection, as it sets a new state of the art in this category. Our code is available at https://github.com/fabiocarrara/cbigan-ad/.

Nicola Messina, Giuseppe Amato, Andrea Esuli et al.

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-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level. Specifically, we present a novel approach called Transformer Encoder Reasoning and Alignment Network (TERAN). TERAN enforces a fine-grained match between the underlying components of images and sentences, i.e., image regions and words, respectively, in order to preserve the informative richness of both modalities. TERAN obtains state-of-the-art results on the image retrieval task on both MS-COCO and Flickr30k datasets. Moreover, on MS-COCO, it also outperforms current approaches on the sentence retrieval task. Focusing on scalable cross-modal information retrieval, TERAN is designed to keep the visual and textual data pipelines well separated. Cross-attention links invalidate any chance to separately extract visual and textual features needed for the online search and the offline indexing steps in large-scale retrieval systems. In this respect, TERAN merges the information from the two domains only during the final alignment phase, immediately before the loss computation. We argue that the fine-grained alignments produced by TERAN pave the way towards the research for effective and efficient methods for large-scale cross-modal information retrieval. We compare the effectiveness of our approach against relevant state-of-the-art methods. On the MS-COCO 1K test set, we obtain an improvement of 5.7% and 3.5% respectively on the image and the sentence retrieval tasks on the Recall@1 metric. The code used for the experiments is publicly available on GitHub at https://github.com/mesnico/TERAN.

Nicola Messina, Fabrizio Falchi, Andrea Esuli et al.

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 matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual and textual features needed for later indexing steps in large-scale retrieval systems. In this regard, we introduce the Transformer Encoder Reasoning Network (TERN), an architecture built upon one of the modern relationship-aware self-attentive architectures, the Transformer Encoder (TE). This architecture is able to separately reason on the two different modalities and to enforce a final common abstract concept space by sharing the weights of the deeper transformer layers. Thanks to this design, the implemented network is able to produce compact and very rich visual and textual features available for the successive indexing step. Experiments are conducted on the MS-COCO dataset, and we evaluate the results using a discounted cumulative gain metric with relevance computed exploiting caption similarities, in order to assess possibly non-exact but relevant search results. We demonstrate that on this metric we are able to achieve state-of-the-art results in the image retrieval task. Our code is freely available at https://github.com/mesnico/TERN.

Giacomo Pacini, Luca Ciampi, Nicola Messina et al.

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 evaluation protocols primarily focus on standard counting errors within single-category images, overlooking a fundamental requirement: the ability to correctly ground the textual prompt in the visual scene. In this paper, we show that several state-of-the-art CAC models often struggle to determine which object class should be counted based on the given prompt, revealing a misalignment between textual semantics and visual object representations. This limitation leads to spurious counting responses and reduced reliability in real-world scenarios. To systematically address these limitations, we propose a new evaluation framework focused on model robustness and trustworthiness. Our contribution is two-fold: (i) we introduce PrACo++ (Prompt-Aware Counting++), a novel test suite featuring two dedicated evaluation protocols -- the negative-label test and the distractor test -- paired with new specialized metrics; and (ii) we present the MUCCA (MUlti-Category Class-Agnostic counting) evaluation dataset, a new collection of real-world images featuring multiple annotated object categories per scene, unlike existing CAC benchmarks that typically include a single category per image. Our extensive experimental evaluation of 10 state-of-the-art methods shows that, despite strong performance under standard counting metrics, current models exhibit significant weaknesses in understanding and grounding object class descriptions. Finally, we provide a quantitative analysis of how semantic similarity between prompts influences these failures. Overall, our results underscore the need for more semantically grounded architectures and offer a reliable framework for future assessment in open-world text-guided CAC methods.

Edoardo Fazzari, Donato Romano, Fabrizio Falchi et al.

Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights into diverse facets of their lives, encompassing health, social dynamics, ecological relationships, and neuroethological dimensions. Although state-of-the-art deep learning models have demonstrated remarkable accuracy in classifying various forms of animal data, their adoption in animal behavior studies remains limited. This survey article endeavors to comprehensively explore deep learning architectures and strategies applied to the identification of animal behavior, spanning auditory, visual, and audiovisual methodologies. Furthermore, the manuscript scrutinizes extant animal behavior datasets, offering a detailed examination of the principal challenges confronting this research domain. The article culminates in a comprehensive discussion of key research directions within deep learning that hold potential for advancing the field of animal behavior studies.

Luca Barsellotti, Lorenzo Bianchi, Nicola Messina et al.

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. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.

Davide Alessandro Coccomini, Roberto Caldelli, Claudio Gennaro et al.

Deepfake detectors are typically trained on large sets of pristine and generated images, resulting in limited generalization capacity; they excel at identifying deepfakes created through methods encountered during training but struggle with those generated by unknown techniques. This paper introduces a learning approach aimed at significantly enhancing the generalization capabilities of deepfake detectors. Our method takes inspiration from the unique "fingerprints" that image generation processes consistently introduce into the frequency domain. These fingerprints manifest as structured and distinctly recognizable frequency patterns. We propose to train detectors using only pristine images injecting in part of them crafted frequency patterns, simulating the effects of various deepfake generation techniques without being specific to any. These synthetic patterns are based on generic shapes, grids, or auras. We evaluated our approach using diverse architectures across 25 different generation methods. The models trained with our approach were able to perform state-of-the-art deepfake detection, demonstrating also superior generalization capabilities in comparison with previous methods. Indeed, they are untied to any specific generation technique and can effectively identify deepfakes regardless of how they were made.

Luca Ciampi, Ali Azmoudeh, Elif Ecem Akbaba et al.

Visual object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories -- a crucial capability for flexible and generalizable counting systems. Unlike humans, who effortlessly identify and count objects from diverse categories without prior knowledge, most existing counting methods are restricted to enumerating instances of known classes, requiring extensive labeled datasets for training and struggling in open-vocabulary settings. In contrast, CAC aims to count objects belonging to classes never seen during training, operating in a few-shot setting. In this paper, we present the first comprehensive review of CAC methodologies. We propose a taxonomy to categorize CAC approaches into three paradigms based on how target object classes can be specified: reference-based, reference-less, and open-world text-guided. Reference-based approaches achieve state-of-the-art performance by relying on exemplar-guided mechanisms. Reference-less methods eliminate exemplar dependency by leveraging inherent image patterns. Finally, open-world text-guided methods use vision-language models, enabling object class descriptions via textual prompts, offering a flexible and promising solution. Based on this taxonomy, we provide an overview of the architectures of 29 CAC approaches and report their results on gold-standard benchmarks. We compare their performance and discuss their strengths and limitations. Specifically, we present results on the FSC-147 dataset, setting a leaderboard using gold-standard metrics, and on the CARPK dataset to assess generalization capabilities. Finally, we offer a critical discussion of persistent challenges, such as annotation dependency and generalization, alongside future directions. We believe this survey will be a valuable resource, showcasing CAC advancements and guiding future research.

Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara et al.

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 an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present Patch-ioner, a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense, region-set, and a newly introduced trace captioning task, highlighting the effectiveness of patch-wise semantic representations for scalable caption generation. Project page at https://paciosoft.com/Patch-ioner/ .

Nicola Messina, Rosario Leonardi, Luca Ciampi et al.

Pixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitoring. However, progress in this area is currently hindered by the scarcity of annotated datasets, as existing approaches rely on costly manual labels. In this paper, we propose to learn human-object interaction detection leveraging narrations -- natural language descriptions of the actions performed by the camera wearer which contain clues about manipulated objects (e.g., "I am pouring vegetables from the chopping board to the pan"). Narrations provide a form of weak supervision that is cheap to acquire and readily available in state-of-the-art egocentric datasets. We introduce Narration-Supervised in-Hand Object Segmentation (NS-iHOS), a novel task where models have to learn to segment in-hand objects by learning from natural-language narrations. Narrations are then not employed at inference time. We showcase the potential of the task by proposing Weakly-Supervised In-hand Object Segmentation from Human Narrations (WISH), an end-to-end model distilling knowledge from narrations to learn plausible hand-object associations and enable in-hand object segmentation without using narrations at test time. We benchmark WISH against different baselines based on open-vocabulary object detectors and vision-language models, showing the superiority of its design. Experiments on EPIC-Kitchens and Ego4D show that WISH surpasses all baselines, recovering more than 50% of the performance of fully supervised methods, without employing fine-grained pixel-wise annotations.

Giacomo Pacini, Lorenzo Bianchi, Luca Ciampi et al.

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 offer flexibility at inference time, they still rely heavily on labeled data for training, which limits scalability and generalization to many downstream use cases. In this paper, we introduce CountingDINO, the first training-free exemplar-based CAC framework that exploits a fully unsupervised feature extractor. Specifically, our approach employs self-supervised vision-only backbones to extract object-aware features, and it eliminates the need for annotated data throughout the entire proposed pipeline. At inference time, we extract latent object prototypes via ROI-Align from DINO features and use them as convolutional kernels to generate similarity maps. These are then transformed into density maps through a simple yet effective normalization scheme. We evaluate our approach on the FSC-147 benchmark, where we consistently outperform a baseline based on an SOTA unsupervised object detector under the same label- and training-free setting. Additionally, we achieve competitive results -- and in some cases surpass -- training-free methods that rely on supervised backbones, non-training-free unsupervised methods, as well as several fully supervised SOTA approaches. This demonstrates that label- and training-free CAC can be both scalable and effective. Code: https://lorebianchi98.github.io/CountingDINO/.

Giacomo Pacini, Fabio Carrara, Nicola Messina et al.

Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing experience of document collections. In cross-modal retrieval, many works have focused on retrieving relevant items from natural language queries, while few have explored query suggestion solutions. In this work, we address query suggestion in cross-modal retrieval, introducing a novel task that focuses on suggesting minimal textual modifications needed to explore visually consistent subsets of the collection, following the premise of ''Maybe you are looking for''. To facilitate the evaluation and development of methods, we present a tailored benchmark named CroQS. This dataset comprises initial queries, grouped result sets, and human-defined suggested queries for each group. We establish dedicated metrics to rigorously evaluate the performance of various methods on this task, measuring representativeness, cluster specificity, and similarity of the suggested queries to the original ones. Baseline methods from related fields, such as image captioning and content summarization, are adapted for this task to provide reference performance scores. Although relatively far from human performance, our experiments reveal that both LLM-based and captioning-based methods achieve competitive results on CroQS, improving the recall on cluster specificity by more than 115% and representativeness mAP by more than 52% with respect to the initial query. The dataset, the implementation of the baseline methods and the notebooks containing our experiments are available here: https://paciosoft.com/CroQS-benchmark/

Nicola Messina, Giuseppe Amato, Fabio Carrara et al.

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the model, allowing it to learn using far fewer free parameters, using only 28k training samples. A comprehensive ablation study confirms the importance of a hybrid CNN + Transformer architecture and the role of the feedback connections, which iteratively refine the internal representation until a stable prediction is obtained. In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.

Fabio Valerio Massoli, Lucia Vadicamo, Giuseppe Amato et al.

In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific community's interest since the late 80s. In such a context, we propose our contribution. First, we introduce basic concepts related to quantum computations, and then we explain the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms. Finally, we gather, compare and analyze the current state-of-the-art concerning Quantum Perceptrons and Quantum Neural Networks implementations.

Davide Coccomini, Nicola Messina, Claudio Gennaro et al.

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 obtained using variational autoencoders (VAEs) or Generative Adversarial Networks (GANs). These technologies are becoming more accessible and accurate, resulting in fake videos that are very difficult to be detected. Traditionally, Convolutional Neural Networks (CNNs) have been used to perform video deepfake detection, with the best results obtained using methods based on EfficientNet B7. In this study, we focus on video deep fake detection on faces, given that most methods are becoming extremely accurate in the generation of realistic human faces. Specifically, we combine various types of Vision Transformers with a convolutional EfficientNet B0 used as a feature extractor, obtaining comparable results with some very recent methods that use Vision Transformers. Differently from the state-of-the-art approaches, we use neither distillation nor ensemble methods. Furthermore, we present a straightforward inference procedure based on a simple voting scheme for handling multiple faces in the same video shot. The best model achieved an AUC of 0.951 and an F1 score of 88.0%, very close to the state-of-the-art on the DeepFake Detection Challenge (DFDC).

Luca Ciampi, Claudio Gennaro, Fabio Carrara et al.

This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras. Unlike most of the literature on this task, which focuses on the analysis of single images, this paper proposes the use of multiple visual sources to monitor a wider parking area from different perspectives. The proposed multi-camera system is capable of automatically estimate the number of cars present in the entire parking lot directly on board the edge devices. It comprises an on-device deep learning-based detector that locates and counts the vehicles from the captured images and a decentralized geometric-based approach that can analyze the inter-camera shared areas and merge the data acquired by all the devices. We conduct the experimental evaluation on an extended version of the CNRPark-EXT dataset, a collection of images taken from the parking lot on the campus of the National Research Council (CNR) in Pisa, Italy. We show that our system is robust and takes advantage of the redundant information deriving from the different cameras, improving the overall performance without requiring any extra geometrical information of the monitored scene.

Nicola Messina, Giuseppe Amato, Fabrizio Falchi et al.

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 modalities. In this paper, we focus on the image-sentence retrieval task, where the objective is to efficiently find relevant images for a given sentence (image-retrieval) or the relevant sentences for a given image (sentence-retrieval). Computer vision literature reports the best results on the image-sentence matching task using deep neural networks equipped with attention and self-attention mechanisms. They evaluate the matching performance on the retrieval task by performing sequential scans of the whole dataset. This method does not scale well with an increasing amount of images or captions. In this work, we explore different preprocessing techniques to produce sparsified deep multi-modal features extracting them from state-of-the-art deep-learning architectures for image-text matching. Our main objective is to lay down the paths for efficient indexing of complex multi-modal descriptions. We use the recently introduced TERN architecture as an image-sentence features extractor. It is designed for producing fixed-size 1024-d vectors describing whole images and sentences, as well as variable-length sets of 1024-d vectors describing the various building components of the two modalities (image regions and sentence words respectively). All these vectors are enforced by the TERN design to lie into the same common space. Our experiments show interesting preliminary results on the explored methods and suggest further experimentation in this important research direction.

Fabio Valerio Massoli, Donato Cafarelli, Claudio Gennaro et al.

Emotions play a central role in the social life of every human being, and their study, which represents a multidisciplinary subject, embraces a great variety of research fields. Especially concerning the latter, the analysis of facial expressions represents a very active research area due to its relevance to human-computer interaction applications. In such a context, Facial Expression Recognition (FER) is the task of recognizing expressions on human faces. Typically, face images are acquired by cameras that have, by nature, different characteristics, such as the output resolution. It has been already shown in the literature that Deep Learning models applied to face recognition experience a degradation in their performance when tested against multi-resolution scenarios. Since the FER task involves analyzing face images that can be acquired with heterogeneous sources, thus involving images with different quality, it is plausible to expect that resolution plays an important role in such a case too. Stemming from such a hypothesis, we prove the benefits of multi-resolution training for models tasked with recognizing facial expressions. Hence, we propose a two-step learning procedure, named MAFER, to train DCNNs to empower them to generate robust predictions across a wide range of resolutions. A relevant feature of MAFER is that it is task-agnostic, i.e., it can be used complementarily to other objective-related techniques. To assess the effectiveness of the proposed approach, we performed an extensive experimental campaign on publicly available datasets: \fer{}, \raf{}, and \oulu{}. For a multi-resolution context, we observe that with our approach, learning models improve upon the current SotA while reporting comparable results in fix-resolution contexts. Finally, we analyze the performance of our models and observe the higher discrimination power of deep features generated from them.

Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro et al.

We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD). In fact, as Hebbian learning is an unsupervised learning method, its potential lies in the possibility of training the internal layers of a DCNN without labels. Only the final fully connected layer has to be trained with labeled examples. We performed experiments on various object recognition datasets, in different regimes of sample efficiency, comparing our semi-supervised (Hebbian for internal layers + SGD for the final fully connected layer) approach with end-to-end supervised backprop training, and with semi-supervised learning based on Variational Auto-Encoder (VAE). The results show that, in regimes where the number of available labeled samples is low, our semi-supervised approach outperforms the other approaches in almost all the cases.

Fabio Valerio Massoli, Donato Cafarelli, Giuseppe Amato et al.

Facial expressions play a fundamental role in human communication. Indeed, they typically reveal the real emotional status of people beyond the spoken language. Moreover, the comprehension of human affect based on visual patterns is a key ingredient for any human-machine interaction system and, for such reasons, the task of Facial Expression Recognition (FER) draws both scientific and industrial interest. In the recent years, Deep Learning techniques reached very high performance on FER by exploiting different architectures and learning paradigms. In such a context, we propose a multi-resolution approach to solve the FER task. We ground our intuition on the observation that often faces images are acquired at different resolutions. Thus, directly considering such property while training a model can help achieve higher performance on recognizing facial expressions. To our aim, we use a ResNet-like architecture, equipped with Squeeze-and-Excitation blocks, trained on the Affect-in-the-Wild 2 dataset. Not being available a test set, we conduct tests and models selection by employing the validation set only on which we achieve more than 90\% accuracy on classifying the seven expressions that the dataset comprises.

Donato Cafarelli, Fabio Valerio Massoli, Fabrizio Falchi et al.

Facial Expression Recognition(FER) is one of the most important topic in Human-Computer interactions(HCI). In this work we report details and experimental results about a facial expression recognition method based on state-of-the-art methods. We fine-tuned a SeNet deep learning architecture pre-trained on the well-known VGGFace2 dataset, on the AffWild2 facial expression recognition dataset. The main goal of this work is to define a baseline for a novel method we are going to propose in the near future. This paper is also required by the Affective Behavior Analysis in-the-wild (ABAW) competition in order to evaluate on the test set this approach. The results reported here are on the validation set and are related on the Expression Challenge part (seven basic emotion recognition) of the competition. We will update them as soon as the actual results on the test set will be published on the leaderboard.

Nicola Messina, Giuseppe Amato, Fabio Carrara et al.

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 reasoning tasks that humans consider easy to solve. In this work, we probe current state-of-the-art convolutional neural networks on a difficult set of tasks known as the same-different problems. All the problems require the same prerequisite to be solved correctly: understanding if two random shapes inside the same image are the same or not. With the experiments carried out in this work, we demonstrate that residual connections, and more generally the skip connections, seem to have only a marginal impact on the learning of the proposed problems. In particular, we experiment with DenseNets, and we examine the contribution of residual and recurrent connections in already tested architectures, ResNet-18, and CorNet-S respectively. Our experiments show that older feed-forward networks, AlexNet and VGG, are almost unable to learn the proposed problems, except in some specific scenarios. We show that recently introduced architectures can converge even in the cases where the important parts of their architecture are removed. We finally carry out some zero-shot generalization tests, and we discover that in these scenarios residual and recurrent connections can have a stronger impact on the overall test accuracy. On four difficult problems from the SVRT dataset, we can reach state-of-the-art results with respect to the previous approaches, obtaining super-human performances on three of the four problems.

Gabriele Lagani, Giuseppe Amato, Fabrizio Falchi et al.

Recent work has shown that biologically plausible Hebbian learning can be integrated with backpropagation learning (backprop), when training deep convolutional neural networks. In particular, it has been shown that Hebbian learning can be used for training the lower or the higher layers of a neural network. For instance, Hebbian learning is effective for re-training the higher layers of a pre-trained deep neural network, achieving comparable accuracy w.r.t. SGD, while requiring fewer training epochs, suggesting potential applications for transfer learning. In this paper we build on these results and we further improve Hebbian learning in these settings, by using a nonlinear Hebbian Principal Component Analysis (HPCA) learning rule, in place of the Hebbian Winner Takes All (HWTA) strategy used in previous work. We test this approach in the context of computer vision. In particular, the HPCA rule is used to train Convolutional Neural Networks in order to extract relevant features from the CIFAR-10 image dataset. The HPCA variant that we explore further improves the previous results, motivating further interest towards biologically plausible learning algorithms.

Gabriele Lagani, Raffaele Mazziotti, Fabrizio Falchi et al.

Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns. However, this work was mainly focused to demonstrate that it is possible to induce plasticity in cultures, rather than performing a rigorous assessment of their pattern recognition performance. In this paper, we address this gap by developing a methodology that allows us to assess the performance of neuronal cultures on a learning task. Specifically, we propose a digital model of the real cultured neuronal networks; we identify biologically plausible simulation parameters that allow us to reliably reproduce the behavior of real cultures; we use the simulated culture to perform handwritten digit recognition and rigorously evaluate its performance; we also show that it is possible to find improved simulation parameters for the specific task, which can guide the creation of real cultures.

Fabio Valerio Massoli, Fabrizio Falchi, Alperen Kantarci et al.

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events' rarity, to train deep learning models on the Anomaly Detection (AD) task, scientists only rely on "normal" data, i.e., non-anomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named Multi-layer One-Class ClassificAtion (MOCCA),to train and test deep learning models on the AD task. Specifically, we applied it to autoencoders. A key novelty in our work stems from the explicit optimization of intermediate representations for the AD task. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multi-layer structure of deep architectures. Each layer's feature space is optimized for AD during training, while in the test phase, the deep representations extracted from the trained layers are combined to detect anomalies. With MOCCA, we split the training process into two steps. First, the autoencoder is trained on the reconstruction task only. Then, we only retain the encoder tasked with minimizing the L_2 distance between the output representation and a reference point, the anomaly-free training data centroid, at each considered layer. Subsequently, we combine the deep features extracted at the various trained layers of the encoder model to detect anomalies at inference time. To assess the performance of the models trained with MOCCA, we conduct extensive experiments on publicly available datasets. We show that our proposed method reaches comparable or superior performance to state-of-the-art approaches available in the literature.

Giuseppe Amato, Paolo Bolettieri, Fabio Carrara et al.

In this paper, we describe in details VISIONE, a video search system that allows users to search for videos using textual keywords, occurrence of objects and their spatial relationships, occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and satisfy user needs. The peculiarity of our approach is that we encode all the information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) have to be merged. In addition, we report an extensive analysis of the system retrieval performance, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies among the ones that we tested.

Tiziano Fagni, Fabrizio Falchi, Margherita Gambini et al.

The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of \real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.

Danilo Sorano, Fabio Carrara, Paolo Cintia et al.

Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of data that describe all the spatio-temporal events that occur in each match. These events (e.g., passes, shots, fouls) are collected by human operators manually, constituting a considerable cost for data providers in terms of time and economic resources. In this paper, we describe PassNet, a method to recognize the most frequent events in soccer, i.e., passes, from video streams. Our model combines a set of artificial neural networks that perform feature extraction from video streams, object detection to identify the positions of the ball and the players, and classification of frame sequences as passes or not passes. We test PassNet on different scenarios, depending on the similarity of conditions to the match used for training. Our results show good classification results and significant improvement in the accuracy of pass detection with respect to baseline classifiers, even when the match's video conditions of the test and training sets are considerably different. PassNet is the first step towards an automated event annotation system that may break the time and the costs for event annotation, enabling data collections for minor and non-professional divisions, youth leagues and, in general, competitions whose matches are not currently annotated by data providers.

Luca Ciampi, Nicola Messina, Fabrizio Falchi et al.

Pedestrian detection through Computer Vision is a building block for a multitude of applications. Recently, there was an increasing interest in Convolutional Neural Network-based architectures for the execution of such a task. One of these supervised networks' critical goals is to generalize the knowledge learned during the training phase to new scenarios with different characteristics. A suitably labeled dataset is essential to achieve this purpose. The main problem is that manually annotating a dataset usually requires a lot of human effort, and it is costly. To this end, we introduce ViPeD (Virtual Pedestrian Dataset), a new synthetically generated set of images collected with the highly photo-realistic graphical engine of the video game GTA V - Grand Theft Auto V, where annotations are automatically acquired. However, when training solely on the synthetic dataset, the model experiences a Synthetic2Real Domain Shift leading to a performance drop when applied to real-world images. To mitigate this gap, we propose two different Domain Adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection. Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data, exploiting the variety of our synthetic dataset. Furthermore, we demonstrate that with our Domain Adaptation techniques, we can reduce the Synthetic2Real Domain Shift, making closer the two domains and obtaining a performance improvement when testing the network over the real-world images. The code, the models, and the dataset are made freely available at https://ciampluca.github.io/viped/