Nuno Gonçalves

Guilherme Schardong, Tiago Novello, Hallison Paz et al.

Face morphing is a problem in computer graphics with numerous artistic and forensic applications. It is challenging due to variations in pose, lighting, gender, and ethnicity. This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coord-based neural networks to represent such warpings and blendings of face images. During training, we exploit the smoothness and flexibility of such networks by combining energy functionals employed in classical approaches without discretizations. Additionally, our method is time-dependent, allowing a continuous warping/blending of the images. During morphing inference, we need both direct and inverse transformations of the time-dependent warping. The first (second) is responsible for warping the target (source) image into the source (target) image. Our neural warping stores those maps in a single network dismissing the need for inverting them. The results of our experiments indicate that our method is competitive with both classical and generative models under the lens of image quality and face-morphing detectors. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.

Nuno Gonçalves, Hugo Pitorro, Vlad Niculae et al.

Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is $α$-entmax attention, a differentiable sparse alternative to softmax that enables input-dependent sparsity yet has lagged behind softmax due to the computational overhead necessary to compute the normalizer $τ$. In this paper, we introduce AdaSplash-2, which addresses this limitation through a novel histogram-based initialization that reduces the number of iterations needed to compute $τ$ to typically 1--2. The key idea is to compute a coarse histogram of attention scores on the fly and store it in on-chip SRAM, yielding a more accurate initialization that enables fast forward and backward computation. Combined with a sparsity-aware GPU implementation that skips zero blocks with low overhead, AdaSplash-2 matches or improves per-step training time relative to FlashAttention-2 when block sparsity is moderate-to-high (e.g., $>$60\%), which often occurs at long-context lengths. On downstream tasks, models trained with our efficient $α$-entmax attention match softmax baselines at short-context lengths and achieve substantial gains in long-context settings.

Luiz Schirmer, Tiago Novello, Vinícius da Silva et al.

\textit{Implicit neural representations} (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating \textit{signed distance functions} (SDFs) for surface scenes, using either oriented point clouds or a set of posed images. We refer to neural SDFs that incorporate differential geometry tools, such as normals and curvatures, in their loss functions as \textit{geometric} INRs. The key idea behind this 3D reconstruction approach is to include additional \textit{regularization} terms in the loss function, ensuring that the INR satisfies certain global properties that the function should hold -- such as having unit gradient in the case of SDFs. We explore key methodological components, including the definition of INR, the construction of geometric loss functions, and sampling schemes from a differential geometry perspective. Our review highlights the significant advancements enabled by geometric INRs in surface reconstruction from oriented point clouds and posed images.

Iurii Medvedev, Farhad Shadmand, Nuno Gonçalves

Face morphing attack detection (MAD) is one of the most challenging tasks in the field of face recognition nowadays. In this work, we introduce a novel deep learning strategy for a single image face morphing detection, which implies the discrimination of morphed face images along with a sophisticated face recognition task in a complex classification scheme. It is directed onto learning the deep facial features, which carry information about the authenticity of these features. Our work also introduces several additional contributions: the public and easy-to-use face morphing detection benchmark and the results of our wild datasets filtering strategy. Our method, which we call MorDeephy, achieved the state of the art performance and demonstrated a prominent ability for generalising the task of morphing detection to unseen scenarios.

Iurii Medvedev, Farhad Shadmand, Nuno Gonçalves

Face recognition has achieved outstanding performance in the last decade with the development of deep learning techniques. Nowadays, the challenges in face recognition are related to specific scenarios, for instance, the performance under diverse image quality, the robustness for aging and edge cases of person age (children and elders), distinguishing of related identities. In this set of problems, recognizing children's faces is one of the most sensitive and important. One of the reasons for this problem is the existing bias towards adults in existing face datasets. In this work, we present a benchmark dataset for children's face recognition, which is compiled similarly to the famous face recognition benchmarks LFW, CALFW, CPLFW, XQLFW and AgeDB. We also present a development dataset (separated into train and test parts) for adapting face recognition models for face images of children. The proposed data is balanced for African, Asian, Caucasian, and Indian races. To the best of our knowledge, this is the first standartized data tool set for benchmarking and the largest collection for development for children's face recognition. Several face recognition experiments are presented to demonstrate the performance of the proposed data tool set.

André G. Viveiros, Nuno Gonçalves, André F. T. Martins et al.

Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought reasoning with continuous latent tokens as intermediate visual imagination steps. In this work, we investigate how recent models leverage such latent tokens. Surprisingly, we find that model accuracy is unaffected when latent tokens are replaced by uninformative ``dummy'' tokens. This indicates that latent tokens play a minimal causal role in the model's final prediction. To better understand this phenomenon, we analyze both the training signal provided by oracle latent representations and the quality of the latent tokens generated at inference time. Our experiments reveal two crucial issues holding back latent visual reasoning: First, in most existing datasets, oracle latent tokens provide limited additional information beyond the original image and do not substantially simplify the task, leading models to ignore them during training and effectively bypassing them at inference time. When fine-tuned on a diagnostic dataset, in which latent tokens provide sufficient support for the final prediction, we show that models can causally rely on them. Second, the latent tokens produced at inference time deviate from their corresponding oracle representations, collapsing to a narrow region and preventing benefits even when the model relies on them. Overall, our findings suggest that future progress in latent visual reasoning depends on two key pillars: high-quality datasets with informative intermediate steps and more precise latent token prediction.

Nuno Gonçalves, Diogo Nunes, Carla Guerra et al.

Ensuring compliance with ISO/IEC and ICAO standards for facial images in machine-readable travel documents (MRTDs) is essential for reliable identity verification, but current manual inspection methods are inefficient in high-demand environments. This paper introduces the DFIC dataset, a novel comprehensive facial image dataset comprising around 58,000 annotated images and 2706 videos of more than 1000 subjects, that cover a broad range of non-compliant conditions, in addition to compliant portraits. Our dataset provides a more balanced demographic distribution than the existing public datasets, with one partition that is nearly uniformly distributed, facilitating the development of automated ICAO compliance verification methods. Using DFIC, we fine-tuned a novel method that heavily relies on spatial attention mechanisms for the automatic validation of ICAO compliance requirements, and we have compared it with the state-of-the-art aimed at ICAO compliance verification, demonstrating improved results. DFIC dataset is now made public (https://github.com/visteam-isr-uc/DFIC) for the training and validation of new models, offering an unprecedented diversity of faces, that will improve both robustness and adaptability to the intrinsically diverse combinations of faces and props that can be presented to the validation system. These results emphasize the potential of DFIC to enhance automated ICAO compliance methods but it can also be used in many other applications that aim to improve the security, privacy, and fairness of facial recognition systems.

Ajnas Muhammed, Iurri Medvedev, Nuno Gonçalves

Advancement of machine learning techniques, combined with the availability of large-scale datasets, has significantly improved the accuracy and efficiency of facial recognition. Modern facial recognition systems are trained using large face datasets collected from diverse individuals or public repositories. However, for training, these datasets are often replicated and stored in multiple workstations, resulting in data replication, which complicates database management and oversight. Currently, once a user submits their face for dataset preparation, they lose control over how their data is used, raising significant privacy and ethical concerns. This paper introduces VOIDFace, a novel framework for facial recognition systems that addresses two major issues. First, it eliminates the need of data replication and improves data control to securely store training face data by using visual secret sharing. Second, it proposes a patch-based multi-training network that uses this novel training data storage mechanism to develop a robust, privacy-preserving facial recognition system. By integrating these advancements, VOIDFace aims to improve the privacy, security, and efficiency of facial recognition training, while ensuring greater control over sensitive personal face data. VOIDFace also enables users to exercise their Right-To-Be-Forgotten property to control their personal data. Experimental evaluations on the VGGFace2 dataset show that VOIDFace provides Right-To-Be-Forgotten, improved data control, security, and privacy while maintaining competitive facial recognition performance. Code is available at: https://github.com/ajnasmuhammed89/VOIDFace

Saul Santos, Nuno Gonçalves, Daniel C. McNamee et al.

Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator, with standard softmax attention corresponding to a Gaussian kernel. However, a kernel-theoretic understanding of sparse attention mechanisms is currently missing. In this paper, we establish a formal correspondence between sparse attention and compact (bounded support) kernels. We show that normalized ReLU and sparsemax attention arise from Epanechnikov kernel regression under fixed and adaptive normalizations, respectively. More generally, we demonstrate that widely used kernels in nonparametric density estimation -- including Epanechnikov, biweight, and triweight -- correspond to $α$-entmax attention with $α= 1 + \frac{1}{n}$ for $n \in \mathbb{N}$, while the softmax/Gaussian relationship emerges in the limit $n \to \infty$. This unified perspective explains how sparsity naturally emerges from kernel design and provides principled alternatives to heuristic top-$k$ attention and other associative memory mechanisms. Experiments with a kernel-regression-based variant of transformers -- Memory Mosaics -- show that kernel-based sparse attention achieves competitive performance on language modeling, in-context learning, and length generalization tasks, offering a principled framework for designing attention mechanisms.

Iurii Medvedev, Nuno Gonçalves

Recent advancements in deep learning have revolutionized technology and security measures, necessitating robust identification methods. Biometric approaches, leveraging personalized characteristics, offer a promising solution. However, Face Recognition Systems are vulnerable to sophisticated attacks, notably face morphing techniques, enabling the creation of fraudulent documents. In this study, we introduce a novel quadruplet loss function for increasing the robustness of face recognition systems against morphing attacks. Our approach involves specific sampling of face image quadruplets, combined with face morphs, for network training. Experimental results demonstrate the efficiency of our strategy in improving the robustness of face recognition networks against morphing attacks.

Arthur Bizzi, Matias Grynberg, Vitor Matias et al.

Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable training and prevent effective feature alignment. To overcome these limitations, we propose FLOWING (FLOW morphING), a framework that recasts warping as the construction of a differential vector flow, naturally ensuring continuity, invertibility, and temporal coherence by encoding structural flow properties directly into the network architectures. This flow-centric approach yields principled and stable transformations, enabling accurate and structure-preserving morphing of both 2D images and 3D shapes. Extensive experiments across a range of applications - including face and image morphing, as well as Gaussian Splatting morphing - show that FLOWING achieves state-of-the-art morphing quality with faster convergence. Code and pretrained models are available at http://schardong.github.io/flowing.

Nuno Gonçalves, Marcos Treviso, André F. T. Martins

The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $α$-entmax attention is an example, offers a flexible data-dependent alternative, but existing implementations are inefficient and do not leverage the sparsity to obtain runtime and memory gains. In this work, we propose AdaSplash, which combines the efficiency of GPU-optimized algorithms with the sparsity benefits of $α$-entmax. We first introduce a hybrid Halley-bisection algorithm, resulting in a 7-fold reduction in the number of iterations needed to compute the $α$-entmax transformation. Then, we implement custom Triton kernels to efficiently handle adaptive sparsity. Experiments with RoBERTa and ModernBERT for text classification and single-vector retrieval, along with GPT-2 for language modeling, show that our method achieves substantial improvements in runtime and memory efficiency compared to existing $α$-entmax implementations. It approaches -- and in some cases surpasses -- the efficiency of highly optimized softmax implementations like FlashAttention-2, enabling long-context training while maintaining strong task performance.

Juan E. Tapia, Mario Nieto, Juan M. Espin et al.

This work summarises and reports the results of the second Presentation Attack Detection competition on ID cards. This new version includes new elements compared to the previous one. (1) An automatic evaluation platform was enabled for automatic benchmarking; (2) Two tracks were proposed in order to evaluate algorithms and datasets, respectively; and (3) A new ID card dataset was shared with Track 1 teams to serve as the baseline dataset for the training and optimisation. The Hochschule Darmstadt, Fraunhofer-IGD, and Facephi company jointly organised this challenge. 20 teams were registered, and 74 submitted models were evaluated. For Track 1, the "Dragons" team reached first place with an Average Ranking and Equal Error rate (EER) of AV-Rank of 40.48% and 11.44% EER, respectively. For the more challenging approach in Track 2, the "Incode" team reached the best results with an AV-Rank of 14.76% and 6.36% EER, improving on the results of the first edition of 74.30% and 21.87% EER, respectively. These results suggest that PAD on ID cards is improving, but it is still a challenging problem related to the number of images, especially of bona fide images.

Iurii Medvedev, Joana Pimenta, Nuno Gonçalves

Face morphing, a sophisticated presentation attack technique, poses significant security risks to face recognition systems. Traditional methods struggle to detect morphing attacks, which involve blending multiple face images to create a synthetic image that can match different individuals. In this paper, we focus on the differential detection of face morphing and propose an extended approach based on fused classification method for no-reference scenario. We introduce a public face morphing detection benchmark for the differential scenario and utilize a specific data mining technique to enhance the performance of our approach. Experimental results demonstrate the effectiveness of our method in detecting morphing attacks.

Joana Pimenta, Iurii Medvedev, Nuno Gonçalves

The increase in security concerns due to technological advancements has led to the popularity of biometric approaches that utilize physiological or behavioral characteristics for enhanced recognition. Face recognition systems (FRSs) have become prevalent, but they are still vulnerable to image manipulation techniques such as face morphing attacks. This study investigates the impact of the alignment settings of input images on deep learning face morphing detection performance. We analyze the interconnections between the face contour and image context and suggest optimal alignment conditions for face morphing detection.

Gledson Melotti, Cristiano Premebida, Jordan J. Bird et al.

In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs. Such layers often produce overconfident predictions rather than proper probabilistic scores, which can thus harm the decision-making of `critical' perception systems applied in autonomous driving and robotics. Given this, the experiments in this work propose a probabilistic approach based on distributions calculated out of the Logit layer scores of pre-trained networks. We demonstrate that Maximum Likelihood (ML) and Maximum a-Posteriori (MAP) functions are more suitable for probabilistic interpretations than SoftMax and Sigmoid-based predictions for object recognition. We explore distinct sensor modalities via RGB images and LiDARs (RV: range-view) data from the KITTI and Lyft Level-5 datasets, where our approach shows promising performance compared to the usual SoftMax and Sigmoid layers, with the benefit of enabling interpretable probabilistic predictions. Another advantage of the approach introduced in this paper is that the ML and MAP functions can be implemented in existing trained networks, that is, the approach benefits from the output of the Logit layer of pre-trained networks. Thus, there is no need to carry out a new training phase since the ML and MAP functions are used in the test/prediction phase.

Diogo Faustino, Nuno Gonçalves, Manuel Portela et al.

The agility inherent to today's business promotes the definition of software architectures where the business entities are decoupled into modules and/or services. However, there are advantages in having a rich domain model, where domain entities are tightly connected, because it fosters an initial quick development. On the other hand, the split of the business logic into modules and/or services, its encapsulation through well-defined interfaces and the introduction of inter-service communication introduces a cost in terms of performance. In this paper we analyze the stepwise migrating of a monolith, using a rich domain object, into a microservice architecture, where a modular monolith architecture is used as an intermediate step. The impact on the migration effort and on performance is measured for both steps. Current state of the art analyses the migration of monolith systems to a microservices architecture, but we observed that migration effort and performance issues are already significant in the migration to a modular monolith. Therefore, a clear distinction is established for each one of the steps, which may inform software architects on the planning of the migration of monolith systems. In particular, the trade-offs of doing all the migration process or just migrating to a modular monolith.

Gustavo Assunção, Nuno Gonçalves, Paulo Menezes

Human beings have developed fantastic abilities to integrate information from various sensory sources exploring their inherent complementarity. Perceptual capabilities are therefore heightened, enabling, for instance, the well-known "cocktail party" and McGurk effects, i.e., speech disambiguation from a panoply of sound signals. This fusion ability is also key in refining the perception of sound source location, as in distinguishing whose voice is being heard in a group conversation. Furthermore, neuroscience has successfully identified the superior colliculus region in the brain as the one responsible for this modality fusion, with a handful of biological models having been proposed to approach its underlying neurophysiological process. Deriving inspiration from one of these models, this paper presents a methodology for effectively fusing correlated auditory and visual information for active speaker detection. Such an ability can have a wide range of applications, from teleconferencing systems to social robotics. The detection approach initially routes auditory and visual information through two specialized neural network structures. The resulting embeddings are fused via a novel layer based on the superior colliculus, whose topological structure emulates spatial neuron cross-mapping of unimodal perceptual fields. The validation process employed two publicly available datasets, with achieved results confirming and greatly surpassing initial expectations.