Brain aging synthesis is a critical task with broad applications in clinical and computational neuroscience. The ability to predict the future structural evolution of a subject's brain from an earlier MRI scan provides valuable insights into aging trajectories. Yet, the high-dimensionality of data, subtle changes of structure across ages, and subject-specific patterns constitute challenges in the synthesis of the aging brain. To overcome these challenges, we propose NeuroAR, a novel brain aging simulation model based on generative autoregressive transformers. NeuroAR synthesizes the aging brain by autoregressively estimating the discrete token maps of a future scan from a convenient space of concatenated token embeddings of a previous and future scan. To guide the generation, it concatenates into each scale the subject's previous scan, and uses its acquisition age and the target age at each block via cross-attention. We evaluate our approach on both the elderly population and adolescent subjects, demonstrating superior performance over state-of-the-art generative models, including latent diffusion models (LDM) and generative adversarial networks, in terms of image fidelity. Furthermore, we employ a pre-trained age predictor to further validate the consistency and realism of the synthesized images with respect to expected aging patterns. NeuroAR significantly outperforms key models, including LDM, demonstrating its ability to model subject-specific brain aging trajectories with high fidelity.

Brain aging represents an intrinsic biological phenomenon marked by discernible morphological changes within the human brain Fjell and Walhovd (2010). In the analysis of brain aging using medical imaging, structural magnetic resonance imaging (sMRI) plays a crucial role as they provide detailed insights into age-related variations and assist in accurate assessments of these alterations. Advances in sMRI-based age transformation have especially allowed researchers and clinicians to visualize and quantify patient-specific intricate brain maturation and degeneration patterns, facilitating medical diagnosis advancements. These capabilities can be pivotal for longitudinal studies to track cognitive or health state progressions over time Cole, Ritchie, Bastin, Hernández, Muñoz Maniega, Royle, Corley, Pattie, Harris, Zhang et al. (2018); Huizinga, Poot, Vernooij, Roshchupkin, Bron, Ikram, Rueckert, Niessen, Klein, Initiative et al. (2018), whereas brain age transformation with preserving patient traits remains a formidable challenge. Because most methods even change characteristics unrelated to aging during the transformation process, the crux lies in modeling the aging process without distorting personal identities intrinsic to each subject Xia, Chartsias, Wang, Tsaftaris, Initiative et al. (2021). When the aging model fails to preserve personal properties regarding identity, it may lead to misinterpretations of age-related changes, potentially compromising the accuracy and reliability of diagnostic decisions. Previous brain age transformation studies Huizinga et al. (2018); Zhang, Shi, Wu, Wang, Yap and Shen (2016); Zhao, Adeli, Honnorat, Leng and Pohl (2019); Lorenzi, Pennec, Frisoni, Ayache, Initiative et al. (2015); Sivera, Delingette, Lorenzi, Pennec, Ayache, Initiative et al. (2019) have often relied on prototype-based strategies that compare averaged brain patterns across different age groups. While these approaches aid in understanding generalized characteristics shared among age groups, they tend to neglect the unique traits of individual subjects. Recently, with the emergence of generative models using longitudinal data Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville and Bengio (2014); Makhzani, Shlens, Jaitly, Goodfellow and Frey (2015), researchers have gained the ability to create more accurate and realistic simulations of brain aging by virtue of the advantages of its data, which comprised MRI scans of the same subject at multiple time points Rachmadi, del C. Valdés-Hernández, Makin,

In recent years, neural machine translation (NMT) has been widely used in everyday life. However, the current NMT lacks a mechanism to adjust the difficulty level of translations to match the user's language level. Additionally, due to the bias in the training data for NMT, translations of simple source sentences are often produced with complex words. In particular, this could pose a problem for children, who may not be able to understand the meaning of the translations correctly. In this study, we propose a method that replaces words with high Age of Acquisitions (AoA) in translations with simpler words to match the translations to the user's level. We achieve this by using large language models (LLMs), providing a triple of a source sentence, a translation, and a target word to be replaced. We create a benchmark dataset using back-translation on Simple English Wikipedia. The experimental results obtained from the dataset show that our method effectively replaces high-AoA words with lower-AoA words and, moreover, can iteratively replace most of the high-AoA words while still maintaining high BLEU and COMET scores.

Face re-aging is a prominent field in computer vision and graphics, with significant applications in photorealistic domains such as movies, advertising, and live streaming. Recently, the need to apply face re-aging to non-photorealistic images, like comics, illustrations, and animations, has emerged as an extension in various entertainment sectors. However, the absence of a network capable of seamlessly editing the apparent age on NPR images means that these tasks have been confined to a naive approach, applying each task sequentially. This often results in unpleasant artifacts and a loss of facial attributes due to domain discrepancies. In this paper, we introduce a novel one-stage method for face re-aging combined with portrait style transfer, executed in a single generative step. We leverage existing face re-aging and style transfer networks, both trained within the same PR domain. Our method uniquely fuses distinct latent vectors, each responsible for managing aging-related attributes and NPR appearance. Adopting an exemplar-based approach, our method offers greater flexibility than domain-level fine-tuning approaches, which typically require separate training or fine-tuning for each domain. This effectively addresses the limitation of requiring paired datasets for re-aging and domain-level, data-driven approaches for stylization. Our experiments show that our model can effortlessly generate re-aged images while simultaneously transferring the style of examples, maintaining both natural appearance and controllability.

Video face re-aging deals with altering the apparent age of a person to the target age in videos. This problem is challenging due to the lack of paired video datasets maintaining temporal consistency in identity and age. Most re-aging methods process each image individually without considering the temporal consistency of videos. While some existing works address the issue of temporal coherence through video facial attribute manipulation in latent space, they often fail to deliver satisfactory performance in age transformation. To tackle the issues, we propose (1) a novel synthetic video dataset that features subjects across a diverse range of age groups; (2) a baseline architecture designed to validate the effectiveness of our proposed dataset, and (3) the development of three novel metrics tailored explicitly for evaluating the temporal consistency of video re-aging techniques. Our comprehensive experiments on public datasets, such as VFHQ and CelebV-HQ, show that our method outperforms the existing approaches in terms of both age transformation and temporal consistency.

Children have less text understanding capability than adults. Moreover, this capability differs among the children of different ages. Hence, automatically predicting a recommended age based on texts or sentences would be a great benefit to propose adequate texts to children and to help authors writing in the most appropriate way. This paper presents our recent advances on the age recommendation task. We consider age recommendation as a regression task, and discuss the need for appropriate evaluation metrics, study the use of state-of-the-art machine learning model, namely Transformers, and compare it to different models coming from the literature. Our results are also compared with recommendations made by experts. Further, this paper deals with preliminary explainability of the age prediction model by analyzing various linguistic features. We conduct the experiments on a dataset of 3, 673 French texts (132K sentences, 2.5M words). To recommend age at the text level and sentence level, our best models achieve MAE scores of 0.98 and 1.83 respectively on the test set. Also, compared to the recommendations made by experts, our sentence-level recommendation model gets a similar score to the experts, while the text-level recommendation model outperforms the experts by an MAE score of 1.48.

Cardiovascular disease, the leading cause of death globally, is an age-related disease. Understanding the morphological and functional changes of the heart during ageing is a key scientific question, the answer to which will help us define important risk factors of cardiovascular disease and monitor disease progression. In this work, we propose a novel conditional generative model to describe the changes of 3D anatomy of the heart during ageing. The proposed model is flexible and allows integration of multiple clinical factors (e.g. age, gender) into the generating process. We train the model on a large-scale cross-sectional dataset of cardiac anatomies and evaluate on both cross-sectional and longitudinal datasets. The model demonstrates excellent performance in predicting the longitudinal evolution of the ageing heart and modelling its data distribution. The codes are available at https://github.com/MengyunQ/AgeHeart.

The deployment of face recognition systems has gained popularity in various application scenarios, such as border control initiatives like the European Entry-Exit System (EES) [Eu19]. In particular, the EES will be used as a central system for collecting and querying traveller data to the Schengen area at all border crossing points to facilitate the cooperation of visa and law enforcement authorities. The biometric performance of a system deployed in such sensitive environments must comply with high standards, such as those defined in the best practices for automated border control of the European Border and Coast Guard Agency (Frontex) [Fr15]. At the same time, the European General Data Protection Law complicates the processing of biometric data to avoid privacy leakages. Without an appropriate performance testing strategy, the risk of security lapses increases significantly and allows for the discriminatory treatment of travellers due to algorithmic or dataset bias. One solution to the lack of available test data includes the generation of synthetic data samples. However, in order to conduct reliable biometric performance tests, the synthetic samples must be as similar as possible to data collected in operational environments.

In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We disentangle the style and content of the input image and propose a new decoder network that adopts a style-based strategy to combine the style and content representations of the input image while conditioning the output on the target age. We go beyond existing aging methods allowing users to adjust the degree of structure preservation in the input image during inference. To this purpose, we introduce a masking mechanism, the CUstom Structure Preservation module, that distinguishes relevant regions in the input image from those that should be discarded. CUSP requires no additional supervision. Finally, our quantitative and qualitative analysis which include a user study, show that our method outperforms prior art and demonstrates the effectiveness of our strategy regarding image editing and adjustable structure preservation.