Search

The purpose of the present work is to construct estimators for the random effects in a fractional diffusion model using a hybrid estimation method where we combine parametric and nonparametric thechniques. We precisely consider $n$ stochastic processes $\left\{X_t^j,\ 0\leq t\leq T\right\}$, $j=1,\ldots, n$ continuously observed over the time interval $[0,T]$, where the dynamics of each process are described by fractional stochastic differential equations with drifts depending on random effects. We first construct a parametric estimator for the random effects using the techniques of maximum likelihood estimation and we study its asymptotic properties when the time horizon $T$ is sufficiently large. Then by taking into account the obtained estimator for the random effects, we build a nonparametric estimator for their common unknown density function using Bernstein polynomials approximation. Some asymptotic properties of the density estimator, such as its asymptotic bias, variance and mean integrated squared error, are studied for an infinite time horizon $T$ and a fixed sample size $n$. The asymptotic normality and the uniform convergence of the estimator are investigated for an infinite time horizon $T$, a high frequency and as the order of Bernstein polynomials is sufficiently large. Some numerical simulations are also presented to illustrate the performance of the Bernstein polynomials based estimator compared to standard Kernel estimator for the random effects density function.

Reconstructing realistic 3D human models from monocular images has significant applications in creative industries, human-computer interfaces, and healthcare. We base our work on 3D Gaussian Splatting (3DGS), a scene representation composed of a mixture of Gaussians. Predicting such mixtures for a human from a single input image is challenging, as it is a non-uniform density (with a many-to-one relationship with input pixels) with strict physical constraints. At the same time, it needs to be flexible to accommodate a variety of clothes and poses. Our key observation is that the vertices of standardized human meshes (such as SMPL) can provide an adequate density and approximate initial position for Gaussians. We can then train a transformer model to jointly predict comparatively small adjustments to these positions, as well as the other Gaussians' attributes and the SMPL parameters. We show empirically that this combination (using only multi-view supervision) can achieve fast inference of 3D human models from a single image without test-time optimization, expensive diffusion models, or 3D points supervision. We also show that it can improve 3D pose estimation by better fitting human models that account for clothes and other variations. The code is available on the project website https://abdullahamdi.com/gst/ ., Comment: preprint

This paper presents an innovative approach utilizing in-memory computing (IMC) for the development and integration of AES (Advanced Encryption Standard) cipher technique. Our research aims to enhance cybersecurity measures for a wide range of applications for IoT, such as robotic self-driving and several uses contexts. Memristor (MR) design optimized for in-memory processing is introduced. Our work highlights the development of a 4-bit state memristor device tailored for various range of arithmetic functions in a hardware prototype of AES system. Additionally, we propose a pipeline AES design aimed at harnessing extensive parallelism and ensuring compatibility with MR devices. This approach enhances hardware performance by by managing larger data amounts, accelerating computational, and achieving greater precision demands. Compared to traditional AES hardware, AES-IMC demonstrates an approximate 30 % improvement in power with a comparable throughput rate. Compared with the latest AES-based NVM engines, AES-IMC achieves an impressive 62 % improvement in throughput at similar power dissipation levels. The IMC-developed design will protect against unintentional incidents involving unmanned devices, reducing the risks associated with hostile assaults such as hijacking and illegal control of robots. This helps to reduce the possible economic and financial losses caused by incidents, Comment: ATSIP2024 Conference , 6 pages

Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy. Previous solutions for learning NeRFs with sparse views and noisy poses only consider local geometry consistency with pairs of views. Closely following \textit{bundle adjustment} in Structure-from-Motion (SfM), we introduce TrackNeRF for more globally consistent geometry reconstruction and more accurate pose optimization. TrackNeRF introduces \textit{feature tracks}, \ie connected pixel trajectories across \textit{all} visible views that correspond to the \textit{same} 3D points. By enforcing reprojection consistency among feature tracks, TrackNeRF encourages holistic 3D consistency explicitly. Through extensive experiments, TrackNeRF sets a new benchmark in noisy and sparse view reconstruction. In particular, TrackNeRF shows significant improvements over the state-of-the-art BARF and SPARF by $\sim8$ and $\sim1$ in terms of PSNR on DTU under various sparse and noisy view setups. The code is available at \href{https://tracknerf.github.io/}., Comment: ECCV 2024 (supplemental pages included)

Whole Slide Image (WSI) classification with multiple instance learning (MIL) in digital pathology faces significant computational challenges. Current methods mostly rely on extensive self-supervised learning (SSL) for satisfactory performance, requiring long training periods and considerable computational resources. At the same time, no pre-training affects performance due to domain shifts from natural images to WSIs. We introduce Snuffy architecture, a novel MIL-pooling method based on sparse transformers that mitigates performance loss with limited pre-training and enables continual few-shot pre-training as a competitive option. Our sparsity pattern is tailored for pathology and is theoretically proven to be a universal approximator with the tightest probabilistic sharp bound on the number of layers for sparse transformers, to date. We demonstrate Snuffy's effectiveness on CAMELYON16 and TCGA Lung cancer datasets, achieving superior WSI and patch-level accuracies. The code is available on https://github.com/jafarinia/snuffy., Comment: Accepted for ECCV 2024

This paper introduces a perspective approach for simulating a memristive sensor tailored for low power biological analyte detection. The necessity for such innovation stems from the increasing demand for efficient biosensing technologies that can operate with minimal poxer consumption. Within this study, a numerical dynamic memristive model serves as a basis platform for implementing enhanced nanosensing method characterized by low cost and high sensitivity. Numerous simulations were conducted to validate the suitability of the dynamic memristive model's behaviour for emulating a chemical sensing approach. The simulated data is collected for deploying an AI application to ensure an advanced predictable biosensing intake function. All in all, this work paves the way for developing compact numerical models of memristive biosensors, addressing the pressing need for portable lox poxer consumption biosensing solutions., Comment: 6 pages

The metaverse, envisioned as the next digital frontier for avatar-based virtual interaction, involves high-performance models. In this dynamic environment, users' tasks frequently shift, requiring fast model personalization despite limited data. This evolution consumes extensive resources and requires vast data volumes. To address this, meta-learning emerges as an invaluable tool for metaverse users, with federated meta-learning (FML), offering even more tailored solutions owing to its adaptive capabilities. However, the metaverse is characterized by users heterogeneity with diverse data structures, varied tasks, and uneven sample sizes, potentially undermining global training outcomes due to statistical difference. Given this, an urgent need arises for smart coalition formation that accounts for these disparities. This paper introduces a dual game-theoretic framework for metaverse services involving meta-learners as workers to manage FML. A blockchain-based cooperative coalition formation game is crafted, grounded on a reputation metric, user similarity, and incentives. We also introduce a novel reputation system based on users' historical contributions and potential contributions to present tasks, leveraging correlations between past and new tasks. Finally, a Stackelberg game-based incentive mechanism is presented to attract reliable workers to participate in meta-learning, minimizing users' energy costs, increasing payoffs, boosting FML efficacy, and improving metaverse utility. Results show that our dual game framework outperforms best-effort, random, and non-uniform clustering schemes - improving training performance by up to 10%, cutting completion times by as much as 30%, enhancing metaverse utility by more than 25%, and offering up to 5% boost in training efficiency over non-blockchain systems, effectively countering misbehaving users., Comment: Accepted in IEEE Internet of Things Journal

Over the past decade, the technology used by referees in football has improved substantially, enhancing the fairness and accuracy of decisions. This progress has culminated in the implementation of the Video Assistant Referee (VAR), an innovation that enables backstage referees to review incidents on the pitch from multiple points of view. However, the VAR is currently limited to professional leagues due to its expensive infrastructure and the lack of referees worldwide. In this paper, we present the semi-automated Video Assistant Referee System (VARS) that leverages the latest findings in multi-view video analysis. VARS sets a new state-of-the-art on the SoccerNet-MVFoul dataset, a multi-view video dataset of football fouls. Our VARS achieves a new state-of-the-art on the SoccerNet-MVFoul dataset by recognizing the type of foul in 50% of instances and the appropriate sanction in 46% of cases. Finally, we conducted a comparative study to investigate human performance in classifying fouls and their corresponding severity and compared these findings to our VARS. The results of our study highlight the potential of our VARS to reach human performance and support football refereeing across all levels of professional and amateur federations., Comment: The paper is subject to the peer review process of Sports Engineering

Restricted Boltzmann machines are powerful tools in the field of generative, probabilistic learning, capable of capturing complex dependencies in data. By understanding their architecture and operational principles, one can employ them for diverse purposes such as dimensionality reduction, feature learning and even representing and analyzing various physical systems. This work aims to provide insights into the capabilities and limitations of restricted Boltzmann machines in modelling complex physical systems in the context of artificial spin ice. Geometrical frustration in artificial spin ice systems creates degeneracies leading to complex states and collective dynamics. From reconfigurable magnonics to neuromorphic computing, artificial spin systems are emerging as versatile functional platforms that go beyond simply imitating naturally occurring materials. Using out of equilibrium data from Monte Carlo simulations of artificial spin ice geometries, this work demonstrates the sensitivity of learning artificial spin ice state distributions with restricted Boltzmann machines. Results indicate that careful application of the restricted Boltzmann machine algorithm can reduce the training data required for feature extraction, which can be used for faster sample generation. Additionally, we demonstrate how the restricted Boltzmann machine can distinguish different artificial spin ice geometries by identifying their respective state distribution features.

We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven to be essential in previous work. The core idea is not only to do SfM for egocentric videos but also to do 2D-3D matching between existing 3D scans and 2D video frames. In this way, we have a hybrid SfM and camera relocalization pipeline, which can provide us with more camera poses, leading to higher QwP and overall success rate. Our method achieves the best performance regarding the most important metric, the overall success rate. We surpass previous state-of-the-art, the competitive EgoLoc, by $1.5\%$. The code is available at \url{https://github.com/Wayne-Mai/egoloc_v1}., Comment: 1st place winner of the 2024 Ego4D-Ego-Exo4D Challenge in VQ3D

Night time semantic segmentation is a crucial task in computer vision, focusing on accurately classifying and segmenting objects in low-light conditions. Unlike daytime techniques, which often perform worse in nighttime scenes, it is essential for autonomous driving due to insufficient lighting, low illumination, dynamic lighting, shadow effects, and reduced contrast. We propose RHRSegNet, implementing a relighting model over a High-Resolution Network for semantic segmentation. RHRSegNet implements residual convolutional feature learning to handle complex lighting conditions. Our model then feeds the lightened scene feature maps into a high-resolution network for scene segmentation. The network consists of a convolutional producing feature maps with varying resolutions, achieving different levels of resolution through down-sampling and up-sampling. Large nighttime datasets are used for training and evaluation, such as NightCity, City-Scape, and Dark-Zurich datasets. Our proposed model increases the HRnet segmentation performance by 5% in low-light or nighttime images.

We introduce MMIS, a novel dataset designed to advance MultiModal Interior Scene generation and recognition. MMIS consists of nearly 160,000 images. Each image within the dataset is accompanied by its corresponding textual description and an audio recording of that description, providing rich and diverse sources of information for scene generation and recognition. MMIS encompasses a wide range of interior spaces, capturing various styles, layouts, and furnishings. To construct this dataset, we employed careful processes involving the collection of images, the generation of textual descriptions, and corresponding speech annotations. The presented dataset contributes to research in multi-modal representation learning tasks such as image generation, retrieval, captioning, and classification.

Facial Expression Recognition (FER) is vital for understanding interpersonal communication. However, existing classification methods often face challenges such as vulnerability to noise, imbalanced datasets, overfitting, and generalization issues. In this paper, we propose GCF, a novel approach that utilizes Graph Convolutional Networks for FER. GCF integrates Convolutional Neural Networks (CNNs) for feature extraction, using either custom architectures or pretrained models. The extracted visual features are then represented on a graph, enhancing local CNN features with global features via a Graph Convolutional Neural Network layer. We evaluate GCF on benchmark datasets including CK+, JAFFE, and FERG. The results show that GCF significantly improves performance over state-of-the-art methods. For example, GCF enhances the accuracy of ResNet18 from 92% to 98% on CK+, from 66% to 89% on JAFFE, and from 94% to 100% on FERG. Similarly, GCF improves the accuracy of VGG16 from 89% to 97% on CK+, from 72% to 92% on JAFFE, and from 96% to 99.49% on FERG. We provide a comprehensive analysis of our approach, demonstrating its effectiveness in capturing nuanced facial expressions. By integrating graph convolutions with CNNs, GCF significantly advances FER, offering improved accuracy and robustness in real-world applications.

This paper deals with the problem of global parameter estimation of AD(1, n) where n is a positive integer which is a subclass of affine diffusions introduced by Duffie, Filipovic, and Schachermayer. In general affine models are applied to the pricing of bond and stock options, which is illustrated for the Vasicek, Cox-Ingersoll-Ross and Heston models. Our main results are about the conditional least squares estimation of AD(1, n) drift parameters based on two types of observations : continuous time observations and discrete time observations with high frequency and infinite horizon. Then, for each case, we study the asymptotic properties according to ergodic and non-ergodic cases. This paper introduces as well some moment results relative to the AD(1, n) model.

This paper proposes a short-range FMCW radar-based facial authentication and out-of-distribution (OOD) detection framework. Our pipeline jointly estimates the correct classes for the in-distribution (ID) samples and detects the OOD samples to prevent their inaccurate prediction. Our reconstruction-based architecture consists of a main convolutional block with one encoder and multi-decoder configuration, and intermediate linear encoder-decoder parts. Together, these elements form an accurate human face classifier and a robust OOD detector. For our dataset, gathered using a 60 GHz short-range FMCW radar, our network achieves an average classification accuracy of 98.07% in identifying in-distribution human faces. As an OOD detector, it achieves an average Area Under the Receiver Operating Characteristic (AUROC) curve of 98.50% and an average False Positive Rate at 95% True Positive Rate (FPR95) of 6.20%. Also, our extensive experiments show that the proposed approach outperforms previous OOD detectors in terms of common OOD detection metrics., Comment: Accepted at ICIP 2024

The relationship between urban form and function is a complex challenge that can be examined from multiple perspectives. In this study, we propose a method to characterize the urban function of U.S. metropolitan areas by analyzing trip patterns extracted from the 2017 National Household Travel Survey (NHTS). To characterize urban form, we employ measures that capture road network topology. We cluster cities based on both form and function and subsequently compare these clusters. Our analysis of 52 U.S. metropolitan areas identifies 7 distinct clusters of cities that exhibit similar travel behavior, suggesting that diverse mobility patterns can be effectively grouped into a few universal classes. The observed disparity between the urban-function clustering and the urban-form clustering suggests that travel behavior in the U.S. is not strongly influenced by the physical infrastructure of the city.

This paper presents a novel methodology for modeling memristive biosensing within COMSOL Multiphysics, focusing on critical performance metrics such as antigen-antibody binding concentration and output resistive states. By studying the impact of increasing inlet concentrations, insights into binding concentration curve and output resistance variations are uncovered. The resultant simulation data effectively trains a support vector machine classifier (SVMC), achieving a remarkable accuracy rate of 97%. The incorporation of artificial intelligence (AI) through SVM demonstrates promising strides in advancing AI-based memristive biosensing modeling, potentially elevating their performance standards and applicability across diverse domains., Comment: BIOSENSORS 2024

The capacity of a discrete-time multiple-input-multiple-output channel with correlated phase noises is investigated. In particular, the electro-optic frequency comb system is considered, where the phase noise of each channel is a combination of two independent Wiener phase-noise sources. Capacity upper and lower bounds are derived for this channel and are compared with lower bounds obtained by numerically evaluating the achievable information rates using quadrature amplitude modulation constellations. Capacity upper and lower bounds are provided for the high signal-to-noise ratio (SNR) regime. The multiplexing gain (pre-log) is shown to be $M-1$, where $M$ represents the number of channels. A constant gap between the asymptotic upper and lower bounds is observed, which depends on the number of channels $M$. For the specific case of $M=2$, capacity is characterized up to a term that vanishes as the SNR grows large., Comment: 45 pages, 3 figures, submitted to TIT, single-column

In this work, we present X-Diffusion, a cross-sectional diffusion model tailored for Magnetic Resonance Imaging (MRI) data. X-Diffusion is capable of generating the entire MRI volume from just a single MRI slice or optionally from few multiple slices, setting new benchmarks in the precision of synthesized MRIs from extremely sparse observations. The uniqueness lies in the novel view-conditional training and inference of X-Diffusion on MRI volumes, allowing for generalized MRI learning. Our evaluations span both brain tumour MRIs from the BRATS dataset and full-body MRIs from the UK Biobank dataset. Utilizing the paired pre-registered Dual-energy X-ray Absorptiometry (DXA) and MRI modalities in the UK Biobank dataset, X-Diffusion is able to generate detailed 3D MRI volume from a single full-body DXA. Remarkably, the resultant MRIs not only stand out in precision on unseen examples (surpassing state-of-the-art results by large margins) but also flawlessly retain essential features of the original MRI, including tumour profiles, spine curvature, brain volume, and beyond. Furthermore, the trained X-Diffusion model on the MRI datasets attains a generalization capacity out-of-domain (e.g. generating knee MRIs even though it is trained on brains). The code is available on the project website https://emmanuelleb985.github.io/XDiffusion/ ., Comment: preprint, project website: https://emmanuelleb985.github.io/XDiffusion/

With the ever-increasing reliance on digital networks for various aspects of modern life, ensuring their security has become a critical challenge. Intrusion Detection Systems play a crucial role in ensuring network security, actively identifying and mitigating malicious behaviours. However, the relentless advancement of cyber-threats has rendered traditional/classical approaches insufficient in addressing the sophistication and complexity of attacks. This paper proposes a novel 3-stage intrusion detection system inspired by a simplified version of the Lockheed Martin cyber kill chain to detect advanced multi-step attacks. The proposed approach consists of three models, each responsible for detecting a group of attacks with common characteristics. The detection outcome of the first two stages is used to conduct a feasibility study on the possibility of predicting attacks in the third stage. Using the ToN IoT dataset, we achieved an average of 94% F1-Score among different stages, outperforming the benchmark approaches based on Random-forest model. Finally, we comment on the feasibility of this approach to be integrated in a real-world system and propose various possible future work.

We compute the large size limit of the moment formula derived in \cite{DHS} for the Hermitian Jacobi process at fixed time. Our computations rely on the polynomial division algorithm which allows to obtain cancellations similar to those obtained in Lemma 3 in \cite{Bia}. In particular, we identify the terms contributing to the limit and show they satisfy a double recurrence relation. We also determine explicitly some of them and revisit a special case relying on Carlitz summation identity for terminating $1$-balanced ${}_4F_3$ functions taken at unity.

RISC-V cores have gained a lot of popularity over the last few years. However, being quite a recent and novel technology, there is still a gap in the availability of comprehensive simulation frameworks for RISC-V that cover both the functional and extra-functional aspects. This gap hinders progress in the field, as fast yet accurate system-level simulation is crucial for Design Space Exploration (DSE). This work presents an open-source framework designed to tackle this challenge, integrating functional RISC-V simulation (achieved with GVSoC) with SystemC-AMS (used to model extra-functional aspects, in detail power storage and distribution). The combination of GVSoC and SystemC-AMS in a single simulation framework allows to perform a DSE that is dependent on the mutual impact between functional and extra-functional aspects. In our experiments, we validate the framework's effectiveness by creating a virtual prototype of a compact, battery-powered embedded system., Comment: 4 pages, 4 figures, to be published in Computing Frontiers Workshops and Special Sessions (CF '24 Companion), May 7--9, 2024, Ischia, Italy

In image compression, with recent advances in generative modeling, the existence of a trade-off between the rate and the perceptual quality (realism) has been brought to light, where the realism is measured by the closeness of the output distribution to the source. It has been shown that randomized codes can be strictly better under a number of formulations. In particular, the role of common randomness has been well studied. We elucidate the role of private randomness in the compression of a memoryless source $X^n=(X_1,...,X_n)$ under two kinds of realism constraints. The near-perfect realism constraint requires the joint distribution of output symbols $(Y_1,...,Y_n)$ to be arbitrarily close the distribution of the source in total variation distance (TVD). The per-symbol near-perfect realism constraint requires that the TVD between the distribution of output symbol $Y_t$ and the source distribution be arbitrarily small, uniformly in the index $t.$ We characterize the corresponding asymptotic rate-distortion trade-off and show that encoder private randomness is not useful if the compression rate is lower than the entropy of the source, however limited the resources in terms of common randomness and decoder private randomness may be., Comment: Submitted to IEEE ISIT 2024

Effective feature representations play a critical role in enhancing the performance of text generation models that rely on deep neural networks. However, current approaches suffer from several drawbacks, such as the inability to capture the deep semantics of language and sensitivity to minor input variations, resulting in significant changes in the generated text. In this paper, we present a novel solution to these challenges by employing a mixture of experts, multiple encoders, to offer distinct perspectives on the emotional state of the user's utterance while simultaneously enhancing performance. We propose an end-to-end model architecture called ASEM that performs emotion analysis on top of sentiment analysis for open-domain chatbots, enabling the generation of empathetic responses that are fluent and relevant. In contrast to traditional attention mechanisms, the proposed model employs a specialized attention strategy that uniquely zeroes in on sentiment and emotion nuances within the user's utterance. This ensures the generation of context-rich representations tailored to the underlying emotional tone and sentiment intricacies of the text. Our approach outperforms existing methods for generating empathetic embeddings, providing empathetic and diverse responses. The performance of our proposed model significantly exceeds that of existing models, enhancing emotion detection accuracy by 6.2% and lexical diversity by 1.4%., Comment: Accepted to the LREC-COLING 2024

In biological, glassy, and active systems, various tracers exhibit Laplace-like, i.e., exponential, spreading of the diffusing packet of particles. The limitations of the central limit theorem in fully capturing the behaviors of such diffusive processes, especially in the tails, have been studied using the continuous time random walk model. For cases when the jump length distribution is super-exponential, e.g., a Gaussian, we use large deviations theory and relate it to the appearance of exponential tails. When the jump length distribution is sub-exponential the packet of spreading particles is described by the big jump principle. We demonstrate the applicability of our approach for finite time, indicating that rare events and the asymptotics of the large deviations rate function can be sampled for large length scales within a reasonably short measurement time., Comment: 14 pages, 8 figures

We consider the numerical behavior of the fixed-stress splitting method for coupled poromechanics as undrained regimes are approached. We explain that pressure stability is related to the splitting error of the scheme, not the fact that the discrete saddle point matrix never appears in the fixed-stress approach. This observation reconciles previous results regarding the pressure stability of the splitting method. Using examples of compositional poromechanics with application to geological CO$_2$ sequestration, we see that solutions obtained using the fixed-stress scheme with a low order finite element-finite volume discretization which is not inherently inf-sup stable can exhibit the same pressure oscillations obtained with the corresponding fully implicit scheme. Moreover, pressure jump stabilization can effectively remove these spurious oscillations in the fixed-stress setting, while also improving the efficiency of the scheme in terms of the number of iterations required at every time step to reach convergence.

Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting), a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes, requiring far fewer particles to represent a scene and thus significantly outperforming Gaussian Splatting methods in efficiency with a plug-and-play replacement ability for Gaussian-based utilities. GES is validated theoretically and empirically in both principled 1D setup and realistic 3D scenes. It is shown to represent signals with sharp edges more accurately, which are typically challenging for Gaussians due to their inherent low-pass characteristics. Our empirical analysis demonstrates that GEF outperforms Gaussians in fitting natural-occurring signals (e.g. squares, triangles, and parabolic signals), thereby reducing the need for extensive splitting operations that increase the memory footprint of Gaussian Splatting. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%. The code is available on the project website https://abdullahamdi.com/ges ., Comment: CVPR 2024 paper. project website https://abdullahamdi.com/ges