Search

Skin cancer segmentation poses a significant challenge in medical image analysis. Numerous existing solutions, predominantly CNN-based, face issues related to a lack of global contextual understanding. Alternatively, some approaches resort to large-scale Transformer models to bridge the global contextual gaps, but at the expense of model size and computational complexity. Finally many Transformer based approaches rely primarily on CNN based decoders overlooking the benefits of Transformer based decoding models. Recognizing these limitations, we address the need efficient lightweight solutions by introducing MobileUNETR, which aims to overcome the performance constraints associated with both CNNs and Transformers while minimizing model size, presenting a promising stride towards efficient image segmentation. MobileUNETR has 3 main features. 1) MobileUNETR comprises of a lightweight hybrid CNN-Transformer encoder to help balance local and global contextual feature extraction in an efficient manner; 2) A novel hybrid decoder that simultaneously utilizes low-level and global features at different resolutions within the decoding stage for accurate mask generation; 3) surpassing large and complex architectures, MobileUNETR achieves superior performance with 3 million parameters and a computational complexity of 1.3 GFLOP resulting in 10x and 23x reduction in parameters and FLOPS, respectively. Extensive experiments have been conducted to validate the effectiveness of our proposed method on four publicly available skin lesion segmentation datasets, including ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets. The code will be publicly available at: https://github.com/OSUPCVLab/MobileUNETR.git, Comment: Accepted at ECCV 2024 - BioImage Computing Workshop (Oral)

Double field theory (DFT) can be constructed from the color-kinematic double copy of Yang-Mills theory. In a recent work, this construction has been extended to higher-derivative terms, starting from the four-derivative extension of Yang-Mills theory with an expectation to obtain a conformally invariant DFT action up to the third order. Here, I attempt to extend this higher-derivative DFT action for all orders in a manifestly background-independent way starting from the second order terms. The third order terms I obtained do not match the third order terms obtained directly from the double copy map. A clear understanding of this mismatch can give valuable information about the double copy procedure for DFT, its relation to background independence, and the conformal symmetry in double configuration space., Comment: 10 pages

Large-scale test collections play a crucial role in Information Retrieval (IR) research. However, according to the Cranfield paradigm and the research into publicly available datasets, the existing information retrieval research studies are commonly developed on small-scale datasets that rely on human assessors for relevance judgments - a time-intensive and expensive process. Recent studies have shown the strong capability of Large Language Models (LLMs) in producing reliable relevance judgments with human accuracy but at a greatly reduced cost. In this paper, to address the missing large-scale ad-hoc document retrieval dataset, we extend the TREC Deep Learning Track (DL) test collection via additional language model synthetic labels to enable researchers to test and evaluate their search systems at a large scale. Specifically, such a test collection includes more than 1,900 test queries from the previous years of tracks. We compare system evaluation with past human labels from past years and find that our synthetically created large-scale test collection can lead to highly correlated system rankings., Comment: 9 pages, resource paper

Assessing seismic hazards and thereby designing earthquake-resilient structures or evaluating structural damage that has been incurred after an earthquake are important objectives in earthquake engineering. Both tasks require critical evaluation of strong ground motion records, and the knowledge of site conditions at the earthquake stations plays a major role in achieving the aforementioned objectives. Site conditions are generally represented by the time-averaged shear wave velocity in the upper 30 meters of the geological materials (Vs30). Several strong motion stations lack Vs30 measurements resulting in potentially inaccurate assessment of seismic hazards and evaluation of ground motion records. In this study, we present a deep learning-based approach for predicting Vs30 at strong motion station locations using three-channel earthquake records. For this purpose, Convolutional Neural Networks (CNNs) with dilated and causal convolutional layers are used to extract deep features from accelerometer records collected from over 700 stations located in Turkey. In order to overcome the limited availability of labeled data, we propose a two-phase training approach. In the first phase, a CNN is trained to estimate the epicenters, for which ground truth is available for all records. After the CNN is trained, the pre-trained encoder is fine-tuned based on the Vs30 ground truth. The performance of the proposed method is compared with machine learning models that utilize hand-crafted features. The results demonstrate that the deep convolutional encoder based Vs30 prediction model outperforms the machine learning models that rely on hand-crafted features., Comment: 12 pages, 14 figures, Accepted by 18th World Conference on Earthquake Engineering WCEE2024

We numerically calculate the dynamic structure factor of the simplest two dimensional $Z_2$ lattice gauge theory. This provides an important benchmark for future experiments which will explore the dynamics of such models. As would be expected, the spectrum is gapped away from the critical point, and can be understood in terms of the elementary excitations., Comment: 5 pages, 6 figures, journal article

Renew interest in the charge density wave phase of TiSe$_2$ stems from the realization of its unique driving mechanism, the so called excitonic insulator phase. Existing claims are motivated by model calculations of the band structure. In this study, angle resolved photoemsision spectroscopy and density functional theory for TiSe$_2$ are directly compared. The substantial discrepancies found between the two descriptions cast serious doubts on the exitonic insulator scenario as the correct physical mechanism underlying the periodic lattice distortion at low temperature. In particular, the formation of a valence-conduction hybridization gap in the bulk band structure is not present in the experimental data. Therefore, the origin of the structural transition in TiSe$_2$ cannot be fully explained within the existing theoretical models., Comment: 5 pages, 4 figures

The electronic origin of the structural transition in 1T-VSe$_2$ is re-evaluated through an extensive angle-resolved photoemission spectroscopy experiment. The components of the band structure, missing in previous reports, are revealed. Earlier observations, shown to be temperature independent and therefore not correlated with the phase transition, are explained in terms of the increased complexity of the band structure close to the Fermi level. Only the overall size of the Fermi surface is found to be positively correlated with the phase transition at 110 K. These observations, quite distant from the charge density wave scenario commonly considered for 1T-VSe$_2$, bring fresh perspectives toward the correct description of structural transitions in dichalcogenides materials., Comment: 7 pages, 4 figures

The LLMJudge challenge is organized as part of the LLM4Eval workshop at SIGIR 2024. Test collections are essential for evaluating information retrieval (IR) systems. The evaluation and tuning of a search system is largely based on relevance labels, which indicate whether a document is useful for a specific search and user. However, collecting relevance judgments on a large scale is costly and resource-intensive. Consequently, typical experiments rely on third-party labelers who may not always produce accurate annotations. The LLMJudge challenge aims to explore an alternative approach by using LLMs to generate relevance judgments. Recent studies have shown that LLMs can generate reliable relevance judgments for search systems. However, it remains unclear which LLMs can match the accuracy of human labelers, which prompts are most effective, how fine-tuned open-source LLMs compare to closed-source LLMs like GPT-4, whether there are biases in synthetically generated data, and if data leakage affects the quality of generated labels. This challenge will investigate these questions, and the collected data will be released as a package to support automatic relevance judgment research in information retrieval and search., Comment: LLMJudge Challenge Overview, 3 pages

The first edition of the workshop on Large Language Model for Evaluation in Information Retrieval (LLM4Eval 2024) took place in July 2024, co-located with the ACM SIGIR Conference 2024 in the USA (SIGIR 2024). The aim was to bring information retrieval researchers together around the topic of LLMs for evaluation in information retrieval that gathered attention with the advancement of large language models and generative AI. Given the novelty of the topic, the workshop was focused around multi-sided discussions, namely panels and poster sessions of the accepted proceedings papers., Comment: LLM4Eval Workshop Report

Immersive displays are advancing rapidly in terms of delivering perceptually realistic images by utilizing emerging perceptual graphics methods such as foveated rendering. In practice, multiple such methods need to be performed sequentially for enhanced perceived quality. However, the limited power and computational resources of the devices that drive immersive displays make it challenging to deploy multiple perceptual models simultaneously. We address this challenge by proposing a computationally-lightweight, text-guided, learned multitasking perceptual graphics model. Given RGB input images, our model outputs perceptually enhanced images by performing one or more perceptual tasks described by the provided text prompts. Our model supports a variety of perceptual tasks, including foveated rendering, dynamic range enhancement, image denoising, and chromostereopsis, through multitask learning. Uniquely, a single inference step of our model supports different permutations of these perceptual tasks at different prompted rates (i.e., mildly, lightly), eliminating the need for daisy-chaining multiple models to get the desired perceptual effect. We train our model on our new dataset of source and perceptually enhanced images, and their corresponding text prompts. We evaluate our model's performance on embedded platforms and validate the perceptual quality of our model through a user study. Our method achieves on-par quality with the state-of-the-art task-specific methods using a single inference step, while offering faster inference speeds and flexibility to blend effects at various intensities.

Despite the success of integrating large language models into the development of conversational systems, many studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses. Hence, many existing studies commonly assume the always need for Retrieval Augmented Generation (RAG) in a conversational system without explicit control. This raises a research question about such a necessity. In this study, we propose to investigate the need for each turn of system response to be augmented with external knowledge. In particular, by leveraging human judgements on the binary choice of adaptive augmentation, we develop RAGate, a gating model, which models conversation context and relevant inputs to predict if a conversational system requires RAG for improved responses. We conduct extensive experiments on devising and applying RAGate to conversational models and well-rounded analyses of different conversational scenarios. Our experimental results and analysis indicate the effective application of RAGate in RAG-based conversational systems in identifying system responses for appropriate RAG with high-quality responses and a high generation confidence. This study also identifies the correlation between the generation's confidence level and the relevance of the augmented knowledge., Comment: 12 pages, under review

We consider collaborative inference at the wireless edge, where each client's model is trained independently on their local datasets. Clients are queried in parallel to make an accurate decision collaboratively. In addition to maximizing the inference accuracy, we also want to ensure the privacy of local models. To this end, we leverage the superposition property of the multiple access channel to implement bandwidth-efficient multi-user inference methods. Specifically, we propose different methods for ensemble and multi-view classification that exploit over-the-air computation. We show that these schemes perform better than their orthogonal counterparts with statistically significant differences while using fewer resources and providing privacy guarantees. We also provide experimental results verifying the benefits of the proposed over-the-air multi-user inference approach and perform an ablation study to demonstrate the effectiveness of our design choices. We share the source code of the framework publicly on Github to facilitate further research and reproducibility., Comment: 15 pages, 8 figures. This work extends from our preliminary study presented at the 2022 IEEE International Symposium on Information Theory [1]. arXiv admin note: text overlap with arXiv:2202.03129

We prove a rigidity result for maps between \v{C}ech-Stone remainders under fairly mild forcing axioms., Comment: 8 pages

In this paper, we propose an algorithm for downlink (DL) channel covariance matrix (CCM) estimation for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) communication systems with base station (BS) possessing a uniform linear array (ULA) antenna structure. We consider a setting where the UL CCM is mapped to DL CCM by a mapping function. We first present a theoretical error analysis of learning a nonlinear embedding by constructing a mapping function, which points to the importance of the Lipschitz regularity of the mapping function for achieving high estimation performance. Then, based on the theoretical ground, we propose a representation learning algorithm as a solution for the estimation problem, where Gaussian RBF kernel interpolators are chosen to map UL CCMs to their DL counterparts. The proposed algorithm is based on the optimization of an objective function that fits a regression model between the DL CCM and UL CCM samples in the training dataset and preserves the local geometric structure of the data in the UL CCM space, while explicitly regulating the Lipschitz continuity of the mapping function in light of our theoretical findings. The proposed algorithm surpasses benchmark methods in terms of three error metrics as shown by simulations.

fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple responsible AI dimensions. This paper presents the library and exposes its underlying design principles: simplicity, coverage, extensibility and performance. We then present how these were implemented in the scientific and engineering choices taken when developing fmeval. A case study demonstrates a typical use case for the library: picking a suitable model for a question answering task. We close by discussing limitations and further work in the development of the library. fmeval can be found at https://github.com/aws/fmeval.

This study proposes a simple architecture for Enterprise application for Large Language Models (LLMs) for role based security and NATO clearance levels. Our proposal aims to address the limitations of current LLMs in handling security and information access. The proposed architecture could be used while utilizing Retrieval-Augmented Generation (RAG) and fine tuning of Mixture of experts models (MoE). It could be used only with RAG, or only with MoE or with both of them. Using roles and security clearance level of the user, documents in RAG and experts in MoE are filtered. This way information leakage is prevented.

In the present work, an approach to the moment closure problem on the basis of orthogonal polynomials derived from Gram matrices is proposed. Its properties are studied in the context of the moment closure problem arising in gas kinetic theory, for which the proposed approach is proven to have multiple attractive mathematical properties. Numerical studies are carried out for model gas particle distributions and the approach is compared to other moment closure methods, such as Grad's closure and the maximum-entropy method. The proposed ``Gramian'' closure is shown to provide very accurate results for a wide range of distribution functions.

Vibration sensors are essential in acquiring seismic activity for an accurate earthquake assessment. The state-of-the-art sensors can provide the best signal quality and the highest bandwidth; however, their high cost usually hinders a wide range of applicability and coverage, which is otherwise possible with their basic and cheap counterparts. But, their poor quality and low bandwidth can significantly degrade the signal fidelity and result in an imprecise analysis. To address these drawbacks, in this study, we propose a novel, high-quality, and full bandwidth seismic signal synthesis by transforming the signal acquired from an inferior sensor. We employ 1D Operational Generative Adversarial Networks (Op-GANs) with novel loss functions to achieve this. Therefore, the study's key contributions include releasing a new dataset, addressing operational constraints in seismic monitoring, and pioneering a deep-learning transformation technique to create the first virtual seismic sensor. The proposed method is extensively evaluated over the Simulated Ground Motion (SimGM) benchmark dataset, and the results demonstrated that the proposed approach significantly improves the quality and bandwidth of seismic signals acquired from a variety of sensors, including a cheap seismic sensor, the CSN-Phidgets, and the integrated accelerometers of an Android, and iOS phone, to the same level as the state-of-the-art sensor (e.g., Kinemetrics-Episensor). The SimGM dataset, our results, and the optimized PyTorch implementation of the proposed approach are publicly shared.

In this study, the problem of robust Schur stability of $n\times n$ dimensional matrix segments by using the bialternate product of matrices is considered. It is shown that the problem can be reduced to the existence of negative eigenvalues of two of three specially constructed matrices and the existence of eigenvalues belonging to the interval $[1,\infty)$ of the third matrix. A necessary and sufficient condition is given for the convex combinations of two stable matrices with rank one difference to be robust Schur stable. It is shown that the robust stability of the convex hull of a finite number of matrices whose two-by-two differences are of rank $1$ is equivalent to the robust stability of the segments formed by these matrices. Examples of applying the obtained results are given.

Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks. However, the precise role of user profiles and their effect mechanism on LLMs remains unclear. This study first confirms that the effectiveness of user profiles is primarily due to personalization information rather than semantic information. Furthermore, we investigate how user profiles affect the personalization of LLMs. Within the user profile, we reveal that it is the historical personalized response produced or approved by users that plays a pivotal role in personalizing LLMs. This discovery unlocks the potential of LLMs to incorporate a greater number of user profiles within the constraints of limited input length. As for the position of user profiles, we observe that user profiles integrated into different positions of the input context do not contribute equally to personalization. Instead, where the user profile that is closer to the beginning affects more on the personalization of LLMs. Our findings reveal the role of user profiles for the personalization of LLMs, and showcase how incorporating user profiles impacts performance providing insight to leverage user profiles effectively.

Microservice Architecture (MSA) is a popular architectural style that offers many advantages regarding quality attributes, including maintainability and scalability. Developing a system as a set of microservices with expected benefits requires a quality assessment strategy that is established on the measurements of the system's properties. This paper proposes a hierarchical quality model based on fuzzy logic to measure and evaluate the maintainability of MSAs considering ISO/IEC 250xy SQuaRE (System and Software Quality Requirements and Evaluation) standards. Since the qualitative bounds of low-level quality attributes are inherently ambiguous, we use a fuzzification technique to transform crisp values of code metrics into fuzzy levels and apply them as inputs to our quality model. The model generates fuzzy values for the quality sub-characteristics of the maintainability, i.e., modifiability and testability, converted to numerical values through defuzzification. In the last step, using the values of the sub-characteristics, we calculate numerical scores indicating the maintainability level of each microservice in the examined software system. This score was used to assess the quality of the microservices and decide whether they need refactoring. We evaluated our approach by creating a test set with the assistance of three developers, who reviewed and categorized the maintainability levels of the microservices in an open-source project based on their knowledge and experience. They labeled microservices as low, medium, or high, with low indicating the need for refactoring. Our method for identifying low-labeled microservices in the given test set achieved 94% accuracy, 78% precision, and 100% recall. These results indicate that our approach can assist designers in evaluating the maintainability quality of microservices., Comment: 35 pages, 7 figures, 10 tables, Accepted by Journal of Systems and Software on 17.06.2024,JSSOFTWARE-D-23-01011R2

The discovery of 80 K superconductivity in bilayer La$_3$Ni$_2$O$_7$ at pressures greater than 14 GPa presents a unique opportunity to study a novel class of high-temperature superconductors. Therefore, other bilayer nickelate following the classical ($T^{4+}$) Ruddlesden-Popper (RP) series of Sr$_3$Ni$_2$O$_7$ would present an interesting new candidate. In this work, we study the stabilization of RP $n=2$ phase in Sr$_3$Ni$_{2-x}$Al$_{x}$O$_7$, via floating zone growth of crystals. With powder and single crystal XRD, we study the stability range of the RP-type phase. Our Thermogravimetric Analysis (TGA), X-ray photoelectron spectroscopy (XPS) and gas extraction studies reveal a remarkably high oxidation state of Ni$^{4+}$. The obtained black crystals are insulating in transport and show a magnetic transition around 12 K.

This paper presents a review of the NTIRE 2024 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year's competition, the challenge images were collected with a mobile phone and the speed of algorithms was also measured alongside the quality of their output. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. There were 2 nominations: quality and efficiency. Top 5 solutions in terms of output quality were sorted by evaluation time (see Fig. 1). The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org., Comment: 10 pages, 10 figures

Machine learning (ML) and Artificial Intelligence (AI) have fueled remarkable advancements, particularly in healthcare. Within medical imaging, ML models hold the promise of improving disease diagnoses, treatment planning, and post-treatment monitoring. Various computer vision tasks like image classification, object detection, and image segmentation are poised to become routine in clinical analysis. However, privacy concerns surrounding patient data hinder the assembly of large training datasets needed for developing and training accurate, robust, and generalizable models. Federated Learning (FL) emerges as a compelling solution, enabling organizations to collaborate on ML model training by sharing model training information (gradients) rather than data (e.g., medical images). FL's distributed learning framework facilitates inter-institutional collaboration while preserving patient privacy. However, FL, while robust in privacy preservation, faces several challenges. Sensitive information can still be gleaned from shared gradients that are passed on between organizations during model training. Additionally, in medical imaging, quantifying model confidence\uncertainty accurately is crucial due to the noise and artifacts present in the data. Uncertainty estimation in FL encounters unique hurdles due to data heterogeneity across organizations. This paper offers a comprehensive review of FL, privacy preservation, and uncertainty estimation, with a focus on medical imaging. Alongside a survey of current research, we identify gaps in the field and suggest future directions for FL research to enhance privacy and address noisy medical imaging data challenges., Comment: 31 pages, 5 figures, 3 tables, Journal preprint

Prostate cancer is one of the most prevalent malignancies in the world. While deep learning has potential to further improve computer-aided prostate cancer detection on MRI, its efficacy hinges on the exhaustive curation of manually annotated images. We propose a novel methodology of semisupervised learning (SSL) guided by automatically extracted clinical information, specifically the lesion locations in radiology reports, allowing for use of unannotated images to reduce the annotation burden. By leveraging lesion locations, we refined pseudo labels, which were then used to train our location-based SSL model. We show that our SSL method can improve prostate lesion detection by utilizing unannotated images, with more substantial impacts being observed when larger proportions of unannotated images are used., Comment: 4 page paper accepted to IEEE International Symposium on Biomedical Imaging (ISBI 2024)

Click-Through Rate (CTR) prediction has become an essential task in digital industries, such as digital advertising or online shopping. Many deep learning-based methods have been implemented and have become state-of-the-art models in the domain. To further improve the performance of CTR models, Knowledge Distillation based approaches have been widely used. However, most of the current CTR prediction models do not have much complex architectures, so it's hard to call one of them 'cumbersome' and the other one 'tiny'. On the other hand, the performance gap is also not very large between complex and simple models. So, distilling knowledge from one model to the other could not be worth the effort. Under these considerations, Mutual Learning could be a better approach, since all the models could be improved mutually. In this paper, we showed how useful the mutual learning algorithm could be when it is between equals. In our experiments on the Criteo and Avazu datasets, the mutual learning algorithm improved the performance of the model by up to 0.66% relative improvement., Comment: 7 pages, 2 figures, 4 tables

Kagome vanadates {\it A}V$_3$Sb$_5$ display unusual low-temperature electronic properties including charge density waves (CDW), whose microscopic origin remains unsettled. Recently, CDW order has been discovered in a new material ScV$_6$Sn$_6$, providing an opportunity to explore whether the onset of CDW leads to unusual electronic properties. Here, we study this question using angle-resolved photoemission spectroscopy (ARPES) and scanning tunneling microscopy (STM). The ARPES measurements show minimal changes to the electronic structure after the onset of CDW. However, STM quasiparticle interference (QPI) measurements show strong dispersing features related to the CDW ordering vectors. A plausible explanation is the presence of a strong momentum-dependent scattering potential peaked at the CDW wavevector, associated with the existence of competing CDW instabilities. Our STM results further indicate that the bands most affected by the CDW are near vHS, analogous to the case of {\it A}V$_3$Sb$_5$ despite very different CDW wavevectors., Comment: 33 pages, 4 figures

Rule mining on knowledge graphs allows for explainable link prediction. Contrarily, embedding-based methods for link prediction are well known for their generalization capabilities, but their predictions are not interpretable. Several approaches combining the two families have been proposed in recent years. The majority of the resulting hybrid approaches are usually trained within a unified learning framework, which often leads to convergence issues due to the complexity of the learning task. In this work, we propose a new way to combine the two families of approaches. Specifically, we enrich a given knowledge graph by means of its pre-trained entity and relation embeddings before applying rule mining systems on the enriched knowledge graph. To validate our approach, we conduct extensive experiments on seven benchmark datasets. An analysis of the results generated by our approach suggests that we discover new valuable rules on the enriched graphs. We provide an open source implementation of our approach as well as pretrained models and datasets at https://github.com/Jean-KOUAGOU/EnhancedRuleLearning, Comment: 13 pages, 2 figures, 11 tables

Skin lesion datasets provide essential information for understanding various skin conditions and developing effective diagnostic tools. They aid the artificial intelligence-based early detection of skin cancer, facilitate treatment planning, and contribute to medical education and research. Published large datasets have partially coverage the subclassifications of the skin lesions. This limitation highlights the need for more expansive and varied datasets to reduce false predictions and help improve the failure analysis for skin lesions. This study presents a diverse dataset comprising 12,345 dermatoscopic images with 38 subclasses of skin lesions collected in Turkiye which comprises different skin types in the transition zone between Europe and Asia. Each subgroup contains high-resolution photos and expert annotations, providing a strong and reliable basis for future research. The detailed analysis of each subgroup provided in this study facilitates targeted research endeavors and enhances the depth of understanding regarding the skin lesions. This dataset distinguishes itself through a diverse structure with 5 super classes, 15 main classes, 38 subclasses and its 12,345 high-resolution dermatoscopic images., Comment: 12 pages, 2 figures, 1 table

Video scene graph generation (VidSGG) has emerged as a transformative approach to capturing and interpreting the intricate relationships among objects and their temporal dynamics in video sequences. In this paper, we introduce the new AeroEye dataset that focuses on multi-object relationship modeling in aerial videos. Our AeroEye dataset features various drone scenes and includes a visually comprehensive and precise collection of predicates that capture the intricate relationships and spatial arrangements among objects. To this end, we propose the novel Cyclic Graph Transformer (CYCLO) approach that allows the model to capture both direct and long-range temporal dependencies by continuously updating the history of interactions in a circular manner. The proposed approach also allows one to handle sequences with inherent cyclical patterns and process object relationships in the correct sequential order. Therefore, it can effectively capture periodic and overlapping relationships while minimizing information loss. The extensive experiments on the AeroEye dataset demonstrate the effectiveness of the proposed CYCLO model, demonstrating its potential to perform scene understanding on drone videos. Finally, the CYCLO method consistently achieves State-of-the-Art (SOTA) results on two in-the-wild scene graph generation benchmarks, i.e., PVSG and ASPIRe.

The main purpose and motivation of this article is to create a linear transformation on the polynomial ring of rational numbers. A matrix representation of this linear transformation based on standard fundamentals will be given. For some special cases of this matrix, matrix equations including inverse matrices, the Bell polynomials will be given. With the help of these equations, new formulas containing different polynomials, especially the Bernoulli polynomials, will be given. Finally, by applying the Laplace transform to the generating function for the Bernoulli polynomials, we derive some novel formulas involving the Hurwitz zeta function and infinite series., Comment: 17 pages

Power-law distribution is one of the most important laws known in nature. Such a special universal behavior is known to occur in very few physical systems. In this work, we analyzed the mortality distribution of the Covid-19 pandemic tails for different countries and continents to discuss the possible universal behavior of the pandemic. Surprisingly, we found that the mortality distribution of Covid-19 follows inverse power-law decays. These universal behaviors for the pandemic are reported in the present work for the first time. Additionally, we showed that mortality tails also decay with time obeying to the inverse power law., Comment: Submitted to Physica A

The advent of Vision Language Models (VLMs) transformed image understanding from closed-set classifications to dynamic image-language interactions, enabling open-vocabulary segmentation. Despite this flexibility, VLMs often fall behind closed-set classifiers in accuracy due to their reliance on ambiguous image captions and lack of domain-specific knowledge. We, therefore, introduce a new task domain adaptation for open-vocabulary segmentation, enhancing VLMs with domain-specific priors while preserving their open-vocabulary nature. Existing adaptation methods, when applied to segmentation tasks, improve performance on training queries but can reduce VLM performance on zero-shot text inputs. To address this shortcoming, we propose an approach that combines parameter-efficient prompt tuning with a triplet-loss-based training strategy. This strategy is designed to enhance open-vocabulary generalization while adapting to the visual domain. Our results outperform other parameter-efficient adaptation strategies in open-vocabulary segment classification tasks across indoor and outdoor datasets. Notably, our approach is the only one that consistently surpasses the original VLM on zero-shot queries. Our adapted VLMs can be plug-and-play integrated into existing open-vocabulary segmentation pipelines, improving OV-Seg by +6.0% mIoU on ADE20K, and OpenMask3D by +4.1% AP on ScanNet++ Offices without any changes to the methods.

This paper explores the application of deep learning (DL) techniques to strong motion records for single-station epicenter localization. Often underutilized in seismology-related studies, strong motion records offer a potential wealth of information about seismic events. We investigate whether DL-based methods can effectively leverage this data for accurate epicenter localization. Our study introduces AFAD-1218, a collection comprising more than 36,000 strong motion records sourced from Turkey. To utilize the strong motion records represented in either the time or the frequency domain, we propose two neural network architectures: deep residual network and temporal convolutional networks. Through extensive experimentation, we demonstrate the efficacy of DL approaches in extracting meaningful insights from these records, showcasing their potential for enhancing seismic event analysis and localization accuracy. Notably, our findings highlight significant reductions in prediction error achieved through the exclusion of low signal-to-noise ratio records, both in nationwide experiments and regional transfer-learning scenarios. Overall, this research underscores the promise of DL techniques in harnessing strong motion records for improved seismic event characterization and localization.