Search

Person re-identification (ReID) models often struggle to generalize across diverse cultural contexts, particularly in Islamic regions like Iran, where modest clothing styles are prevalent. Existing datasets predominantly feature Western and East Asian fashion, limiting their applicability in these settings. To address this gap, we introduce IUST_PersonReId, a dataset designed to reflect the unique challenges of ReID in new cultural environments, emphasizing modest attire and diverse scenarios from Iran, including markets, campuses, and mosques. Experiments on IUST_PersonReId with state-of-the-art models, such as Solider and CLIP-ReID, reveal significant performance drops compared to benchmarks like Market1501 and MSMT17, highlighting the challenges posed by occlusion and limited distinctive features. Sequence-based evaluations show improvements by leveraging temporal context, emphasizing the dataset's potential for advancing culturally sensitive and robust ReID systems. IUST_PersonReId offers a critical resource for addressing fairness and bias in ReID research globally. The dataset is publicly available at https://computervisioniust.github.io/IUST_PersonReId/., Comment: 12 pages, 4 figures. The dataset introduced in this paper, IUST_PersonReId, is publicly available at https://computervisioniust.github.io/IUST_PersonReId/

Cardiovascular magnetic resonance (CMR) imaging is the gold standard for diagnosing several heart diseases due to its non-invasive nature and proper contrast. MR imaging is time-consuming because of signal acquisition and image formation issues. Prolonging the imaging process can result in the appearance of artefacts in the final image, which can affect the diagnosis. It is possible to speed up CMR imaging using image reconstruction based on deep learning. For this purpose, the high-quality clinical interpretable images can be reconstructed by acquiring highly undersampled k-space data, that is only partially filled, and using a deep learning model. In this study, we proposed a stepwise reconstruction approach based on the Patch-GAN structure for highly undersampled k-space data compatible with the multi-contrast nature, various anatomical views and trajectories of CMR imaging. The proposed approach was validated using the CMRxRecon2024 challenge dataset and outperformed previous studies. The structural similarity index measure (SSIM) values for the first and second tasks of the challenge are 99.07 and 97.99, respectively. This approach can accelerate CMR imaging to obtain high-quality images, more accurate diagnosis and a pleasant patient experience.

This study proposes an attention-based statistical distance-guided unsupervised domain adaptation model for multi-class cardiovascular magnetic resonance (CMR) image quality assessment. The proposed model consists of a feature extractor, a label predictor and a statistical distance estimator. An annotated dataset as the source set and an unlabeled dataset as the target set with different statistical distributions are considered inputs. The statistical distance estimator approximates the Wasserstein distance between the extracted feature vectors from the source and target data in a mini-batch. The label predictor predicts data labels of source data and uses a combinational loss function for training, which includes cross entropy and centre loss functions plus the estimated value of the distance estimator. Four datasets, including imaging and k-space data, were used to evaluate the proposed model in identifying four common CMR imaging artefacts: respiratory and cardiac motions, Gibbs ringing and Aliasing. The results of the extensive experiments showed that the proposed model, both in image and k-space analysis, has an acceptable performance in covering the domain shift between the source and target sets. The model explainability evaluations and the ablation studies confirmed the proper functioning and effectiveness of all the model's modules. The proposed model outperformed the previous studies regarding performance and the number of examined artefacts. The proposed model can be used for CMR post-imaging quality control or in large-scale cohort studies for image and k-space quality assessment due to the appropriate performance in domain shift coverage without a tedious data-labelling process.

Anomaly detection involves identifying instances within a dataset that deviate from the norm and occur infrequently. Current benchmarks tend to favor methods biased towards low diversity in normal data, which does not align with real-world scenarios. Despite advancements in these benchmarks, contemporary anomaly detection methods often struggle with out-of-distribution generalization, particularly in classifying samples with subtle transformations during testing. These methods typically assume that normal samples during test time have distributions very similar to those in the training set, while anomalies are distributed much further away. However, real-world test samples often exhibit various levels of distribution shift while maintaining semantic consistency. Therefore, effectively generalizing to samples that have undergone semantic-preserving transformations, while accurately detecting normal samples whose semantic meaning has changed after transformation as anomalies, is crucial for the trustworthiness and reliability of a model. For example, although it is clear that rotation shifts the meaning for a car in the context of anomaly detection but preserves the meaning for a bird, current methods are likely to detect both as abnormal. This complexity underscores the necessity for dynamic learning procedures rooted in the intrinsic concept of outliers. To address this issue, we propose new testing protocols and a novel method called Knowledge Exposure (KE), which integrates external knowledge to comprehend concept dynamics and differentiate transformations that induce semantic shifts. This approach enhances generalization by utilizing insights from a pre-trained CLIP model to evaluate the significance of anomalies for each concept. Evaluation on CIFAR-10, CIFAR-100, and SVHN with the new protocols demonstrates superior performance compared to previous methods.

The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic data generators offer a promising alternative, particularly for embodied AI tasks, they often fall short for computer vision tasks due to low asset and rendering quality, limited diversity, and unrealistic physical properties. We introduce the BEHAVIOR Vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1K. BVS supports a large number of adjustable parameters at the scene level (e.g., lighting, object placement), the object level (e.g., joint configuration, attributes such as "filled" and "folded"), and the camera level (e.g., field of view, focal length). Researchers can arbitrarily vary these parameters during data generation to perform controlled experiments. We showcase three example application scenarios: systematically evaluating the robustness of models across different continuous axes of domain shift, evaluating scene understanding models on the same set of images, and training and evaluating simulation-to-real transfer for a novel vision task: unary and binary state prediction. Project website: https://behavior-vision-suite.github.io/, Comment: CVPR 2024 (Highlight). Project website: https://behavior-vision-suite.github.io/

Background: Image classification can be considered one of the key pillars of medical image analysis. Deep learning (DL) faces challenges that prevent its practical applications despite the remarkable improvement in medical image classification. The data distribution differences can lead to a drop in the efficiency of DL, known as the domain shift problem. Besides, requiring bulk annotated data for model training, the large size of models, and the privacy-preserving of patients are other challenges of using DL in medical image classification. This study presents a strategy that can address the mentioned issues simultaneously. Method: The proposed domain adaptive model based on knowledge distillation can classify images by receiving limited annotated data of different distributions. The designed multiple teachers-meticulous student model trains a student network that tries to solve the challenges by receiving the parameters of several teacher networks. The proposed model was evaluated using six available datasets of different distributions by defining the respiratory motion artefact detection task. Results: The results of extensive experiments using several datasets show the superiority of the proposed model in addressing the domain shift problem and lack of access to bulk annotated data. Besides, the privacy preservation of patients by receiving only the teacher network parameters instead of the original data and consolidating the knowledge of several DL models into a model with almost similar performance are other advantages of the proposed model. Conclusions: The proposed model can pave the way for practical clinical applications of deep classification methods by achieving the mentioned objectives simultaneously.

We present BEHAVIOR-1K, a comprehensive simulation benchmark for human-centered robotics. BEHAVIOR-1K includes two components, guided and motivated by the results of an extensive survey on "what do you want robots to do for you?". The first is the definition of 1,000 everyday activities, grounded in 50 scenes (houses, gardens, restaurants, offices, etc.) with more than 9,000 objects annotated with rich physical and semantic properties. The second is OMNIGIBSON, a novel simulation environment that supports these activities via realistic physics simulation and rendering of rigid bodies, deformable bodies, and liquids. Our experiments indicate that the activities in BEHAVIOR-1K are long-horizon and dependent on complex manipulation skills, both of which remain a challenge for even state-of-the-art robot learning solutions. To calibrate the simulation-to-reality gap of BEHAVIOR-1K, we provide an initial study on transferring solutions learned with a mobile manipulator in a simulated apartment to its real-world counterpart. We hope that BEHAVIOR-1K's human-grounded nature, diversity, and realism make it valuable for embodied AI and robot learning research. Project website: https://behavior.stanford.edu., Comment: A preliminary version was published at 6th Conference on Robot Learning (CoRL 2022)

Deposition of MoS2 on (111)-Au alters the electronic properties of MoS2. In this study, we investigate the free-standing MoS2 monolayer and the MoS2~\(111)-Au heterostructure, with and without strain, as well as defects of interest in memristive and neuromorphic applications. We focus on so-called atomristor devices based on monolayer materials that achieve resistive switching characteristics with the adsorption and desorption of metal adatoms. Our study confirms that the formation of midgap states is the primary mechanism behind the resistive switching. Our results show that strain lowers the adsorption~\desorption energies of Au+defect structures of interest, leading to more favorable switching energies, but simultaneously reduces the switching ratio between states of differing conductivities. The presence of the (111)-Au substrate additionally introduces non-uniform amounts of strain throughout and charge transfer to the MoS2 monolayer. We propose that the induced strain can contribute to the experimentally observed n- to p-type transition and Ohmic to Schottky transition in the MoS2 monolayer. The charge transfer leads to a permanent polarization at the interface, which can be tuned by strain. Our study has important implications on the role of the electrode as being a source of the observed variability in memristive devices and as serving as an additional degree of freedom for tuning the switching characteristics of the memristor device.

Partially synchronized solitary states occur frequently when a synchronized system of networked oscillators is perturbed locally. Several asymptotic states of different frequencies can coexist at the same node. Here, we reveal the mechanism behind this multistability: additional solitary frequencies arise from the coupling between network modes and the solitary oscillator's frequency, leading to significant energy transfer. This can cause the solitary node's frequency to resonate with a Laplacian eigenvalue. We analyze which network structures enable this resonance and explain longstanding numerical observations. Another solitary state is characterized by the effective decoupling of the synchronized network and the solitary node at the natural frequency. Our framework unifies the description of solitary states near and far from resonance, allowing to predict the behavior of complex networks.

The power-grid frequency reflects the balance between electricity supply and demand. Measuring the frequency and its variations allows monitoring of the power balance in the system and, thus, the grid stability. In addition, gaining insight into the characteristics of frequency variations and defining precise evaluation metrics for these variations enables accurate assessment of the performance of forecasts and synthetic models of the power-grid frequency. Previous work was limited to a few geographical regions and did not quantify the observed effects. In this contribution, we analyze and quantify the statistical and stochastic properties of self-recorded power-grid frequency data from various synchronous areas in Asia, Australia, and Europe at a resolution of one second. Revealing non-standard statistics of both empirical and synthetic frequency data, we effectively constrain the space of possible (stochastic) power-grid frequency models and share a range of analysis tools to benchmark any model or characterize empirical data. Furthermore, we emphasize the need to analyze data from a large range of synchronous areas to obtain generally applicable models., Comment: 7 pages; 7 figures

In this paper, we consider Einstein-Hilbert gravity in the presence of cosmological constant with cylindrical symmetry to introduce the black hole solution of this model. Here, we solve the Einstein's vacuum field equation, and then we calculate the appropriate metric for this problem., Comment: 9 pages, 1 figure, to appear in INJP

The paper is published in Chaos. Please refer to the Chaos version from now on. Anna B\"uttner, Anton Plietzsch, Mehrnaz Anvari, Frank Hellmann; A framework for synthetic power system dynamics. Chaos 1 August 2023; 33 (8): 083120. https://doi.org/10.1063/5.0155971 Information on power grids is confidential and thus real data is often inaccessible. This necessitates the use of synthetic power grid models in research. So far the models used, for example, in machine learning had to be very simple and homogeneous to produce large ensembles of robust grids. We present a modular framework to generate synthetic power grids that considers the heterogeneity of real power grid dynamics but remains simple and tractable. This enables the generation of large sets of synthetic grids for a wide range of applications. We also include the major drivers of fluctuations on short-time scales. The synthetic grids generated are robust and show good synchronization under all evaluated scenarios, as should be expected for realistic power grids. This opens the door to future research that studies grids under severe stress due to extreme events which could lead to destabilization and black-outs. A software package that includes an efficient Julia implementation of the framework is released as a companion to the paper.

Adaptivity is a dynamical feature that is omnipresent in nature, socio-economics, and technology. For example, adaptive couplings appear in various real-world systems like the power grid, social, and neural networks, and they form the backbone of closed-loop control strategies and machine learning algorithms. In this article, we provide an interdisciplinary perspective on adaptive systems. We reflect on the notion and terminology of adaptivity in different disciplines and discuss which role adaptivity plays for various fields. We highlight common open challenges, and give perspectives on future research directions, looking to inspire interdisciplinary approaches., Comment: 46 pages, 9 figures

The Texan electric network in the Gulf Coast of the United States is frequently hit by Tropical Cyclones (TC) causing widespread power outages, a risk that is expected to substantially increase under global warming. Here, we introduce a new approach of combining a probabilistic line fragility model with a network model of the Texas grid to simulate the temporal evolution of wind-induced failures of transmission lines and the resulting cascading power outages from seven major historical hurricanes. The approach allows reproducing observed supply failures. In addition, compared to a static approach, it provides a significant advantage in identifying critical lines whose failure can trigger large supply shortages. We show that protecting only 1% of total lines can reduce the likelihood of the most destructive type of outages by a factor of between 5 and 20. The proposed modelling approach could represent a tool so far missing to effectively strengthen the power grids against future hurricane risks even under limited knowledge.

Given a 4-manifold with a homologically trivial and locally-linear cyclic group action, we obtain necessary and sufficient conditions for the existence of equivariant bundles. The conditions are derived from the twisted signature formula and are in the form of congruence relations between the fixed point data and the isotropy representations., Comment: 23 pages (v2).Revisions following from referee reports

Stem cell-derived organoids are a promising tool to model native human tissues as they resemble human organs functionally and structurally compared to traditional monolayer cell-based assays. For instance, colon organoids can spontaneously develop crypt-like structures similar to those found in the native colon. While analyzing the structural development of organoids can be a valuable readout, using traditional image analysis tools makes it challenging because of the heterogeneities and the abstract nature of organoid morphologies. To address this limitation, we developed and validated a deep learning-based image analysis tool, named D-CryptO, for the classification of organoid morphology. D-CryptO can automatically assess the crypt formation and opacity of colorectal organoids from brightfield images to determine the extent of organoid structural maturity. To validate this tool, changes in organoid morphology were analyzed during organoid passaging and short-term forskolin stimulation. To further demonstrate the potential of D-CryptO for drug testing, organoid structures were analyzed following treatments with a panel of chemotherapeutic drugs. With D-CryptO, subtle variations in how colon organoids responded to the different chemotherapeutic drugs were detected, which suggest potentially distinct mechanisms of action. This tool could be expanded to other organoid types, like intestinal organoids, to facilitate 3D tissue morphological analysis., Comment: Lab on a Chip (2022)

Digitized documents such as scientific articles, tax forms, invoices, contract papers, historic texts are widely used nowadays. These document images could be degraded or damaged due to various reasons including poor lighting conditions, shadow, distortions like noise and blur, aging, ink stain, bleed-through, watermark, stamp, etc. Document image enhancement plays a crucial role as a pre-processing step in many automated document analysis and recognition tasks such as character recognition. With recent advances in deep learning, many methods are proposed to enhance the quality of these document images. In this paper, we review deep learning-based methods, datasets, and metrics for six main document image enhancement tasks, including binarization, debluring, denoising, defading, watermark removal, and shadow removal. We summarize the recent works for each task and discuss their features, challenges, and limitations. We introduce multiple document image enhancement tasks that have received little to no attention, including over and under exposure correction, super resolution, and bleed-through removal. We identify several promising research directions and opportunities for future research.