With the rapid growth of social media and digital photography, visually appealing images have become essential for effective communication and emotional engagement. Among the factors influencing aesthetic appeal, composition—the arrangement of visual elements within a frame—plays a crucial role. In recent years, specialized models for photographic composition have achieved impressive results across various aesthetic tasks. Meanwhile, rapidly advancing multimodal large language models (MLLMs) have excelled in several visual perception tasks. However, their ability to embed and understand compositional information remains underexplored, primarily due to the lack of suitable evaluation datasets. To address this gap, we introduce the Photographic Image Composition Dataset (PICD), a large-scale dataset consisting of 36,857 images categorized into 24 composition categories across 355 diverse scenes. We demonstrate the advantages of PICD over existing datasets in terms of data scale, composition category, label quality, and scene diversity. Building on PICD, we establish benchmarks to evaluate the composition embedding capabilities of specialized models and the compositional understanding ability of MLLMs. To enable efficient and effective evaluation, we propose a novel Composition Discrimination Accuracy (CDA) metric. Our evaluation highlights the limitations of current models and provides insights into directions for improving their ability to embed and understand composition.

The rapid evolution of blockchain has established it as a critical enabler for decentralized zero-trust services and networks. Without relying on traditional trust mechanisms such as pre-established mutual trust or central authentication, blockchain facilitates trust-free services via smart contract. Smart contracts offer verifiable software trust for various blockchain-enabled services (BESs) while protecting participants’ interests. However, the impact of blockchain on BES remains underexplored and unclear. In this work, we consider a general BES framework suitable for diverse decentralized zero-trust services and assess the role of blockchain in BES. We first build anM/G/1-type queuing model for BES and establish the stability conditions using matrix analytic methods. Based on the stability conditions, we identify the blockchain scalability and server capability as two critical bottlenecks of BES. We further use a tandem queuing model to describe the BES latency of the assembling and service phases. We analytically characterize the properties such as the convexity of service-phase latency with respect to traffic intensity, and highlight the BES pooling effects from traffic offloading and resource sharing. At last, we verify our conclusions through simulations and explore potential pathways for more efficient BES frameworks.

Blockchain radio access network (B-RAN) offers a promising solution for trustworthy wireless applications by leveraging blockchain and smart contracts. However, the existing literature falls short in addressing the corresponding modeling and theoretical analysis. In this study, we develop analytical models to characterize the wireless access process in B-RAN, which also sheds light on other blockchain-enabled services. We first construct a two-dimensional queuing model and identify both blockchain scalability and RAN capability as two system bottlenecks, and then introduce the matrix analytic method to reduce complexity and improve efficiency. Furthermore, we build tandem queuing models for obtaining tight latency bounds with closed-form expressions. The performance and complexity of the proposed models are evaluated and compared against existing benchmarks to provide a comprehensive perspective. Finally, we present experimental results from a lab-built B-RAN prototype to demonstrate the efficacy of our models.

Arctic sea ice leads, which are narrow linear openings between sea ice, are critical to polar climate and ocean–atmosphere interactions. However, detecting multi-width leads accurately under the case of cloud interference remains challenging for thermal infrared (TIR) data. In this article, we propose an improved U-Net-based model–CTMLU-Net–which is designed to extract multi-width leads, including internal bright leads, from FY-3D MERSI-II 250-m TIR imagery under varied cloudy conditions. The model incorporates a dynamic fast Fourier transform (FFT) module to distinguish leads from clouds in the frequency domain and introduces cloud categories into the training labels to improve the lead detection accuracy. A dual-loss module and multi-window brightness temperature anomaly (BTA) inputs further enhance the sensitivity to different lead widths. Under cloudy conditions, CTMLU-Net achieved a precision of 86.82% and a recall of 71.73%, outperforming the traditional BTA method by 39.26% and 23.95%, respectively. For multi-width leads, it achieved a precision of 92.10% and a recall of 87.73%, and for bright leads, the corresponding scores were 90.59% and 84.75%, respectively. Compared to the original U-Net model, the FFT module improved the precision and recall by 4.80% and 17.66% in cloudy conditions, respectively. Compared to single-loss setting, the dual-loss module further enhanced the multi-width lead detection precision and recall by 23.64% and 9.92%. CTMLU-Net was also applied to 7045 scenes of MERSI-II TIR images to generate monthly Arctic lead frequency maps from November 2019 to April 2020. The spatiotemporal patterns of the leads can capture dynamic events, such as the collapse of the Beaufort High in spring 2020. Overall, CTMLU-Net offers a robust and accurate solution for multi-width sea ice lead detection under cloudy conditions.

Leads are almost linear fractures within the ice pack, which are commonly observed in polar regions. In wintertime, leads promote energy flux from the underlying ocean to the atmosphere. Synthetic aperture radar (SAR) can monitor leads at a finer spatial resolution than other spaceborne datasets, regardless of solar illumination and atmospheric conditions. However, the SAR-based lead detection methods proposed to date are restricted to some specific areas, instead of the entire Arctic. In this article, we present a generalized deep learning-based approach for automatic sea ice lead detection (SILDET) in the Arctic wintertime using Sentinel-1 SAR images. The validation results show that SILDET has the capability of detecting open and frozen leads at different stages of development. Compared with the visual interpretation of Sentinel-1 images, the overall detection accuracy is 97.80% and the Kappa coefficient is 0.88. The lead map of a regional study obtained from SILDET was compared to that from a previous SAR-based lead detection method and a lead dataset based on Moderate Resolution Imaging Spectroradiometer (MODIS) data. The lead map was also validated using Sentinel-2 images. The result shows that SILDET can provide a more detailed distribution of leads and a better estimation of lead width and area. SILDET was applied to present the Arctic-wide lead distribution from January to April 2023 with a spatial resolution of 40 m. The Arctic-wide lead width distribution follows a power law with an average exponent of 1.65. The SILDET approach can be expected to provide long-term high-resolution lead distribution records.

Watermarking by Zernike moments has been proven to be effective in providing high rotational resistance. However, due to the high computational complexity, the conventional video watermarking methods using Zernike moments are developed for videos with low resolution. Moreover, according to the properties of Zernike moments, only the matrices of equal height and width can be calculated since the inscribed circle of the original image matrix is selected as the area to be processed, but most of the available videos on the Internet do not meet such requirement. To solve the above problem, this paper proposes a fast watermarking method based on Zernike moments for high resolution videos to resist various attacks. In the proposed method, the frames of a video sequence are firstly grouped, from which a certain number of frame pairs are then selected for watermark embedding. For each frame pair to be embedded, we partition one frame into a set of disjoint blocks and apply singular value decomposition to each block to obtain a square feature matrix. Thereafter, by calculating all the Zernike moments, secret information is embedded into the selected Zernike moments to achieve superior robustness while keeping imperceptibility. Finally, according to the video encoding framework, we overwrite the frame difference of the frame pair by the watermark to resist compression and transcoding attacks. Furthermore, we propose two optional methods for compensating the special cases of rotation and scaling attacks during watermark detection. Experiments demonstrate the advantage of our method over the existing robust watermarking methods.

Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data is generally heterogeneous which dynamically varies over time, and this invalidates most existing community detection approaches. To cope with these issues, this paper proposes the temporal-heterogeneous graph convolutional networks (THGCN) to detect communities using the learnt feature representations of a set of temporal heterogeneous graphs. Particularly, we first design a heterogeneous GCN component to represent features of heterogeneous graph at each time step. Then, a residual compressed aggregation component is proposed to learn temporal feature representations extracted from two consecutive heterogeneous graphs. These temporal features are considered to contain evolutionary patterns of underlying communities. To the best of our knowledge, this is the first attempt to detect communities from temporal heterogeneous graphs. To evaluate the model performance, extensive experiments are performed on two real-world datasets, i.e., DBLP and IMDB. The promising results have demonstrated that the proposed THGCN is superior to both benchmark and the state-of-the-art approaches, e.g., GCN, GAT, GNN, LGNN, HAN and STAR, with respect to a number of evaluation criteria.

Lead is an important feature of the Arctic ice cover, with possible contents of thin ice /or open water. In this letter, we present an algorithm for lead detection based on brightness temperature observations from a single thermal infrared channel of MERSI-II onboard the Chinese FY-3D satellite. Lead contents is classified into open water and thin ice with support information from Sentinel-1 SAR data. Results are evaluated based on visual interpretation of MERSI-II TIR (Thermal infrared) and Sentinel-2 NIR (Near Infrared) data. The accuracy is found to be 85.6% for lead detection and 67% and 52% for thin ice and open water within the lead, respectively.

Because of the redundant information contained in the EEG signals, the classification accuracy of motor imagery may be greatly reduced. The channel selection method helps to remove task-independent EEG signals, thereby improving the performance of the BCI system. However, the brain regions associated with motor imagery in different subjects are not exactly same, and the method of channel selection depends on the feedback of classification results. Aiming at the above problems, this paper proposed a new method of channel selection based on backward elimination and threshold. First, we calculated the variance of channels between categories based on the covariance matrix. The backward selection and threshold selection methods were then used to retain the highly differentiated channels. We also used different criterion to evaluate the discriminability between different classes. The selected EEG signals used common spatial pattern (CSP) and support vector machine (SVM) to calculate the classification accuracy. The efficacy of the proposed approach was examined using three data sets. The proposed approach has achieved 77.82% accuracy on the BCI Competition IV data set IIa, 86.02% accuracy on the BCI Competition III data set IIIa, and 86.86% accuracy on the binary class BCI Competition III data set IVa. The performance of the proposed algorithm is compared with other existing algorithms. The results of our experiments demonstrated that the proposed algorithm produces a higher classification accuracy compared to the other algorithms using lesser number of channels.