Explore the vast range of titles available.

During the long history of computer vision, one of the grand challenges has been semantic segmentation which is the ability to segment an unknown image into different parts and objects (e.g., beach, ocean, sun, dog, swimmer). Furthermore, segmentation is even deeper than object recognition because recognition is not necessary for segmentation. Specifically, humans can perform image segmentation without even knowing what the objects are (for example, in satellite imagery or medical X-ray scans, there may be several objects which are unknown, but they can still be segmented within the image typically for further investigation). Performing segmentation without knowing the exact identity of all objects in the scene is an important part of our visual understanding process which can give us a powerful model to understand the world and also be used to improve or augment existing computer vision techniques. Herein this work, we review the field of semantic segmentation as pertaining to deep convolutional neural networks. We provide comprehensive coverage of the top approaches and summarize the strengths, weaknesses and major challenges.

The burning of fossil fuels in industry results in significant carbon emissions, and the heat generated is often not fully utilized. For high-temperature industries, thermophotovoltaics (TPVs) is an effective method for waste heat recovery. This review covers two aspects of high-efficiency TPV systems and industrial waste heat applications. At the system level, representative results of TPV complete the systems, while selective emitters and photovoltaic cells in the last decade are compiled. The key points of components to improve the energy conversion efficiency are further analyzed, and the related micro/nano-fabrication methods are introduced. At the application level, the feasibility of TPV applications in high-temperature industries is shown from the world waste heat utilization situation. The potential of TPV in waste heat recovery and carbon neutrality is illustrated with the steel industry as an example. The state of the art of the thermophotovoltaic (TPV) generation on heat recovery is highlighted. At the system level, representative results of TPV systems and components are compiled. At the application level, feasibility of TPV in high-temperature industrial applications is exhibited. Key points of TPV systems to improve energy conversion efficiency are further analyzed.

Remote sensing image segmentation requires balancing global context and local detail across multi-scale objects. However, convolutional neural network (CNN)-based methods struggle to model long-range dependencies, while transformer-based approaches suffer from quadratic complexity and become inefficient for high-resolution remote sensing scenarios. In addition, the semantic gap between deep and shallow features can cause misalignment during cross-layer aggregation, and information loss in upsampling tends to break thin continuous structures, such as roads and roof edges, introducing pronounced structural noise. To address these issues, we propose lightweight Lite-BSSNet (Blueprint-Guided State Space Network). First, a Structural Blueprint Generator (SBG) converts high-level semantics into an edge-enhanced structural blueprint that provides a topological prior. Then, a Visual State Space Bridge (VSS-Bridge) aligns multi-level features and projects axially aggregated features into a linear-complexity visual state space, smoothing high-gradient edge signals for sequential scanning. Finally, a Structural Repair Block (SRB) enlarges the effective receptive field via dilated convolutions and uses spatial/channel gating to suppress upsampling artifacts and reconnect thin structures. Experiments on the ISPRS Vaihingen and Potsdam datasets show that Lite-BSSNet achieves the highest segmentation accuracy among the compared lightweight models, with mIoU of 83.9% and 86.7%, respectively, while requiring only 45.4 GFLOPs, thus achieving a favorable trade-off between accuracy and efficiency.

We study language-guided target localization in synthetic aperture radar (SAR) imagery for deployment on resource-constrained platforms. Existing vision-language models either rely on heavy backbones unsuitable for edge devices or are designed for natural images, overlooking SAR-specific characteristics such as speckle noise, weak scattering responses, and geometric distortions. The proposed model, TVLightFormer, combines a lightweight dual-modal encoder (MobileNetV3 and TinyBERT) with a grouped-query attention (GQA) mechanism for efficient cross-modal interaction and an activation-free lightweight feature pyramid network (LFPN) to handle scale variation while preserving weak scattering signals. The individual modules are not claimed as newly invented components; the main contribution lies in their SAR-aware integration for edge-oriented cross-modal localization. We evaluate the model on five remote sensing datasets—SOMA-1M, ATRNet-STAR, GAIA, MLRSNet, and SODAS—under a unified localization setting, and we explicitly discuss the limitations introduced by weak or scene-level annotations. The results show that TVLightFormer achieves a favorable trade-off between accuracy and efficiency, reaching an average mIoU of 69.8% with 27.4 M parameters and 9.7 GFLOPs. Ablation studies quantify the contribution of each component. The model is suited for edge-oriented scenarios where computational resources are limited. We also provide a critical analysis of failure cases, SAR-specific disturbance factors, loss-function choices, and dataset-protocol sensitivity.

Referring Remote Sensing Image Segmentation (RRSIS) aims to accurately locate and segment target objects in high-resolution aerial imagery based on natural language descriptions. Most existing approaches either directly modify Referring Image Segmentation (RIS) frameworks originally designed for natural images or employ image-based foundation models such as SAM to improve segmentation accuracy. However, current RRSIS models still face substantial challenges due to the domain gap between remote sensing and natural images, including large-scale variations, arbitrary object rotations, and complex spatial–linguistic relationships. Consequently, such transfers often lead to weak cross-modal interaction, inaccurate semantic alignment, and reduced localization precision, particularly for small or rotated objects. In addition, approaches that rely on multi-stage alignment pipelines, redundant high-level feature fusion, or the incorporation of large foundation models generally incur substantial computational overhead and training inefficiency, especially when dealing with complex referring expressions in high-resolution remote sensing imagery. To address these challenges, we propose CD2FSAN, a CLIP-driven dynamic feature selection and alignment network that establishes a unified framework for fine-grained cross-modal understanding in remote sensing imagery. This network first follows the principle of maximizing cross-modal information to dynamically select the visual representations most semantically aligned with the language from CLIP’s hierarchical features, thereby strengthening cross-modal correspondence under image domain shifts. It then performs adaptive multi-scale aggregation and alignment to integrate linguistic cues into spatially diverse visual contexts, enabling precise feature fusion across varying object scales. Finally, a dynamic rotation correction decoder with differentiable affine transformation was designed to refine segmentation by compensating for orientation diversity and geometric distortions. Extensive experiments verify that CD2FSAN consistently outperforms existing methods in segmentation accuracy, validating the effectiveness of its core components while maintaining competitive computational efficiency. These results demonstrate the framework’s strong capability to bridge the cross-modal gap between language and remote sensing imagery, highlighting its potential for advancing semantic understanding in vision–language remote sensing tasks.

Remote sensing target detection faces significant challenges in handling multi-scale targets, with the high similarity in color and shape between targets and backgrounds in complex scenes further complicating the detection task. To address this challenge, we propose a multi-Scale and complex Background Aware network for remote sensing target detection, named YOLO-SBA. Our proposed YOLO-SBA first processes the input through the Multi-Branch Attention Feature Fusion Module (MBAFF) to extract global contextual dependencies and local detail features. It then integrates these features using the Bilateral Attention Feature Mixer (BAFM) for efficient fusion, enhancing the saliency of multi-scale target features to tackle target scale variations. Next, we utilize the Gated Multi-scale Attention Pyramid (GMAP) to perform channel–spatial dual reconstruction and gating fusion encoding on multi-scale feature maps. This enhances target features while finely suppressing spectral redundancy. Additionally, to prevent the loss of effective information extracted by key modules during inference, we improve the downsampling method using Asymmetric Dynamic Downsampling (ADDown), maximizing the retention of image detail information. We achieve the best performance on the DIOR, DOTA, and RSOD datasets. On the DIOR dataset, YOLO-SBA improves mAP by 16.6% and single-category detection AP by 0.8–23.8% compared to the existing state-of-the-art algorithm.

Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence. Like traditional machine learning, federated learning is threatened by multiple attacks, such as backdoor attacks, Byzantine attacks, and adversarial attacks. The weaknesses are exacerbated by the inaccessibility of data in federated learning, which makes it more difficult to defend against these threats. This points to the need for further research into defensive approaches to make federated learning a real solution for distributed machine learning paradigm with securing data privacy. Our survey provides a taxonomy of these threats and defense methods, describing the general situation of this vulnerability in federated learning. We also sort out the relationship between these methods, their advantages and disadvantages, and discuss future research directions regarding the security issues of federated learning from multiple perspectives.

Existing deepfake detection methods heavily rely on specific training data distributions and struggle to generalize to unknown forgery techniques. To address the challenge, this paper focuses on two critical research gaps: (1) the lack of systematic mining of standard features across multiple forgery methods; (2) the unresolved distribution shift problem in the strong supervised learning paradigm. To tackle these issues, we propose a self-supervised learning framework based on feature disentanglement, which enhances the generalization ability of detection models by uncovering the intrinsic features of forged content. The core method comprises three key components: self-supervised sample construction and training samples for feature disentanglement, which are generated via an image self-mixing mechanism; feature disentanglement network, where the input image is decomposed into two parts—content features irrelevant to forgery and discriminative forgery-related features; and conditional decoder verification, where both types of features are used to reconstruct the image, with forgery-related features serving as conditional vectors to guide the reconstruction process. Orthogonal constraints on features are enforced to mitigate the overfitting problem in traditional methods. Experimental results demonstrate that, compared with state-of-the-art methods, the proposed framework exhibits superior generalization performance in cross-unknown forgery technique detection tasks, effectively breaking through the dependency bottleneck of traditional supervised learning on training data distributions. This study provides a universal solution for deepfake detection that does not rely on specific forgery techniques. The model’s robustness in real-world complex scenarios is significantly improved by mining the common essence of forgery features.

What are the main findings? * A simulation with two IGS stations (>8000 km apart) indicates that the GFS-PPP method enables remote OH determination. With 10[sup.−18]-level ground clocks, the intercontinental-scale OH determination is expected to reach an accuracy of approximately 20 cm. * A multi-period joint-measurement strategy—aggregating sessions with stability-based weights—suppresses stochastic errors and enhances robustness, improving the reliability and accuracy of remote OH determination to the centimeter level. A simulation with two IGS stations (>8000 km apart) indicates that the GFS-PPP method enables remote OH determination. With 10[sup.−18]-level ground clocks, the intercontinental-scale OH determination is expected to reach an accuracy of approximately 20 cm. A multi-period joint-measurement strategy—aggregating sessions with stability-based weights—suppresses stochastic errors and enhances robustness, improving the reliability and accuracy of remote OH determination to the centimeter level. What are the implications of the main findings? * The findings quantify the practical limits of GNSS PPP time-frequency transfer and assess the achievable accuracy and performance bounds of the GFS-PPP approach for remote geopotential and OH determination. * The proposed stability-weighted multi-period joint-measurement strategy offers practical pathway toward centimeter-level cross-sea OH determination, thereby positioning GFS-PPP as a promising technique for establishing a high-precision IHRS. The findings quantify the practical limits of GNSS PPP time-frequency transfer and assess the achievable accuracy and performance bounds of the GFS-PPP approach for remote geopotential and OH determination. The proposed stability-weighted multi-period joint-measurement strategy offers practical pathway toward centimeter-level cross-sea OH determination, thereby positioning GFS-PPP as a promising technique for establishing a high-precision IHRS. State-of-the-art atomic clocks, in combination with high-precision time-frequency transfer techniques, have established a novel relativistic geodetic approach for determining the Earth’s geopotential. By exploiting ultra-stable atomic clocks and GNSS Precise Point Positioning (PPP) time-frequency transfer, this study investigates the cross-sea Orthometric Height (OH) determination between two remote stations separated by over 8000 km, corresponding to an OH difference of approximately 2260 m. Simulation results indicate that, when employing clocks with a frequency stability of 1 × 10[sup.−18], the remote OH determination could achieve a limiting accuracy of approximately 20 cm. This limitation is primarily attributed to the finite precision of the PPP time-frequency transfer, which constrains the ultimate performance of the OH determination. Furthermore, aggregating multiple observation periods could further enhance the accuracy to approximately 6 cm. These findings demonstrate that the PPP time-frequency transfer facilitates high-precision OH determination over intercontinental distances and thereby provides a feasible pathway toward the realization of a centimeter-level International Height Reference System (IHRS).

Detection of rotating targets in complex remote sensing scenarios often suffers from angular inconsistencies and boundary jitter, especially for small-to-medium objects with rapid pose changes or indistinct boundaries in dense environments. To address this, we propose ASBPNet, a unified framework coupling geometric alignment with policy adaptation. It features the following: (1) Angle-Synchronized Graph (ASG), which injects angle–alignment relationships and residual-based boundary refinement to improve rotational consistency and reduce boundary errors for small objects; (2) Bilevel Policy Optimization (BPO), which unifies control over rotation enhancement, sample allocation, block scanning, and rotational NMS for cross-stage policy coordination and improved recall. Together, ASG and BPO form a tightly coupled pipeline in which geometric alignment directly reinforces policy optimization, yielding mutually enhanced rotation robustness, boundary stability, and detection recall across densely distributed remote sensing scenes. We conducted systematic evaluations on datasets including DIOR-R, HRSC2016, and DOTAv1.0: compared to baselines, overall accuracy achieved significant improvement on DIOR-R, with performance reaching 98.2% on HRSC2016. Simultaneously, enhanced robustness and boundary stability were demonstrated in complex backgrounds and dense small-object scenarios, validating the synergistic value of geometric alignment and policy adaptation.