Search Results (456)

Steganography using deep learning can preserve pixel-level image quality while still changing object, attribute, or relational information in captions generated by vision-language models (VLMs). This caption drift creates a detection channel that is not measured by global image-embedding similarity alone. This paper presents StegoGuard, a framework that embeds secret payloads while enforcing caption-level semantic consistency. Concept drift is defined as a measurable divergence in object-level, attribute-level, or relational semantics between cover and stego captions and is quantified using CLIP text-embedding cosine distance. The main technical contribution is a cross-modal semantic drift regularization term based on BLIP-2 captions generated for cover and stego images. The framework combines this objective with CLIP-based saliency-guided region selection and a lightweight Vision Transformer encoder-decoder. Saliency-map quality is evaluated against ground-truth segmentation masks, and a deterministic bit-to-patch mapping protocol is provided for reproducibility. Experiments use COCO2017, DIV2K, and BOSSBase. Within the controlled six-baseline protocol, StegoGuard achieved a PSNR of 38.9 dB, an SSIM of 0.976 at 256 bits, detector AUC values of 0.521–0.562, and caption similarity of 0.962 as measured by CLIP text cosine similarity (model-relative, not human-verified). The ablation results show that the drift term reduces the measured concept-shift rates while preserving the reported bit-recovery and image-quality levels. Full article

Legal systems evolve continuously in response to legislative reforms, emerging judicial interpretations, and shifting societal expectations, making it increasingly difficult to anticipate changes in legal precedent using conventional analytical methods. This study introduces an explainable artificial intelligence framework for predictive jurisprudence that captures the temporal evolution of legal reasoning by jointly modeling semantic, structural, and causal relationships within judicial decisions. The proposed framework integrates neural temporal graph networks to learn evolving citation dependencies, dynamic topic modeling to characterize changes in legal doctrines over time, and causal-inference techniques to distinguish genuine jurisprudential influence from spurious associations. To enhance transparency, the predictive process is complemented by GNNExplainer, enabling the identification of the legal principles, precedents, and citation patterns that most strongly influence model predictions. The framework is evaluated using the Free Law Project and LePaRD benchmark datasets and demonstrates superior performance over existing approaches in detecting causal judicial influences and accurately quantifying precedent evolution. Its practical applicability and interpretability are further validated through expert legal assessment and historical backtesting against documented jurisprudential shifts. The experimental findings demonstrate that integrating explainable machine learning with causal legal analytics provides reliable early indicators of doctrinal change, offering valuable decision-support capabilities in legal environments. Full article

With the advancement of Earth observation technology and the improvement of multisource data acquisition capabilities, heterogeneous remote sensing image change detection technology has become increasingly important. However, existing heterogeneous remote sensing image change detection methods rely largely on fixed network architectures, which makes adapting to complex modal differences and severe noise interference difficult. To address these issues, in this paper, a decoupled differential search-based graph change detection network (DDS-Net) is proposed. First, the model designs a decoupled differential search-based dual-stream graph encoder (DDSGE). By decoupling the search space from the optimization strategy, it automatically optimizes feature extraction operators and graph topologies for different modalities, thereby significantly increasing feature adaptability while reducing computational complexity. Second, to address nonlinear geometric distortions between heterogeneous images, in this paper, a heterogeneous spatiotemporal alignment module that is based on differential localization search (HSTAM) is proposed. This module uses a local soft attention mechanism to dynamically correct registration errors in the feature space. Furthermore, to suppress erroneous graph connections caused by noise, structural consistency and smooth denoising (SCSD) loss is introduced, and deep semantic feedback and graph smoothing regularization constraints are collaboratively used to dynamically generate graphs, thereby effectively increasing the internal consistency of the transformed graph and suppressing misconnection noise. Extensive experimental results demonstrate that this method significantly improves the robustness and accuracy of the model in complex registration error scenarios while maintaining computational efficiency. Full article

Artifacts, including halos and saturated bright spots, are common in spaceborne optical images and can degrade the reliability of star extraction, space object detection, and photometric analysis. Traditional signal-processing methods, such as morphological filtering and low-rank decomposition, rely on fixed priors that may fail under complex artifact morphologies. Deep restoration networks can improve visual quality but do not explicitly enforce radiometric consistency. Multimodal instruction-driven editing models provide semantic localization capability, but probabilistic diffusion resampling can introduce uncontrolled pixel changes in non-target regions, compromising pixel-level physical consistency. We refer to this problem as editing-induced radiometric drift. To address this problem, we propose PARE, a physics-preserving attention-guided artifact removal framework for spaceborne optical images. Instead of directly using the edited image as the final restoration, PARE treats it as a candidate restoration and derives artifact-region constraints from the image-to-text cross-attention sub-block of the MM-DiT joint attention matrix. These constraints are combined with multi-scale fusion to restrict generative modification to localized artifact regions, thereby enabling artifact suppression while reducing unintended changes in non-target regions. Experiments on simulated and real spaceborne optical image datasets show that PARE achieves effective artifact suppression while improving radiometric preservation. On real on-orbit images, PARE reaches 92.95% artifact mean reduction (AMR) and 98.57% artifact energy reduction (AER), reduces the outer-region mean absolute error (O-MAE) to 0.54, and improves the outer-region structural similarity index (O-SSIM) to 0.997. It also yields the smallest background shifts among all compared methods. These results indicate that PARE provides a favorable trade-off between artifact suppression and radiometric fidelity and offers a practical way to apply generative models to scientific imaging tasks that require pixel-level physical consistency. Full article

Semantic Change Detection (SCD) in high-resolution remote sensing images is challenged by appearance-induced pseudo-changes and highly imbalanced class transitions. To address these coupled difficulties, we propose FD-ProtoSCD, a decoupled SCD framework that combines Frequency-Domain Change Disentanglement (FDCD) with a Dynamic Class Prototype Decoder (DCPD). FDCD decomposes bi-temporal features with a learnable Fourier-domain mask and emphasizes low-frequency structural differences while constraining high-frequency appearance variations in unchanged regions. DCPD maintains online semantic prototype banks and uses focal prototype contrastive learning to strengthen rare transition recognition. Under the reported comparison protocols, experiments on SECOND, Hi-UCD, and LEVIR-CD show improved semantic consistency and binary change localization over the included representative baselines, with an SCD score of 45.60 on SECOND and F1 scores of 46.23 and 94.24 on the Hi-UCD transfer and LEVIR-CD settings, respectively. Full article

The fine-scale monitoring of plantation cover disappearance and appearance is challenging because these changes are often expressed as weak within-class variations in high-resolution images. This study proposes MLLAForestCD, a three-class pixel-level semantic change-detection network for Eucalyptus plantations. The model uses an MLLA encoder to model the long-range spatial context with efficient linear attention, while a dual-axis change extractor reorganizes paired bi-temporal features through complementary layouts before contextual interaction. Multi-scale fusion then combines semantic cues with boundary-level details. We further construct the Eucalyptus Change Detection Dataset (ECDD), which contains plantation scenes with weak spectral contrast, fragmented boundaries, and directional canopy textures. Under the retained patch-level training/validation split, MLLAForestCD achieves an F1-score of 96.66% and an mIoU of 93.59%. After separate training and evaluation based on WHU-CD, it achieves an F1-score of 97.29% and an IoU of 90.10%; this result reflects performance under an independent WHU-CD training protocol. Finally, annual change maps from 2020 to 2023 are used to derive the most recently detected plantation-appearance time within the observation window. The resulting product is interpreted as a recent stand-renewal event map and requires independent forestry records before biological stand age can be inferred. Full article

Change detection in high-resolution optical remote sensing images is essential for dynamic surface monitoring and land resource management. However, existing methods still face challenges in representing multiscale change information, accurately locating change boundaries, and handling the imbalance between changed and unchanged samples. This study proposes SAM3TGNet, which transforms the general visual features of Segment Anything Model 3 (SAM3) into change-oriented representations through lightweight channel adaptation, multiscale cross-temporal interaction, and spatiotemporal feature fusion, while the Global Context Spatial Attention (GCSA) module and dynamic weighted loss enhance boundary representation and alleviate class imbalance, respectively. First, a SAM3-based bi-temporal remote sensing image feature encoder with channel adapters is developed, where intermediate multiscale feature layers are exploited to enhance semantic representation and generalization for diverse change patterns. Second, the GCSA module is introduced after spatiotemporal feature fusion to model global dependencies and enhance local details, improving boundary localization accuracy. Third, a dynamic weighted change loss function is designed to adaptively adjust the contribution of changed pixels according to their proportion in each batch, reducing background bias caused by sample imbalance and improving change localization and completeness. Experiments on the Wuhan University Change Detection (WHU-CD) and Sun Yat-sen University Change Detection (SYSU-CD) datasets demonstrate that the proposed method achieves F1-scores of 94.08 ± 0.12% and 82.91 ± 0.20%, respectively, outperforming existing approaches in multiscale change detection and boundary delineation. Full article

Geometry-processing and computational-imaging workflows combine heterogeneous data structures, topology-changing edits, dense numerical fields, visualization, and repeated experimental variation. These workflows are often clear as algorithms but obscured in software by traversal boilerplate, representation conversions, build-system boundaries, and ad hoc scripting conventions. This paper presents tgLang, a domain-specific language with explicit, runtime-enforced representation types that makes meshes, point clouds, curve networks, grids, two-dimensional images, and image stacks first-class executable values. The language combines manifest types, typed arrays, modules, deterministic parallel constructs, flow-oriented queries, and runtime-provided domain operations. Its current implementation uses a stack-based bytecode virtual machine for reference semantics and dispatches representation-heavy operations to optimized C++ kernels. The evaluation is organized around complete workflows: topological hole detection, distance-field-based mean camber line extraction, voxel downsampling of point clouds, curve-network generation, surface-mesh smoothing and remeshing, image-stack edge detection, morphological image processing, and image-stack surface extraction. These examples show that a domain-aware source language can express multi-representation geometry and imaging algorithms as compact, reproducible programs while preserving explicit representation choices and a path toward deployable implementations. Full article

Liver tumor segmentation is a significant task in clinical imaging that involves detecting liver tumors and distinguishing them from the surrounding liver tissue in CT scans. Precision segmentation performs important roles in the initial detection of liver cancer, treatment planning, and monitoring disease development, which also supports doctors, facilitating surgeries and radiation therapy more efficiently. Meanwhile, clinical imaging and segmentation algorithms have been enhanced over the years. The currently prevailing state-of-the-art methods still face multiple difficulties, though, in obtaining precision and reliability in their outcomes. Tumors with irregular shapes, variable sizes, and densities similar to those of surrounding tissues often lead to segmentation inaccuracies and potential misdiagnoses. In this work, we tackle these challenges by developing an advanced process for precise liver tumor segmentation by utilizing CT images from the LiTS dataset. The proposed DTARNU-Net was developed, trained, validated, and evaluated exclusively using the Liver Tumor Segmentation (LiTS) benchmark dataset. No experiments were conducted on the 3D-IRCADbI dataset in this study. All quantitative and qualitative results presented in the manuscript correspond to the LiTS dataset. The LiTS dataset contains contrast-enhanced abdominal CT scans with expert-annotated liver and tumor masks. The proposed model was evaluated using patient-level training, validation, and testing partitions (9:2:2 ratio), and all experiments were independently repeated five times. Statistical significance was assessed using paired Student’s t-test (p < 0.05), and the results confirmed that the performance improvements over competing methods are statistically significant. We introduce a novel three-level pre-processing approach that significantly enhances image quality through histogram equalization, noise removal, smoothing, and sharpening. Our approach is embodied in the Dense Tiered Attention Residual Nested U-Net (DTARNU-Net), a sophisticated model combining the strengths of a Siamese network and a nested U-Net architecture. This model incorporates the ACON-ReLU residual convolution block (A-R), which improves recognition accuracy in regions with subtle changes, reducing missed detection. The presented method enhances trait collaboration and spatial data by utilizing the Brownian Motion-based Butterfly Optimization Algorithm (BM-BOA). This algorithm efficiently integrates low-level trait details with high-level semantic data. The Dense Tiered Attention Residual Module (DTSRM) additionally improves these traits to obtain more precise segmentation. The model achieved segmentation robustness of 96.78% for liver segmentation and 97.00% for liver tumor segmentation on the LiTS dataset. These outcomes indicate that the presented method performs better than the prevailing state-of-the-art methods and has the capability to help computer-assisted detection and treatment by furnishing more precise and reliable liver tumor segmentation. Full article

Pixel-level annotation of bi-temporal high-resolution imagery is costly because annotators must distinguish genuine changes from pseudo-changes caused by illumination, seasonality, shadows, and residual misregistration. From a temporal-symmetry perspective, unchanged regions approximately preserve cross-temporal semantic correspondence, whereas genuine building changes introduce localized symmetry breaking between the two acquisition times. This paper presents BSCNet, a semi-supervised framework for binary building change detection that jointly models boundary-sensitive differences and scene-dependent scale preferences. A shared-weight MixTransformer extracts multi-level bi-temporal features. The Edge-Aware Optimization Module suppresses spatially invariant channel responses, enhances residual spatial cues, and predicts a Sobel-supervised edge map. The Parallel Selective Context Module aggregates depthwise-separable branches with different receptive fields and produces an image-level scale distribution. The Multi-scale Edge-Consistent Mean Teacher framework aligns the final prediction, intermediate edge representation, and scale-selection distribution between an exponential-moving-average teacher and the student. Experiments on WHU-CD and LEVIR-CD under 5%, 10%, and 20% labeled-data settings show consistent improvements over RCL, C2F-SemiCD, and CutMix-CD. With 5% labeled data, BSCNet achieves F1/IoU scores of 88.57%/79.49% on WHU-CD and 88.88%/79.98% on LEVIR-CD. An additional UAV-CD evaluation examines transfer to 0.06 m low-altitude UAV imagery containing both building and land changes; under 5% supervision, BSCNet obtains an F1/IoU of 68.07%/51.60%. Progressive ablations confirm complementary gains from the boundary, scale, and consistency components. Full article

Change detection under Gaussian noise is challenging because noise perturbs spectral clustering and posterior inference. This study presents a scene-adaptive weakly supervised framework that combines self-supervised single-image restoration with posterior-probability change modeling. A channel-spatial attention aggregation network (CAANet) is optimized jointly from the observed bitemporal scene by masked reconstruction without clean-image targets. The observed and restored images are coupled in a restoration-guided fuzzy decomposition, after which a normalized context-sensitive Bayesian network converts soft signal evidence into land-cover posterior vectors. Their temporal displacement is measured in a normalized semantic evidence space. Experiments on five remote-sensing datasets use zero-mean Gaussian noise with variance v ∈ {0.01, 0.03, 0.05, 0.07, 0.09}. At v = 0.05, FCC_CAANet achieves OA values of 0.9280–0.9659 and Kappa values of 0.7296–0.9521, obtaining the highest OA and Kappa on all five datasets among the implemented methods. The claims are limited to this controlled synthetic Gaussian-noise setting. Full article

In psychotherapy, case formulation can organize clinically relevant information into a coherent account of how psychological difficulties emerge, persist, and may change. The Personal Meaning System Fuzzy Cognitive Map (PMS-FCM) represents the client’s bipolar construct system as a weighted directed graph, whereas the FCM-FRHP (Fuzzy Cognitive Map of Human Problem Formation and Resolution) provides a professional functional reference model for problem formation and resolution. This paper proposes a semantically constrained method for identifying systemic archetype-inspired configurations in PMS-FCM representations enriched with FCM-FRHP semantics. Rather than importing classical systemic archetypes directly, the method reformulates them as configurable graph templates adapted to intrapersonal bipolar construct systems. Detection combines FCM-FRHP functional roles, predefined semantic-affinity rules and PB-based structural criteria, edge-weight thresholds, and ranking criteria. The goal is to support the traceable identification of static structures that may inform the examination of clinically relevant systemic hypotheses, without treating them as diagnoses or evidence of observed temporal dynamics. The pipeline combines property-graph querying, RDF/SHACL conformance checking, ranked materialization, and rule-based trace generation. A local language model is used only after detection and conformance checking, as a constrained graph-to-text layer grounded in graph evidence and FCM-FRHP semantics. The approach offers a formally specified and reproducible method for conducting explicit, auditable pattern-level analysis of psychological case formulations. Full article

Remote sensing (RS) image change detection (CD) is crucial for environmental monitoring, urban planning, and disaster assessment. Despite recent advances, existing methods struggle to effectively exploit bitemporal difference information, leading to false alarms caused by illumination or seasonal variations. Furthermore, they often fail to fully leverage coarse predictions as explicit semantic priors, restricting their capability to detect small-scale change regions. To address these issues, we propose a Difference-Gated Interaction and Change-Aware Cross-Temporal Fusion Network (DCAFNet) within a unified coarse-to-fine framework. Specifically, a Difference-Gated Feature Interaction (DGFI) module generates change correlation gates based on difference magnitudes to suppress pseudo-changes while preserving genuine change signals, and a Change-Aware Cross-Temporal Fusion (CCTF) module leverages coarse predictions as semantic guidance for feature recalibration and employs cross-temporal attention with learnable adaptive fusion to recover subtle change regions. Extensive experiments on four benchmark datasets (LEVIR-CD, WHU-CD, CDD, and SYSU-CD) demonstrate that DCAFNet consistently outperforms ten state-of-the-art methods, with additional ablation studies confirming the effectiveness of each component. Full article

Limited by the diversity and complexity of real-world scenes, existing remote sensing change detection methods often suffer from insufficient fine-grained semantic understanding and blurred boundaries of change targets. To address these issues, this paper proposes a boundary-constrained remote sensing change detection network based on vision foundation models (BCNet). BCNet employs a differential modeling approach and multi-branch guidance mechanism to design a differential detail enhancement module, amplifying fine-grained semantic information. Through cross-layer feature alignment, stepwise fusion, and edge-sensitive modeling, it constructs a multi-scale edge enhancement module that enhances perception of minute variations and edge details, fully leveraging the universal semantic representation capabilities of the vision foundation model. In addition, an edge feature constraint mechanism is introduced that applies dual guidance and supervision during the feature fusion and output stages. This mechanism achieves refined delineation of change region boundaries and significantly mitigates the issue of boundary blurring. Experimental results on four mainstream datasets, namely LEVIR-CD, WHU-CD, NJDS and MSRS-CD, demonstrate that BCNet outperforms 13 state-of-the-art methods in terms of key metrics including F1 and IoU. Against the best VFM-based baseline, BCNet obtains F1 score gains of 0.21%, 0.71%, 6.33% and 0.63% on the above four datasets. Specifically, the proposed method exhibits superior detection accuracy and edge detail preservation capabilities in complex regions. Full article

Frame-based RGB image sensors and event-based vision sensors provide complementary sensing capabilities for human-perceptual imaging and machine vision. RGB image sensors capture dense spatial, color, and texture information that is essential for human-viewable imaging, semantic recognition, and conventional image signal processing pipelines. In contrast, dynamic vision sensors (DVSs) and event vision sensors (EVSs) asynchronously detect local brightness changes and provide sparse temporal information with low latency, high temporal resolution, and reduced redundant data output. Because neither modality alone satisfies all requirements of emerging vision systems, hybrid event–frame sensing has become an important direction for compact, low-latency, and energy-efficient sensing. This review presents a sensor-oriented taxonomy of hybrid event–frame sensing architectures and systems, including dual-camera event–frame systems, optically aligned event–frame systems, pixel-level shared hybrid image sensors, stacked CIS–DVS hybrid image sensors, homogeneous-pixel sensing systems, and event-only reconstruction systems. We analyze key sensor specifications, including latency, spatial resolution, color fidelity, power consumption, and form factor, and discuss how these specifications guide sensor configuration and design. The review identifies stacked CIS–DVS sensors as one of the most balanced and competitive architectures because they can support compact integration, synchronized event–frame sensing, and on-chip processing. However, important challenges remain, including color fidelity, demosaicing, event-pixel ratio optimization, calibration, benchmarking, and edge-AI deployment. Finally, we emphasize that future hybrid event–frame sensing systems should be developed through sensor–algorithm–ISP–AI co-design. This review provides practical guidelines for developing next-generation hybrid event–frame sensing systems for both human-perceptual imaging and machine vision. Full article