Secure transmission of private information over public channels without arousing suspicion remains a fundamental challenge in stega-nography. Traditional methods modify pixel-level or frequency-domain features, making them vulnerable to detection and degradation. Recent synthesis-based approaches leverage generative models to embed data but often suffer from limited capacity or visual artifacts. In this work, we propose a pose conditioned generative steganographic framework that decouples message representation from image content. Binary messages are first mapped to human poses using a geometry-aware codebook derived from real-world data. These poses then serve as structural conditions to guide diffusion-based image generation, producing semantically coherent and visually natural stego images. By encoding multiple human poses in a single image, our framework increases message capacity while preserving visual coherence. To enhance robustness, we introduce a randomized linear expansion scheme to stabilize pose-code mapping under occlusion and detection noise. We evaluate the method under various perturbations and assess detectability using state-of-the-art steganalysis models. Experimental results show strong imperceptibility, decoding accuracy, and semantic flexibility, highlighting the effectiveness of our framework in enabling secure and coverless generative steganography. The code for PCGS is made available at https://github.com/Neo-0-Gu/PCGS .
Current multi-dataset 3D object detection pipelines directly train the detectors from scratch, which achieves suboptimal performance owing to intrinsic discrepancies between various scenarios. In this paper, we observe that there are underlying shared spatial and semantic characteristics that can be excavated in a self-supervised and fully-supervised manner. Motivated by this, we propose a novel pre-training method (UniPT) with geometry-aware and semantic-aware supervision to obtain a universal representation of multiple datasets, thus reducing the vast differences. Concretely, we firstly perform the reconstruction of point cloud and point density estimation. Then, the occupancy prediction and classification guidance are provided in semantic-aware supervision. Moreover, we devise a cross-dataset integration scheme to minimize the differences of dataset-level features between domains. Extensive experiments on Waymo Open Dataset (WOD), nuScenes and KITTI with consolidation settings illustrate the effectiveness of our method. It is notable that UniPT surpasses the previous work Uni3D by 2.29 mAPH (L1) on WOD, 1.45 mAP (BEV) on nuScenes and 2.08 mAP (3D) on KITTI. Our code will be available at https://github.com/microjie372/UniPT .
Existing online hashing methods generally employ the Hamming distance for similarity evaluation, which leads to the information loss of data location. Candidate images may have the same Hamming distance but different similarity from the query, which reduces the retrieval accuracy. Especially for non-stationary data environments, concept drift problems are prevalent. The location information loss makes it more difficult for capturing the distribution changes in data environments. To alleviate above concerns, Incremental Hashing with Asymmetric Distance (ICHAD) is proposed in this paper for image retrieval in non-stationary environments. In ICHAD, the online asymmetric distance based on learned hash codes is employed for the similarity evaluation. It preserves the location information of data more accurately and is computed efficiently without accessing the old data. Experimental results show that ICHAD outperforms existing hashing methods in various non-stationary data scenarios with concept drift.
GUI automation testing is a mainstream approach to ensure the software quality of mobile applications. To reduce manual testing costs, a large number of automated test cases are typically executed for regression and compatibility testing whenever there are requirement changes or version updates. Although extensive research has applied LLMs and MLLMs to GUI automation, most of these works conduct testing in stable, interference-free environments. In contrast, real-world business scenarios often involve numerous dynamic interference factors and strong business-specific contexts, leading to lower success rates for these methods. To address these challenges, we propose a novel UI automation testing technology (UI-Most) based on a multi-agent architecture. This method is designed to enhance the robustness of UI automation testing by assigning specialized roles to independent agents and enabling their collaboration. At the same time, it leverages the business knowledge from AppGraph for one-shot learning, thereby improving the recognition of UI elements in new scenarios. The effectiveness of our approach has been validated on real test case sets. Furthermore, this method has already been applied to automated regression testing, significantly reducing both manual testing costs and maintenance overhead of test cases.
With the continuous development of 3D laser scanning technology, point clouds can quickly and intuitively obtain real-world information. Point cloud registration can solve the limitation that a single data source cannot fully reflect objective things. However, the partial overlap and the difficulty in identifying matchable and repeatable corresponding points lead to a large number of outliers and low registration accuracy. To address these issues, we propose a relative geometric-driven registration network with virtual correspondences (VRGNet). First, robust features between scenes are extracted through self-attention and cross-attention mechanisms. The virtual point generation (VPG) module is used to optimize point cloud position information and improve the point matching probability in overlapping areas. Then, combine the original and generated point clouds to learn rotation-invariant geometric features through relative geometric embedding (RGE). Finally, the coarse-to-fine point matching method is used to obtain reliable correspondences and high-precision transformation matrices. We conduct extensive testing on the large-scale outdoor KITTI dataset. The experimental results demonstrate that our method achieves higher efficiency and registration accuracy.
This paper proposes a data cleaning method combining the Local Outlier Factor with Image Threshold Segmentation (LOF-ITSM), in order to address the problem that traditional image threshold segmentation methods cannot effectively detect outlier data in wind power curves, and global thresholds are difficult to adapt to curve fuzzy boundaries. Firstly, the LOF algorithm is used to detect wind power data and identify outlier types of abnormal data; Then, by introducing a local adaptive threshold optimization mechanism, the image threshold segmentation method is improved to better adapt to the fuzzy boundaries in the curve, while alleviating the sensitivity of the LOF algorithm to stacked abnormal data. The experimental results show that this method can better detect abnormal data in the wind power curve, laying a data foundation for promoting efficient utilization of wind energy and green transformation of energy structure.
Robust monocular SLAM is challenged by image distortions and non-uniform keypoint distributions. This paper introduces SED-SLAM, a novel system enhancing distortion resilience through spatially equalized deep feature extraction. At its core, a lightweight Mobile-Superpoint network extracts discriminative features, while our proposed Spatially Adaptive Thresholding (SAT) module ensures their uniform spatial coverage by adaptively regulating keypoint selection. Experiments on public benchmarks demonstrate that SED-SLAM achieves superior trajectory accuracy and robustness under various image distortions with real-time efficiency. These results validate that jointly optimizing feature quality and spatial balance is critical for enhancing SLAM performance in challenging environments.
Object detection in aerial images is highly challenging due to the arbitrary orientation of targets and the scarcity of details in small targets. Aiming at the periodicity and boundary discontinuity of angle representation in traditional rotated bounding box detection, as well as the defect that feature representation struggles to balance spatial details and semantic enhancement, this paper proposes an Adaptive Radius Circular Smooth Label and a Lightweight Feature Enhancement Module. Detection performance is improved through geometric prior guidance and hierarchical feature interaction. Experiments on the DOTA and HRSC2016 datasets show that the proposed method achieves an mAP of 63.1
Optical Coherence Tomography (OCT) is a light-based, 3D imaging technique used in ophthalmology for eye disease detection. Every so often, the OCT device requires re-calibration, where setup parameters are re-evaluated to create updated correction vectors. These are critical for OCT imaging as they enable the removal of signal nonlinearities that lead to image resolution degradation. Here, we demonstrate that a nonlinear raw OCT signal can be efficiently corrected, i.e., linearised, using a neural network, without a priori knowledge of OCT device parameters. We test several training strategies for their successful performance - signal pre-processing and training dataset size variation - on both the computer-generated and experimental data.
Generative models have shown encouraging results for time series anomaly identification in the past few years. However, real-world time series data often presents inherent spatiotemporal uncertainties caused by noise and non-stationary environmental factors in sensor measurements. Moreover, there is a significant amount of redundant information association between various dimensions of data attributes. Existing approaches are unable to dynamically capture critical features and suppress noise interference in complex conditions like network-traffic, where the importance of each individual dimension in the temporal features often evolves dynamically over time. To solve these problems, we present Diff-DTF, a brand-new anomaly detection approach integrating diffusion models with dynamic dimension-aware mechanisms. Our method proposes a dynamic temporal feature extraction mechanism that adaptively allocates dimension-wise weights based on the temporal characteristics of the dataset to achieve dynamic focus on critical features. Furthermore, we creatively integrate depthwise separable convolution (DWConv) and partial convolution (PConv) to enhance information transmission. This allows our model to refine important information by adaptively emphasizing the most critical temporal characteristics. Diff-DTF significantly enhances the detection of anomalies in multivariate time series through an effective integration of diffusion models with dynamic temporal feature extraction and refinement processes. Comprehensive evaluations across four real-world time series datasets reveal significant performance gains over existing baseline methods, validating its effectiveness in detecting anomalies within complex multivariate time series data.
The detection head framework critically influences the balance between classification and localization in small object detection, yet existing designs often neglect task-specific feature interactions, leading to optimization conflicts. To address this, we propose Bi-Level Attention Head (BLAH), a novel framework that harmonizes dual-task learning through structured attention mechanisms and adaptive loss optimization. BLAH introduces two key innovations: (1) Channel Group Self-Attention (CGSA) stacks, which dynamically recalibrate channel-group dependencies to align classification and localization features, resolving spatial-channel decoupling limitations in conventional attention. (2) Dual-Task Attention (DTA), integrating global channel attention for classification robustness (translation invariance) and local spatial attention for precise localization (translation variability), enabling synergistic task interaction without computational overhead. Further, we design a Differentiable Task-Balanced Loss (DTBL) that adaptively modulates gradients between tasks via cosine similarity constraints, ensuring stable optimization without extra parameters. Extensive experiments on MS COCO and VisDrone demonstrate BLAH’s superiority. When integrated with DETR, Deformable DETR, and YOLOv10, BLAH achieves +1.2 AP_S on YOLOv12). Ablation studies validate each component’s necessity.
Effective helmet detection is critical for construction safety but challenging to deploy in resource-limited environments. This paper proposes an enhanced object detector based on YOLO11, integrating Deformable Weighted Residual (DWR) modules and a BIdirectional Feature Pyramid Network (BIFPN) architecture. This integration significantly reduces computational demands while improving accuracy over YOLO11. Comprehensive experiments confirm that our proposed model outperforms other leading detection methods, providing a highly accurate, efficient solution for real-time helmet detection in resource-constrained environments.
3D object detection is essential for autonomous driving, especially with the growing use of cost-effective visual cameras. However, relying solely on visual data for 3D detection presents key challenges: 1) Difficulty in obtaining accurate depth from single-frame images for precise 3D localization; 2) Challenge of projecting 3D bounding boxes consistently across multiple camera views for spatial coherence. To address these challenges, we propose a novel spatio-temporal transformer network that tracks object movement across frames using homography pose transformation matrices. This allows for the use of historical data to improve predictions for the current frame. Additionally, we integrate an advanced 3D Region of Interest (ROI) pooling technique, which refines 3D proposal generation, significantly enhancing detection precision. Our experimental results demonstrate the superior performance of our approach compared to existing methods, validating its effectiveness in real-world autonomous driving scenarios.
We propose a self-supervised pre-training framework for multivariate time-series classification that addresses the mismatch between fixed-window tokenization and the inherently variable temporal structure of real-world signals. Our framework combines Dynamic-Segment Masking (DSM) with a channel-independent Transformer encoder. DSM uses a recursive linear-fit validator to partition each sequence into content-adaptive, ϵ -linear segments and then randomly masks a proportion of segments. Besides, a lightweight, channel-independent Transformer encoder is trained to reconstruct the missing intervals, thereby learning temporal dependencies between observed and missing intervals. Despite having only 2.4 million parameters, our model achieves an average accuracy of 0.74 across 14 UEA benchmark datasets—exceeding a randomly initialized baseline by 7
Modern video understanding requires integrating multimodal signals, but current Multimodal Large Language Models (MLLMs) often process audio and visual streams separately, missing key relationships and causing fragmented understanding with a disjointed audio-visual representation. In this work, we propose UniAVLM, a large audio-visual language model for comprehensive video understanding, which first employing Whisper-style audio feature extraction to capture relevant auditory information. We then introduce spatiotemporal position encoding to enhance the video representation with temporal dynamics. Finally, we implement cross-modal attention mechanisms to explicitly fuse the audio and visual features, allowing the model to learn the intricate relationships between these modalities and creating a cohesive multimodal representation. We conduct extensive experiments on the Audio-Visual Scene-Aware Dialogue (AVSD) benchmark, comparing our model against seven representative multimodal baselines and demonstrate state-of-the-art performance, with our model achieving 48.91
In recent years, frequency-domain modeling has emerged as a popular approach for time series forecasting due to its ability to capture recurring patterns. However, classical Fourier-based techniques often face difficulties in representing structural relationships and dynamic variations within non-stationary multivariate sequences, leading to spectral confusion across both temporal and channel dimensions. To address this issue, we introduce SpecMixer, a frequency-aware forecasting framework that jointly alleviates spectral confusion from the perspectives of local temporal dynamics and inter-channel structures. The framework incorporates an adaptive windowed Short-Time Fourier Transform, a Locality-Sensitive Hashing based channel grouping strategy, and a Dual-Bucket Attention mechanism, which together enhance local spectral resolution and strengthen cross-channel dependency modeling. Comprehensive experiments on four benchmark datasets—ETT, Weather, Traffic, and Electricity—demonstrate that SpecMixer consistently surpasses competitive baselines in medium- and long-term forecasting tasks, achieving improved accuracy and robustness. These findings highlight the significance of mitigating spectral confusion across time and channel dimensions and establish a new foundation for frequency-domain modeling of complex multivariate time series.
Existing prediction models that rely on static architectures and fixed receptive fields often have difficulty handling complex non-stationary behaviors such as sudden state transitions, transient anomalies, and heterogeneous frequency patterns that are common in real-world time series. These characteristics pose a major challenge to models that lack spectral filtering and adaptive reasoning capabilities, severely limiting their effectiveness in capturing changing temporal dynamics. To address this critical challenge, we propose a Temporal-Spiking-Spatial-Attention Network (TSSA-Net), which integrates two complementary modules: a frequency-based spatial-temporal attention (FSTA) and a just-in-time dynamic adaptor (JITDA). Inspired by Spiking Neural Networks, FSTA employs frequency-aware filtering and attention mechanisms to actively suppress noise and enhance salient signal patterns. JITDA leverages Just-in-Time Learning principles to dynamically calibrate predictions during inference, endowing the model with rapid adaptability to concept drift. Extensive experiments on multiple large-scale benchmark datasets demonstrate that TSSA-Net significantly outperforms all baseline methods, including the latest state-of-the-art models, showcasing its superior robustness and effectiveness in complex non-stationary environments.
Instance segmentation of individual tree crowns in aerial imagery is a critical task for forest management, carbon storage estimation, and biodiversity modeling. However, achieving effective segmentation faces significant challenges including dense canopy overlapping, diverse crown characteristics, and varying environmental conditions across different geographical regions. This paper proposes YOLOv8-UT, a unified training approach for cross-environment tree crown instance segmentation that enhances model generalization across rural and urban environments. YOLOv8-UT employs a two-stage training strategy that leverages unified pre-training on combined datasets followed by environment-specific fine-tuning to learn robust cross-environment features. Moreover, YOLOv8-UT incorporates the Large Kernel Attention mechanism to enhance feature representation for complex tree crown identification. Comprehensive experiments on aerial imagery from the Greater Wellington region demonstrate that YOLOv8-UT outperforms other recent peer competitors, achieving Box AP of 39.7 and Mask AP of 34.4 on the rural dataset, and Box AP of 48.2 and Mask AP of 40.5 on the urban dataset.
Skin lesion segmentation is a medical image analysis task that involves automatically delineating lesion boundaries from dermatoscopic or clinical images. It plays a critical role in the early detection of skin cancer like melanoma. Low contrast and fuzzy boundaries are the main challenges, especially for limited training images. To tackle these challenges with limited annotation data, we propose a controllable prompt generation agent to activate the skin lesion segmentation capability in vision foundation models for medical image analysis. Specifically, we reduce the pixel-level action space to the grid level for efficient search. With Convolutional Neural Networks as the backbone, the agent performs spatial reasoning over an image to simultaneously find the prompt coordinate and its label using a policy function, and provides the selected prompt points for vision foundation model. The interaction process will be terminated within a fixed iteration number. For optimization, we propose asymmetric rewards aligned with the value function and introduce them into proximal policy optimization to save computation and memory cost. Interestingly, better performance is achieved with fewer prompt points than the threshold number, along with some background points. Thus, the proposed agent is referred to as the Prompt Efficient Generation agent. Experimental results on public benchmark skin lesion segmentation datasets show that PEG outperforms state-of-the-art methods, and the IoU improvement is at least 4
Real-time anomaly detection in data streams requires continuous adaptation to evolving patterns and concept drift, yet existing methods rely on static algorithm selection and fixed hyperparameters that become suboptimal as data characteristics change. We introduce AutoSAD, the first fully autonomous framework that solves unsupervised streaming anomaly detection through intelligent model selection. Our approach maintains an ensemble of diverse detectors and employs multi-armed bandit optimization with normalized anomaly scores as reward signals, coupled with evolutionary hyperparameter mutation guided by performance feedback. Comprehensive evaluation on diverse datasets demonstrates that AutoSAD achieves superior performance, outperforming state-of-the-art streaming detectors and showing statistically significant improvements across varying data stream characteristics.
