Day-to-night unpaired image translation is important to downstream tasks but remains challenging due to large appearance shifts and the lack of direct pixel-level supervision. Existing methods often introduce semantic hallucinations, where objects from target classes such as traffic signs and vehicles, as well as man-made light effects, are incorrectly synthesized. These hallucinations significantly degrade downstream performance. We propose a novel framework that detects and suppresses hallucinations of target-class features during unpaired translation. To detect hallucination, we design a dual-head discriminator that additionly performs semantic segmentation to identify hallucinated content in background regions. To suppress these hallucinations, we introduce class-specific prototypes, constructed by aggregating features of annotated target-domain objects, which act as semantic anchors for each class. Built upon a Schrödinger Bridge-based translation model, our framework performs iterative refinement, where detected hallucination features are explicitly pushed away from class prototypes in feature space, thus preserving object semantics across the translation trajectory. Experiments show that our method outperforms existing approaches both qualitatively and quantitatively. On the BDD100K dataset, it improves mAP by 15.5% for day-to-night domain adaptation, with a notable 31.7% gain for classes such as traffic lights that are prone to hallucinations.

The rapid emergence of image synthesis models poses challenges to the generalization of AI-generated image detectors. However, existing methods often rely on model-specific features, leading to overfitting and poor generalization. In this paper, we introduce the Multi-Cue Aggregation Network (MCAN), a novel framework that integrates different yet complementary cues as input. MCAN employs a mixture-of-encoders adapter to dynamically process these cues, enabling more adaptive and robust feature representation. Our cues include the input image itself, which represents the overall content, and high-frequency components that emphasize edge details. Additionally, we introduce a Chromatic Inconsistency (CI) cue, which normalizes intensity values and captures noise information introduced during the image acquisition process in real images, making these noise patterns more distinguishable from those in AI-generated content. Unlike prior methods, MCAN employs a multi-cue aggregation strategy, leveraging spatial, frequency, and chromaticity-based cues. These cues are intrinsically more indicative of real images, enhancing cross-model generalization. Extensive experiments on the GenImage, Chameleon, and UniversalFakeDetect benchmark validate the state-of-the-art performance of MCAN. In the GenImage dataset, MCAN outperforms the best state-of-the-art method by up to 7.4\% in average ACC across eight different image generators.

Sub-GHz, a frequency band under 1 GHz, has become an innovative internet of things solution by offering low power consumption and long-range communication capabilities. However, meter scale wavelengths (> 30 cm) make the design of compact and miniaturized sub-GHz devices highly challenging. Here, we propose a sub-GHz sensor based on magnetic hyperbolic metasurfaces (MHMSs) for object sensing. Intriguing high-kmodes are created by the hyperbolic dispersion of MHMs at low frequencies due to magnetic responses. Such bonded modes compact the detected propagating waves, i.e., magnetic hyperbolic polaritons, within MHMSs at a decay constant ~1.1 mm (~ 1 / 675 of the operation wavelength). Loaded on a flexible substrate, the planar sensor with normalized sizes of 0.052λg×0.026λg×0.0002λgachieves up to 9% sensitivity and 2.75 figure of merit at around 0.3925 GHz in experiments, with robustness against deformations like bending and twisting. The sensor operates efficiently for detecting small and ultrathin substances with 2.47% sensitivity and 0.91 figure of merit. The application of magnetic hyperbolic characteristics brings not only a novel prototype of sensing devices but also a strategy to design high-performance fundamental electric components at sub-GHz.

Inferring Gene Regulatory Networks (GRNs) from gene expression data is crucial for understanding biological processes. While supervised models are reported to achieve high performance for this task, they rely on costly ground truth (GT) labels and risk learning gene-specific biases—such as class imbalances of GT interactions—rather than true regulatory mechanisms. To address these issues, we introduce InfoSEM, an unsupervised generative model that leverages textual gene embeddings as informative priors, improving GRN inference without GT labels. InfoSEM can also integrate GT labels as an additional prior when available, avoiding biases and further enhancing performance. Additionally, we propose a biologically motivated benchmarking framework that better reflects real-world applications such as biomarker discovery and reveals learned biases of existing supervised methods. InfoSEM outperforms existing models by 38.5% across four datasets using textual embeddings prior and further boosts performance by 11.1% when integrating labeled data as priors.

Nighttime conditions pose a significant challenge to color constancy due to the diversity of lighting conditions and the presence of substantial low-light noise. Existing color constancy methods struggle with nighttime scenes, frequently leading to imprecise light color estimations. To tackle nighttime color constancy, we propose a novel unsupervised domain adaptation approach that utilizes labeled daytime data to facilitate learning on unlabeled nighttime images. To specifically address the unique lighting conditions of nighttime and ensure the robustness of pseudo labels, we propose adaptive channel masking and light uncertainty. By selectively masking channels that are less sen-sitive to lighting conditions, adaptive channel masking directs the model to progressively focus on features less affected by variations in light colors and noise. Addition-ally, our model leverages light uncertainty to provide a pixel-wise uncertainty estimation regarding light color prediction, which helps avoid learning from incorrect labels. Our model demonstrates a significant improvement in accuracy, achieving 21.5% lower Mean Angular Error (MAE) compared to the state-of-the-art method on our nighttime dataset.

Falling is ranked highly among the threats in elderly healthcare, which promotes the development of automatic fall detection systems with extensive concern. With the fast development of the Internet of Things (IoT) and Artificial Intelligence (AI), camera vision-based solutions have drawn much attention for single-frame prediction and video understanding on fall detection in the elderly by using Convolutional Neural Network (CNN) and 3D-CNN, respectively. However, these methods hardly supervise the intermediate features with good accurate and efficient performance on edge devices, which makes the system difficult to be applied in practice. This work introduces a fast and lightweight video fall detection network based on a spatio-temporal joint-point model to overcome these hurdles. Instead of detecting fall motion by the traditional CNNs, we propose a Long Short-Term Memory (LSTM) model based on time-series joint-point features extracted from a pose extractor . We also introduce the increasingly mature RGB-D camera and propose 3D pose estimation network to further improve the accuracy of the system. We propose to apply tensor train decomposition on the model to reduce storage and computational consumption so the deployment on edge devices can to realized. Experiments are conducted to verify the proposed framework. For fall detection task, the proposed video fall detection framework achieves a high sensitivity of 98.46% on Multiple Cameras Fall, 100% on UR Fall, and 98.01% on NTU RGB-D 120. For pose estimation task, our 2D model attains 73.3 mAP in the COCO keypoint challenge, which outperforms the OpenPose by 8%. Our 3D model attains 78.6% mAP on NTU RGB-D dataset with 3.6× faster speed than OpenPose.

Tripping or falling is among the top threats in elderly healthcare, and the development of automatic fall detection systems are of considerable importance. With the fast development of the Internet of Things (IoT), camera vision-based solutions have drawn much attention in recent years. The traditional fall video analysis on the cloud has significant communication overhead. This work introduces a fast and lightweight video fall detection network based on a spatio-temporal joint-point model to overcome these hurdles. Instead of detecting falling motion by the traditional Convolutional Neural Networks (CNNs), we propose a Long Short-Term Memory (LSTM) model based on time-series joint-point features, extracted from a pose extractor and then filtered from a geometric joint-point filter. Experiments are conducted to verify the proposed framework, which shows a high sensitivity of 98.46% on Multiple Cameras Fall Dataset and 100% on UR Fall Dataset. Furthermore, our model can achieve pose estimation tasks simultaneously, attaining 73.3 mAP in the COCO keypoint challenge dataset, which outperforms the OpenPose work by 8%.

SUMMARY: Colorectal cancer is a heterogeneous disease with diverse prognoses between left-sided and right-sided patients; therefore, it is necessary to precisely evaluate the survival probability of side-specific colorectal cancer patients. Here, we collected multi-omics data from The Cancer Genome Atlas program, including gene expression, DNA methylation and microRNA expression. Specificity measure and robust likelihood-based survival analysis were used to identify 6 left-sided and 28 right-sided prognostic biomarkers. Compared to the performance of clinical prognostic models, the addition of these biomarkers could significantly improve the discriminatory ability and calibration in predicting side-specific 5-year survival for colorectal cancer. Additional dataset derived from Gene Expression Omnibus was used to validate the prognostic value of side-specific genes. Finally, we constructed colorectal cancer side-specific molecular database (CoSMeD), a user-friendly interface for estimating side-specific colorectal cancer 5-year survival probability, which can lay the basis for personalized management of left-sided and right-sided colorectal cancer patients. AVAILABILITY AND IMPLEMENTATION: CoSMeD is freely available at https://mulongdu.shinyapps.io/cosmed. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

With the rapid development of remote sensing technology, how to accurately detect changes that have occurred on the land surface has been a critical task, particularly when images come from different satellite sensors. In this letter, we propose an unsupervised change detection method for heterogeneous synthetic aperture radar (SAR) and optical images based on the logarithmic transformation feature learning framework. First, the logarithmic transformation is applied to the SAR image that aims to achieve similar statistical distribution properties as the optical image. Then, high-level feature representations can be learned from the transformed image pair via joint feature extraction, which are used to select reliable samples for training a neural network classifier. When it is trained well, a robust change map can be obtained, thus identifying changed regions accurately. The experimental results on three real heterogeneous data sets demonstrate the effectiveness and superiority of the proposed method compared with other existing state-of-the-art approaches.

At present, the digital control technology of single chip microcomputer has been widely used in stage lighting control, but here are still some limitations in the system resources, such as computing speed, storage space and scalability. In order to improve these problems, this paper has proposed a new system design with an ARM microprocessor as the control core. The dimming data transmission follows the DMX512 protocol, so a digital PWM controller was used to generate duty-cycle adjustable PWM signal. The drive circuit controlled the IGBT device to turn-on and turn-off. Therefore, the brightness of lamp is adjustable through the dimming system. The experimental results have shown the perfect performance of simple operation and stable dimming effect of our system, which can satisfied the demand of stage dimming for modern performing places.