The rapid growth of short video platforms has made short video fake news detection a critical security task. This task predicts news authenticity by leveraging multimodal information, including video frames, text, audio, and others. Previous works typically capture temporal cues only implicitly and suffer from passive coarse aggregation that favors global semantics, thereby obscuring subtle tampering traces. In addition, treating videos as isolated instances fails to exploit global correlations, which hinders the refinement of predictions for ambiguous cases. To address these limitations, we propose a two-stage framework with Temporal Reprogramming and Residual Graph Label Propagation (TR-GLP) for short video fake news detection. Specifically, we first employ a Temporal Reprogramming module in Stage 1 to learn temporal pattern prototypes as a reference basis for video dynamics and re-express keyframe features via cross-attention over these prototypes, where prototype attention activations reveal prototype-inconsistent temporal cues and support fine-grained forgery detection. Subsequently, we utilize a Residual Graph Label Propagation Network in Stage 2 to propagate supervision from labeled to unlabeled samples over the graph, and the residual design aggregates global context while preserving instance-level features. Experiments on FakeSV and FakeTT indicate that TR-GLP delivers superior performance compared with representative baseline methods.

The exponential rise of social media videos necessitates accurate detection of hate speech targeting protected attributes. However, existing multimodal approaches are hindered by two critical limitations: symmetric fusion, which induces modal competition and sensitivity to visual noise, and instance-based retrieval, which suffers from semantic ambiguity and high computational overhead due to reliance on raw data. To address these challenges, we propose the Multimodal Pattern Bank-guided Hierarchical Complementary Gating (HCG-MPB) framework. Specifically, we introduce a Hierarchical Complementary Gating (HCG) mechanism. It initially utilizes text as a semantic anchor to establish a stable context, and subsequently generates dynamic gating weights to selectively integrate audio-visual features, thereby effectively suppressing noise while preserving complementary information. Furthermore, to address semantic and efficiency challenges, we propose the Multimodal Pattern Bank (MPB). Instead of retrieving from vast raw instances, MPB leverages Large Language Models (LLMs) to distill extensive training samples into a compact set of interpretable prototypes. This approach significantly minimizes the storage footprint and retrieval latency, providing robust semantic guidance without the computational burden of traditional methods. Experiments on two public datasets demonstrate that HCG-MPB achieves excellent performance in both detection accuracy and efficiency.

Image manipulation localization (IML) aims to segment manipulated regions in suspicious images. However, most existing methods rely solely on intrinsic features extracted from the input image and passively model local or global inconsistencies, making it difficult to accurately delineate manipulated regions with ambiguous boundaries. To address these challenges, we propose a prototype memory-based neighboring feature fusion network (PNF-Net), which is inspired by a biological memory mechanism. PNF-Net simulates selective preference by learning manipulation-trace prototypes as memory priors, thereby guiding representation learning toward consistent and discriminative manipulation cues. Specifically, we propose a memory-guided localization module (MLM) that models the consistencies and anomalies between manipulated regions and the background as memory priors, enabling precise localization. We then propose a neighboring feature interaction module (NFIM) that preserves fine-grained details from neighboring shallow features, enhances global semantics from neighboring deep features, and effectively fuses them. Finally, a verification fusion module (VFM) is designed to enrich contextual semantics and improve the completeness and accuracy of localization results. Extensive experiments on multiple benchmark datasets show that our PNF-Net outperforms most state-of-the-art IML models. Our code is available on https://github.com/vpsg-research/PNF-Net.

To develop a community-based care platform integrating traditional Chinese medicine (TCM) and Western medicine, in order to better meet the needs of elderly populations in chronic disease management. The platform incorporates TCM four-diagnosis data collection devices and standard health monitoring equipment, utilizes Internet of Things (IoT) technology for data transmission, and applies data analysis methods to identify health trends. Based on individual conditions, the system delivers personalized health guidance integrating both TCM and Western approaches, and supports follow-up and health education. The platform has achieved the integration of Traditional Chinese Medicine (TCM) and Western medical information, enabling continuous collection of health data and delivery of online intervention services. It has served over 200 elderly patients with chronic diseases, and user satisfaction surveys indicate high ratings in dimensions such as TCM integration and intervention practicality. The platform has improved the standardization and convenience of chronic disease management in community settings and demonstrates good potential for broader application in community-based elderly care.

Extracting singing melody from polyphonic music is an important topic in the field of music information retrieval. In this paper, we propose a singing melody extraction network consisting of five stacked multi-scale feature time-frequency aggregation (MF-TFA) modules. In the same network, deeper layers generally contain more contextual information than shallower layers. To help the shallower layers enhance the ability of task-relevant feature extraction, we propose a self-distillation and multi-level supervision (SD-MS) method, which leverages the feature distillation from the deepest layer to the shallower one and multi-level supervision to guide network training. Visualization analysis shows that by introducing SD-MS, the same-level layer in the network can obtain a clearer representation of fundamental frequency components, while the shallower layers can even learn more task-relevant semantic information. Ablation study results indicate that SD-MS applies to existing melody extraction models and can consistently improve performance. Experimental results show that our proposed method, MF-TFA with SD-MS, outperforms six compared state-of-the-art methods, achieving overall accuracy (OA) scores of 87.1%, 89.9%, and 76.6% on the ADC 2004, MIREX 05, and MEDLEY DB datasets, respectively. The main code will be available at https://github.com/SmoothJing/MF-TFA_SD-MS.

Fake news detection has received increasing attention from researchers in recent years, especially in the area of multimodal fake news detection involving both text and images. However, many previous studies have simply fed the semantic features of both text and image modalities into a binary classifier after applying basic concatenation or attention mechanisms, where these features often contain a significant amount of inherent noise. This, in turn, leads to both intra- and inter-modal uncertainty. In addition, while methods based on simple concatenation of the two modalities have achieved notable results, they often ignore the drawback of applying fixed weights across modalities, which causes some high-impact features to be ignored. To address these issues, we propose a novel semantic-level m ultimodal d ynamic f usion framework for f ake n ews d etection ( MDF-FND ). To the best of our knowledge, this is the first attempt to develop a dynamic fusion framework for semantic-level multimodal fake news detection. Specifically, our model consists of two main components: (1) the U ncertainty E stimation M odule ( UEM ), which is an uncertainty modeling module that uses a multi-head attention mechanism to model intra-modal uncertainty, and (2) the D ynamic F usion N etwork, which is based on Dempster–Shafer evidence theory ( DFN ) and is designed to dynamically integrate the weights of both text and image modalities. To further enhance the dynamic fusion framework, a graph attention network is employed for inter-modal uncertainty modeling before DFN. Extensive experiments have demonstrated the effectiveness of our model across three datasets, with a performance improvement of up to 4% on the Twitter dataset, achieving state-of-the-art performance. We also conducted a systematic ablation study to gain insights into our motivation and architectural design. Our model is publicly available at https://github.com/CoisiniStar/MDF-FND .

In the field of network security, anomaly traffic detection is a key technology for identifying network attacks. It detects abnormal behavior and counteracts it by monitoring changes in traffic patterns. Deep learning-based methods significantly improve detection performance due to their ability to efficiently learn and extract complex feature representations. However, these methods require large amounts of data for training, which exacerbates the risk of privacy breaches and increases training time consumption. This paper proposes an anomaly traffic detection method based on differential privacy and temporal convolutional networks, named DUDPA-TATD. DUDPA-TATD consists of two components: the Dynamic Update Strategy with Differential Privacy Protection Laplace Mechanism (DUDPA) and the Temporal Aggregation Traffic Detection network based on Temporal Convolutional Networks (TATD). DUDPA gradually adjusts the privacy protection strategy according to the inference rules of TATD, while TATD enhances the learning of macro and micro differences in time-series data by aggregating key features, further improving detection performance. We conducted experiments on two public datasets. Compared with baseline methods, extensive experiments on the DAPT2020 and SMAP datasets demonstrate that our DUDPA-TATD not only exhibits superior detection performance but also requires less average training time than most baseline methods, qualifying it as a lightweight detection model.

Event causality identification (ECI) aims to identify possible causal relationships between event-mention pairs in a text. In the past, ECI models mainly used classification frameworks and rarely used generative models to solve this task. Although some progress has been made, the existing approaches suffer from the following two problems: (1) In the generative approach of inter-event mention dependency paths, noise and unnecessary sentence components cannot be effectively reduced, thus limiting the ability of the model to capture the critical correlation knowledge between event mentions; and (2) Existing multi-task generative model training which uses the REINFORCE algorithm suffers from a high-variance problem that imposes limitations on capturing critical causal knowledge. Therefore, we propose a novel Structural Optimization strategy Reinforcement Learning algorithm Generation model, GenSORL. The model aims to generate causal relationships from input sentences and includes dependency path generation as a complementary task to improve the causal label prediction performance. Specifically, this approach utilizes a new dependency syntax strategy to optimize dependency-path generation and extract important ECI contextual words between event mentions. Regarding the high-variance problem, a policy gradient with baseline is proposed for training the generative model, further adopting an innovative reward function to measure the accuracy of causal prediction and generation quality. In experiments using two frequently used benchmark datasets, the proposed method outperformed state-of-the-art models.

Event Extraction (EE) is an essential task in natural language processing that aims to mine events occurring in event mentions represent events using event records, which usually consist of event types, trigger words, argument elements corresponding to roles in the event types. Recently, prompt-based generative models have been developed to extract events. However, these prompt-based generative studies have ignored the fact that the strong language comprehension capability of the pre-trained language model (PLM) can analyze extract the potential role relationships in multiple templates for more information that can help extract argument elements. To determine the extended templates that can help the model for event extraction, we propose the multiple template choice model (MTCM), which designs an extended event type mining module to automatically mine the extended event types in the event mention uses the templates corresponding to the extended event types to interact with the template, corresponding to the currently to-be-extracted event type of event mention, in a multi-template information interaction, which gives the model more information guides the PLM for event extraction. To validate our model, we used two widely used datasets in the event extraction domain, ACE2005-EN ERE-EN. The experimental results show that our model achieves state-of-the-art performance on the ACE2005-EN dataset significantly improves the ERE dataset. In addition, according to the results, our model can be effectively adapted to low-resource environments.

Face forgery detection has become a new research hotspot. Though existing detection works have achieved impressive performance, they are difficult to achieve a proper trade-off between detection accuracy and model complexity. To solve this problem, we design some low-complexity modules and construct a lightweight dynamic fusion network (LDFnet) to achieve high accuracy and lightweight face forgery detection. Firstly, we regard significant local visual artifacts as a correct semantic feature needed for detection. A spatial group-wise enhance (SGE) module is introduced as a supervision to suppress possible noise and capture local artifacts. Secondly, we design a manipulation trace extraction block (TraceBlock), which can replace vanilla convolution to achieve global inference, thus capturing the texture information in the global scope. Based on TraceBlock, we construct a global texture representation (GTR) network to extract global manipulation features hierarchically. Finally, we design a dynamic fusion mechanism (DFM) to fully fuse local and global clues, and dynamically generate a more discriminating feature representation. Extensive experimental results show that the proposed LDFnet is significantly superior to the previous detection works on some popular face forgery datasets, such as FF++, DFDC, CelebDF and HFF. In particular, LDFnet only uses 963k model parameters and 801M FLOPs, which is far lower than the calculation cost of face forgery detection based on large model, and achieves better detection results.

BACKGROUND: Long non-coding RNAs (lncRNAs) have been reported to have a crucial impact on the pathogenesis of acute myeloid leukemia (AML). Cuproptosis, a copper-triggered modality of mitochondrial cell death, might serve as a promising therapeutic target for cancer treatment and clinical outcome prediction. Nevertheless, the role of cuproptosis-related lncRNAs in AML is not fully understood. METHODS: The RNA sequencing data and demographic characteristics of AML patients were downloaded from The Cancer Genome Atlas database. Pearson correlation analysis, the least absolute shrinkage and selection operator algorithm, and univariable and multivariable Cox regression analyses were applied to identify the cuproptosis-related lncRNA signature and determine its feasibility for AML prognosis prediction. The performance of the proposed signature was evaluated via Kaplan-Meier survival analysis, receiver operating characteristic curves, and principal component analysis. Functional analysis was implemented to uncover the potential prognostic mechanisms. Additionally, quantitative real-time PCR (qRT-PCR) was employed to validate the expression of the prognostic lncRNAs in AML samples. RESULTS: A signature consisting of seven cuproptosis-related lncRNAs (namely NFE4, LINC00989, LINC02062, AC006460.2, AL353796.1, PSMB8-AS1, and AC000120.1) was proposed. Multivariable cox regression analysis revealed that the proposed signature was an independent prognostic factor for AML. Notably, the nomogram based on this signature showed excellent accuracy in predicting the 1-, 3-, and 5-year survival (area under curve = 0.846, 0.801, and 0.895, respectively). Functional analysis results suggested the existence of a significant association between the prognostic signature and immune-related pathways. The expression pattern of the lncRNAs was validated in AML samples. CONCLUSION: Collectively, we constructed a prediction model based on seven cuproptosis-related lncRNAs for AML prognosis. The obtained risk score may reveal the immunotherapy response in patients with this disease.

Abstract Most of the semantic segmentation real‐time networks improve the segmentation speed by reducing the spatial resolution, leading to the accuracy being significantly reduced as a result. To solve this problem, we propose feature enhancement module (FEM), feature extraction and fusion module (FEFM). By extracting and enhancing the future map before the image down‐sample on the backbone and fusing the low‐level features with rich details and the high‐level features with more semantic information. Based on the FEM and FEFM, we introduce a real‐time semantic segmentation network feature extraction and enhancement network. In the experiment, using Cityscapes and CamVid datasets, the proposed network achieves a balance between computing speed and accuracy. Without additional processing and pretraining, it achieves 75.47% Mean IoU on the Cityscapes test dataset with only 29.96G Flops and a speed of 94 frames per second on a single RTX 2080Ti card. Code is available at https://github.com/favoMJ/FEENet.

Target detection in unmanned aerial vehicle application scenarios has other problems, such as dense targets. The existing unmanned aerial vehicle target detection model with high computational complexity makes it difficult to meet real-time unmanned aerial vehicle target detection, and the detection accuracy of small targets is low. To address these problems, we propose an improved YOLOv7 small target detection model based on context and pyramidal attention that can cope with dense unmanned aerial vehicle scenarios - CPA-YOLOv7. This model embeds our proposed lightweight multi-scale attentional feature spatial pyramid pooling module, which can better distinguish between small and large target features, reducing the computational effort while improving the detection accuracy of the model. Secondly, we design a contextual dynamic fusion attention module in the network to fuse global and local contextual information and dynamically assign features to multiple groups of channels; in the multi-scale fusion process, it effectively increases the characterization ability of small target features and enables the network to better focus on small target information. Finally, we improve Wise-Intersection-over-Union loss as the regression loss function, add a moderation factor to retain some of the high and low-quality sample weights to improve the regression accuracy of high-quality anchor frames, and use the dynamic non-monotonic focusing mechanism to increase the model's focus on ordinary quality anchor frames to improve the model's localization performance and robustness to low-quality samples. Numerous experimental results show that on the unmanned aerial vehicle datasets VisDrone2021-DET and AI-TOD, the mAP values of our model are 2.3% and 1.1% higher than those of the YOLOv7 model with fewer parameters introduced, and the computational speed reaches 146 frames per second (FPS), which can meet the real-time requirements of unmanned aerial vehicle detection.

Due to their inherent characteristics, small objects have weaker feature representation after multiple down-sampling and are even annihilated in the background. FPN’s simple feature concatenation does not fully utilize multi-scale information and introduces irrelevant context into the information transfer, further reducing the detection performance of the small object. To address the above issues, we propose the simple but effective FE-YOLOv5. (1) We designed the feature enhancement module (FEM) to capture more discriminative features of the small object. Global attention and high-level global contextual information are used to guide shallow, high-resolution features. Global attention interacts with cross-dimensional feature interaction and reduces information loss. High-level context complements more detailed semantic information by modeling global relationships through non-local networks. (2) We design the spatially aware module (SAM) to filter spatial information and enhance the robustness of features. Deformable convolution performs sparse sampling and adaptive spatial learning to better focus on foreground objects. According to the experimental results, our proposed FE-YOLOv5 outperforms the other architectures in the VisDrone2019 dataset and Tsinghua-Tencent100K dataset. Compared to YOLOv5, the APS was improved by 2.8% and 2.9%, respectively.

Most person re-identification methods are researched under various assumptions. However, viewpoint variations or occlusions are often encountered in practical scenarios. These are prone to intra-class variance. In this paper, we propose a multiscale global-aware channel attention (MGCA) model to solve this problem. It imitates the process of human visual perception, which tends to observe things from coarse to fine. The core of our approach is a multiscale structure containing two key elements: the global-aware channel attention (GCA) module for capturing the global structural information and the adaptive selection feature fusion (ASFF) module for highlighting discriminative features. Moreover, we introduce a bidirectional guided pairwise metric triplet (BPM) loss to reduce the effect of outliers. Extensive experiments on Market-1501, DukeMTMC-reID, and MSMT17, and achieve the state-of-the-art results on mAP. Especially, our approach exceeds the current best method by 2.0% on the most challenging MSMT17 dataset.

There is a lack of robust generalizable predictive biomarkers of response to immune checkpoint blockade in multiple types of cancer. We develop hDirect-MAP, an algorithm that maps T cells into a shared high-dimensional (HD) expression space of diverse T cell functional signatures in which cells group by the common T cell phenotypes rather than dimensional reduced features or a distorted view of these features. Using projection-free single-cell modeling, hDirect-MAP first removed a large group of cells that did not contribute to response and then clearly distinguished T cells into response-specific subpopulations that were defined by critical T cell functional markers of strong differential expression patterns. We found that these grouped cells cannot be distinguished by dimensional-reduction algorithms but are blended by diluted expression patterns. Moreover, these identified response-specific T cell subpopulations enabled a generalizable prediction by their HD metrics. Tested using five single-cell RNA-seq or mass cytometry datasets from basal cell carcinoma, squamous cell carcinoma and melanoma, hDirect-MAP demonstrated common response-specific T cell phenotypes that defined a generalizable and accurate predictive biomarker.

Recently, the time-domain-based methods (i.e., the method of modeling the raw waveform directly) for audio source separation have shown tremendous potential. In this paper, we propose a model which combines the complexed spectrogram domain feature and time-domain feature by a cross-domain encoder (CDE) and adopts the hierarchic temporal convolutional network (HTCN) for multiple music sources separation. The CDE is designed to enable the network to code the interactive information of the time-domain and complexed spectrogram domain features. HTCN enables it to learn the long-time series dependence effectively. We also designed a feature calibration unit (FCU) to be applied in the HTCN and adopted the multi-stage training strategy during the training stage. The ablation study demonstrates the effectiveness of each designed component in the model. We conducted the experiments on the MUSDB18 dataset. The experimental results indicate that our proposed CDE-HTCN model outperforms the top-of-the-line methods and, compared with the state-of-the-art method, DEMUCS, achieves the improvement of the average SDR score of 0.61 dB. Significantly, the improvement of the SDR score for the$\ bass$source has a sizable margin of 0.91 dB.

There is an urgent public health need to better understand Severe Acute Respiratory Syndrome (SARS)-CoV-2/COVID-19, particularly how sequences of the viruses could lead to diverse incidence and mortality of COVID-19 in different countries. However, because of its unknown ancestors and hosts, elucidating the genetic variations of the novel coronavirus, SARS-CoV-2, has been difficult. Without needing to know ancestors, we identified an uneven distribution of local genome similarities among the viruses categorized by geographic regions, and it was strongly correlated with incidence and mortality. To ensure unbiased and origin-independent analyses, we used a pairwise comparison of local genome sequences of virus genomes by Basic Local Alignment Search Tool (BLAST). We found a strong statistical correlation between dominance of the SARS-CoV-2 in distributions of uneven similarities and the incidence and mortality of illness. Genomic annotation of the BLAST hits also showed that viruses from geographic regions with severe infections tended to have more dynamic genomic regions in the SARS-CoV-2 receptor-binding domain (RBD) and receptor-binding motif (RBM) of the spike protein (S protein). Dynamic domains in the S protein were also confirmed by a canyon region of mismatches coincident with RBM and RBD, without hits of alignments of 100% matching. Thus, our origin-independent analysis suggests that the dynamic and unstable SARS-CoV-2-RBD could be the main reason for diverse incidence and mortality of COVID-19 infection.