Cross-modal hashing has emerged as a pivotal solution for efficient retrieval across diverse modalities, such as images and texts, by mapping them into compact binary hash spaces. However, in real-world scenarios, the modalities data is often missing or misaligned. Existing methods are most rely on fully paired training data and ignore missing or misaligned modalities data, resulting in the semantic inconsistencies. To address these challenges, we propose an Adaptive Graph Attention-Based Discrete Hashing (AGADH) method, which consists of three parts. First, to solve the problem of missing modalities, AGADH employs a masked completion strategy to reconstruct missing modalities. Second, to mitigate semantic misalignment, AGADH leverages a Graph Attention Network (GAT) encoder-decoder architecture with alignment module to construct features from different modalities. Additionally, to enhance the fusion performance, an adaptive fusion module dynamically adjusting the contributions of image and text modalities with learnable weighting coefficients is proposed. Extensive experiments on three benchmark datasets, MS-COCO, NUS-WIDE, and MIRFlickr-25K, demonstrating that AGADH outperforms state-of-the-art methods in both fully paired and incompletely paired scenarios, showing its robustness and effectiveness in cross-modal retrieval tasks.

Generative recommendation as a new paradigm is influencing the current development of recommender systems. It aims to assign identifiers that capture richer semantic and collaborative information to items, and subsequently predict item identifiers via autoregressive generation using Large Language Models (LLMs). Existing approaches primarily tokenize item text into codebooks with preserved semantic IDs through RQ-VAE, or separately tokenize different modality features of items. However, existing tokenization methods face two major challenges: (1) Learning decoupled multi-modal features limits the quality of the semantic representation. (2) Ignoring collaborative signals from interaction history limits the comprehensiveness of identifiers. To address these limitations, we propose a multi-modal semantic-enhanced identifier with collaborative signals for generative recommendation, named MusicRec. In MusicRec, we propose a tokenization approach based on shared-specific modal fusion, enabling the generated identifiers to preserve semantic information more comprehensively from all modalities. In addition, we incorporate collaborative signals from user interactions to guide identifier generation, preserving collaborative patterns in the semantic representation space. Extensive experiments on three public datasets demonstrate that MusicRec achieves state-of-the-art performance compared to existing baseline methods.

Personality detection aims to deduce a user’s personality from their published posts. The goal of this task is to map posts to specific personality types. Existing methods encode post information to obtain user vectors, which are then mapped to personality labels. However, existing methods face two main issues: first, only using small models makes it hard to accurately extract semantic features from multiple long documents. Second, the relationship between user vectors and personality labels is not fully considered. To address the issue of poor user representation, we utilize the text embedding capabilities of LLM. To solve the problem of insufficient consideration of the relationship between user vectors and personality labels, we leverage the text generation capabilities of LLM. Therefore, we propose the LLM-Enhanced Text Mapping Model (ETM) for Personality Detection. The model applies LLM’s text embedding capability to enhance user vector representations. Additionally, it uses LLM’s text generation capability to create multi-perspective interpretations of the labels, which are then used within a contrastive learning framework to strengthen the mapping of these vectors to personality labels. Experimental results show that our model achieves state-of-the-art performance on benchmark datasets.

Adding imperceptible watermarks to artwork images, such as paintings and photographs, can effectively safeguard the copyright of these images without compromising their usability. However, existing blind watermarking techniques encounter two major challenges in addressing this task: imperceptibility and robustness, particularly when subjected to various noise attacks. In this paper, we propose a blind watermarking method for artwork image copyright protection, IWRN, which can ensure both the Imperceptibility of the Watermark and Robustness against Noise attacks. For imperceptibility, we design a Learnable Wavelet Network (LWN) to adaptively embed the watermark into the high-frequency region where the watermark has better invisibility. For robustness, we establish a Deform-Attention based Invertible Neural Network (DA-INN) with a decoding optimization, which offers the advantage of computational reversion, and combines the deform-attention mechanism and decoding optimization to enhance the model's resistance against noises. Additionally, we design a Joint Contrast Learning (JCL) mechanism to improve imperceptibility and robustness simultaneously. Experiments show that our IWRN outperforms other state-of-the-art blind watermarking methods, achieves an average performance of 41.55 PSNR and 99.57% accuracy on the Coco2017, Wikiart, and Div2k datasets when facing 12 kinds of noise attacks.

The inherent constraint of the "human-in-the-loop" sensing mechanism, imposes mobile crowdsensing with high dynamics and uncertainty, ultimately leading to the issue of incomplete data collection. Current data inference solutions in mobile crowdsensing can be broadly categorized as low-rank models and deep learning models. Low-rank models apply structural prior for data inference, but have limited model capacity, while deep learning models possess salient feature expressivity, but are prone to overfitting in sparse crowdsensing scenarios. In this paper, we try to absorb the strengths of both two paradigms, and propose a structural prior guided Transformer, StrucFormer, for crowd-sensing data inference. Specifically, we exploit structural prior of low-rankness to power canonical Transformer from the aspects of input embedding, attention forming and model regularization, which enables the model to precisely capture the spatiotemporal and multi-type data correlations for accurate inference with only sparse observations. Extensive empirical results demonstrate the superiority of StrucFormer in terms of accuracy and generality in heterogeneous urban sensing tasks. The code is available at: https://github.com/CUPK-K/StrucFormer.

Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose CFPT, a novel method that empowering time series forecasting through Cross-Frequency Interaction (CFI) and Periodic-Aware Timestamp Modeling (PTM). To learn cross-frequency interactions, we design the CFI branch to process signals in frequency domain and captures their interactions through a feature fusion mechanism. Furthermore, to enhance prediction performance by leveraging timestamp periodicity, we develop the PTM branch which transforms timestamp sequences into 2D periodic tensors and utilizes 2D convolution to capture both intra-period dependencies and inter-period correlations of time series based on timestamp patterns. Extensive experiments on multiple real-world benchmarks demonstrate that CFPT achieves state-of-the-art performance in long-term forecasting tasks. The code is publicly available at this repository: https://github.com/BUPT-SN/CFPT.

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have demonstrated significant potential in automated fact-checking. However, existing methods face limitations in insufficient evidence utilization and lack of explicit verification criteria. Specifically, these approaches aggregate evidence for collective reasoning without independently analyzing each piece, hindering their ability to leverage the available information thoroughly. Additionally, they rely on simple prompts or few-shot learning for verification, which makes truthfulness judgments less reliable, especially for complex claims. To address these limitations, we propose a novel method to enhance evidence utilization and introduce explicit verification criteria, named EVICheck. Our approach independently reasons each evidence piece and synthesizes the results to enable more thorough exploration and enhance interpretability. Additionally, by incorporating fine-grained truthfulness criteria, we make the model's verification process more structured and reliable, especially when handling complex claims. Experimental results on the public RAWFC dataset demonstrate that EVICheck achieves state-of-the-art performance across all evaluation metrics. Our method demonstrates strong potential in fake news verification, significantly improving the accuracy.

The advancements in generative models and the real-world attack of machine-generated text(MGT) create a demand for more robust detection methods. The existing MGT detection methods for adversarial environments primarily consist of manually designed statistical-based methods and fine-tuned classifier-based approaches. Statistical-based methods extract intrinsic features but suffer from rigid decision boundaries vulnerable to adaptive attacks, while fine-tuned classifiers achieve outstanding performance at the cost of overfitting to superficial textual feature. We argue that the key to detection in current adversarial environments lies in how to extract intrinsic invariant features and ensure that the classifier possesses dynamic adaptability. In that case, we propose OSTAR, a novel MGT detection framework designed for adversarial environments which composed of a statistical enhanced classifier and a Multi-Faceted Contrastive Learning(MFCL). In the classifier aspect, our Multi-Dimensional Statistical Profiling (MDSP) module extracts intrinsic difference between human and machine texts, complementing classifiers with useful stable features. In the model optimization aspect, the MFCL strategy enhances robustness by contrasting feature variations before and after text attacks, jointly optimizing statistical feature mapping and baseline pre-trained models. Experimental results on three public datasets under various adversarial scenarios demonstrate that our framework outperforms existing MGT detection methods, achieving state-of-the-art performance and robust against attacks.The code is available at https://github.com/BUPT-SN/OSTAR.

The demand for multimodal data processing drives the development of information technology. Cross-modal hash retrieval has attracted much attention because it can overcome modal differences and achieve efficient retrieval, and has shown great application potential in many practical scenarios. Existing cross-modal hashing methods have difficulties in fully capturing the semantic information of different modal data, which leads to a significant semantic gap between modalities. Moreover, these methods often ignore the importance differences of channels, and due to the limitation of a single goal, the matching effect between hash codes is also affected to a certain extent, thus facing many challenges. To address these issues, we propose a Dynamic Masking and Auxiliary Hash Learning (AHLR) method for enhanced cross-modal retrieval. By jointly leveraging the dynamic masking and auxiliary hash learning mechanisms, our approach effectively resolves the problems of channel information imbalance and insufficient key information capture, thereby significantly improving the retrieval accuracy. Specifically, we introduce a dynamic masking mechanism that automatically screens and weights the key information in images and texts during the training process, enhancing the accuracy of feature matching. We further construct an auxiliary hash layer to adaptively balance the weights of features across each channel, compensating for the deficiencies of traditional methods in key information capture and channel processing. In addition, we design a contrastive loss function to optimize the generation of hash codes and enhance their discriminative power, further improving the performance of cross-modal retrieval. Comprehensive experimental results on NUS-WIDE, MIRFlickr-25K and MS-COCO benchmark datasets show that the proposed AHLR algorithm outperforms several existing algorithms.

The Low Earth Orbit (LEO) constellation has great potential for global coverage and high-capacity transmission. However, poor reliability and high energy consumption can severely affect the routing transfer performance. In this paper, a multi-path adaptive energy-efficient routing scheduling scheme for LEO constellations is designed. A static weight multi-path (SWM) routing scheme is proposed initially, extending single-path routing to multi-path routing to simulate route scheduling in large-scale constellations accurately. To further address the limitations of static weight allocation in adapting to dynamic network changes, a particle swarm optimization-based dynamic weight multi-path (PSODWM) routing scheme is proposed, considering transmission delay, energy consumption, capacity, and packet loss rate, thereby achieving an optimal multi-path load distribution without additional resource consumption. Finally, leveraging the neural population dynamics optimization algorithm (NPDOA) and digital twin technology, the multi-path adaptive energy-efficient (MPAEE) scheme is developed, providing real-time feedback for path selection and optimizing system performance. Simulation results demonstrate that the MPAEE scheme significantly reduces propagation delay, packet loss, hop count, and interruption probability while improving satellite energy efficiency and extending satellite lifetime.

Drones are sophisticated machines that can hover over extreme locations, conduct aerial surveillance, collect surveillance data, and disseminate it to the distributed edge for processing and analysis. The distributed edge deploys advanced artificial intelligence (AI) models to detect any unwarranted activity or object based on surveillance data. However, these lightweight and low-power unmanned aerial vehicles (UAVs) may experience faults due to unprecedented workload when deployed in extreme surveillance domains. In this article, we have designed an AI framework to detect any safety concerns with drones deployed for aerial surveillance in extreme locations based on real-time drone critical parameters. We also propose a MapReduce-based object recognition and classification module to process large-scale images captured by drones efficiently. However, conventional AI systems behave like black box systems, leading to a lack of trust and transparency. Thus, we convert the traditional framework of AI into an explainable edge AI framework using Shapley additive explanations (SHAPs) that opens Pandora’s black box. The experimental results show the effectiveness of the proposed framework in detecting drone safety concerns through explainable health status tracking alongside ensuring an effective object detection mechanism.

Cross-modal retrieval is crucial for achieving accurate and efficient information retrieval by establishing semantic correlations between heterogeneous images and text. However, traditional image-text training sets suffer from information asymmetry, which includes short lengths and limited sentence structures. This phenomenon often results in insufficient representations of essential visual information. We introduce RichDataset, which offers extensive semantic information. It includes diverse real-life image-text pairs and AI-generated content across domains such as news, entertainment, education, and posters. Compared with classic benchmarks such as Flickr30k and MS-COCO, RichDataset exhibits a novel and balanced distribution. Existing cross-modal retrieval models face challenges in extracting distinct features from the emerging data, leading to low retrieval accuracy. We propose SGG-MVAR, a comprehensive retrieval model guided by multiview scene information and semantic relationships. Leveraging a scene knowledge database, our model parses scene graphs and identifies differences in attributes and relationships. We conduct extensive experiments to evaluate our proposed dataset and model. All experimental results consistently demonstrate a significant improvement in recall for cross-modal retrieval.

With the popularization of social networks, fake news is also widely and rapidly spreading, which poses a great threat to the Internet. Therefore, how to detect fake news automatically and efficiently has become an urgent problem to be solved. However, the existing approaches mostly focus on the explicit features (images and text) and deep fusions, without considering potential features such as text emotion and image category. To find a solution to this issue, we propose a Potential Features Fusion Network (PFFN), which models the explicit and potential features at the same time. To exploit the potential image features, we introduce a mixture of experts structure to process the news image separately, which can best use the relationships between the news image category and fake news detection. Besides, we also extract emotion features as potential text features and fuse them with explicit text features. Finally, we establish an attention-based feature fusion network to fuse the potential features with the explicit features, which can obtain a multimodal fusion feature of a piece of news and thus further improve the performance. We make experiments on four public datasets (Weibo16, Weibo19, Twitter, and PolitiFact); the results compared with the baseline approaches demonstrate that our PFFN has a better performance. Our code is available at https://github.com/Wang-bupt/PFFN

Knowledge Graphs (KGs) serve as valuable auxiliary information to improve the accuracy of recommendation systems. Previous methods have leveraged the knowledge graph to enhance item representation and thus achieve excellent performance. However, these approaches heavily rely on high-quality knowledge graphs and learn enhanced representations with the assistance of carefully designed triplets. Furthermore, the emergence of knowledge graphs has led to models that ignore the inherent relationships between items and entities. To address these challenges, we propose a Self-Derived Knowledge Graph Contrastive Learning framework (CL-SDKG) to enhance recommendation systems. Specifically, we employ the variational graph reconstruction technique to estimate the Gaussian distribution of user-item nodes corresponding to the graph neural network aggregation layer. This process generates multiple KGs, referred to as self-derived KGs. The self-derived KG acquires more robust perceptual representations through the consistency of the estimated structure. Besides, the self-derived KG allows models to focus on user-item interactions and reduce the negative impact of miscellaneous dependencies introduced by conventional KGs. Finally, we apply contrastive learning to the self-derived KG to further improve the robustness of CL-SDKG through the traditional KG contrast-enhanced process. We conducted comprehensive experiments on three public datasets, and the results demonstrate that our CL-SDKG outperforms state-of-the-art baselines.

Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and semantic associations, which greatly restricts their performance and applicability in practical applications. To deal with this challenge, in this paper, we propose an end-to-end graph attention network hashing (EGATH) for cross-modal retrieval, which can not only capture direct semantic associations between images and texts but also match semantic content between different modalities. We adopt the contrastive language image pretraining (CLIP) combined with the Transformer to improve understanding and generalization ability in semantic consistency across different data modalities. The classifier based on graph attention network is applied to obtain predicted labels to enhance cross-modal feature representation. We construct hash codes using an optimization strategy and loss function to preserve the semantic information and compactness of the hash code. Comprehensive experiments on the NUS-WIDE, MIRFlickr25K, and MS-COCO benchmark datasets show that our EGATH significantly outperforms against several state-of-the-art methods.

Location factor of recommender systems has been extensively studied in the past decade. However, there is no research thoroughly analyzing location’s role in news recommendation. In this paper, a comprehensive exploration on role of location in news recommendation is presented. First of all, based on analysis of real news datasets, we find that news recommendation differs from spatial item recommendation. Location affects news consumption behaviors of users with two-fold aspects including geographic feature and semantic feature. Regarding geographic feature, location influences news recommendation according to region rather than latitude-longitude level. Furthermore, interesting news topics are also impacted by semantic feature of location. Semantic feature may play a more positive role than geographic feature. The novel findings consistently manifest that, as non-spatial items, news differ from spatial items in that location influences users' selection in terms of different pattern and degree. In summary, geographic and semantic features influence reading preference through mapping locations into special topics. Changing of location topics leads to varying of reading preference. The news datasets in this paper belong to check in data. NewsREEL dataset is from a company, and it is provided by German researcher. The location data in Twitter dataset is also check in data. NetEase news dataset are collected from NetEase news websites, and the type of location data is city or region.

Machine Learning technologies have obtained breakthrough in various fields, and medical information extraction has also successfully made great progress through deep learning methods. However, entity relationship overlap is a key issue and challenge in the field of medical entity relationship extraction. Hence, we propose an intelligent extraction method for Chinese medicine entity relationship through improving graph neural network and structure optimization strategy. We optimize model structure and introduce global pointer network. The sentence feature information is captured by attention mechanism and Bi-LSTM. Grammatical relations between entities are parsed using GCN layer. Finally, multiple decoders are used for joint extraction of entity relations through the global pointer network. The model learns the graph structure data by GCN, while the challenge of entity relationship overlap is solved through using the pointer network. The experiments demonstrate that the model achieves 83.77% in terms of F1 value, which is better than other baseline models.

The rapid development of the social network has brought great convenience to people's lives. A large amount of cross-media big data, such as text, image, and video data, has been accumulated. A cross-media search can facilitate a quick query of information so that users can obtain helpful content for social networks. However, cross-media data suffer from semantic gaps and sparsity in social networks, which bring challenges to cross-media searches. To alleviate the semantic gaps and sparsity, we propose a cross-media search method based on complementary attention and generative adversarial networks (CAGS). To obtain high-quality feature representations, we build a complementary attention mechanism containing the focused and unfocused features of images to realize the consistent association of cross-media data in social networks. By designing the cross-media adversarial learning process, we can obtain a common semantic representation of cross-media data and further alleviate the semantic gap and sparsity issues for social networks. Finally, we perform a similarity calculation to realize an accurate cross-media search. We construct four search tasks utilizing two standard cross-media data sets to verify the search performance of the proposed CAGS.

Predicting the development trend of future scientific research not only provides a reference for researchers to understand the development of the discipline, but also provides support for decision-making and fund allocation for decision-makers. The continuous growth of scientific publications has brought challenges to track the development trends of scientific research topics. The existing topic trend prediction methods have proved that the research topic trend of a publication is influenced by other peer publications. However, they ignore the fact that the research topics of different publications belong to different research topic space. Moreover, the existing topic prediction methods do not fully consider the interactive influence among publications that the research topic of one publication affects the topics of other publications, it is also influenced by the research topics of other publications. In line with this, this paper proposes a scientific research topic trend prediction model based on multi-long short-term memory (multi-LSTM) and Graph Convolutional Network. Specifically, multiple LSTMs are employed to map research topics of different publications into their respective topic space. Then, the graph convolutional neural network is applied to learn the scientific influence context of each publication, so that the research topic of each publication not only integrates the influence of neighbor nodes, but also considers the influence of the neighbors of the neighbor node on the research topic of the publication, so as to more accurately fuse scientific influence context of research topic of peer publications. Experiments results on the data set of scientific research papers in the field of artificial intelligence and data mining demonstrate that the model improves the prediction precision and achieves the state-of-the-art research topic trend prediction effect compared with the other baseline models.

String matching is a basic problem of string operation, and privacy-preserving string matching, as a special case of secure multi-party computation, has broad applications in auction, bidding and some other commercial areas. In this paper, some protocols are proposed to solve this private matching problem, the security and correctness are analyzed respectively, and the actual efficiency is tested by experiment. A protocol is also designed based on the BMH algorithm which is more efficient and conceals more private information.