Article
Computer Science, Information Systems
Yue Fu, Xinyi Yu, Yongliang Wu, Xueyi Ding, Shuliang Zhao
Summary: The aim of heterogeneous attributed network embedding is to map the network into low-dimensional representations while preserving topological structure and attributed content. However, when the content similarity of closely related nodes is low, the embedding vectors obtained by combining network structure and content information are poor. To address this issue, we propose a robust model called HANE-DS, which embeds the heterogeneous attributed network into dual spaces.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Hao Wei, Gang Xiong, Qiang Wei, Weiquan Cao, Xin Li
Summary: Network embedding in heterogeneous network has attracted much attention due to its effectiveness in capturing network structure and properties. Existing models mainly focus on node proximity, but they fail to consider the different types of nodes and edges in heterogeneous network. We propose a novel structure-aware Attributed Heterogeneous Network Embedding model (SAHNE), which takes into consideration the community and organization structure in heterogeneous network. We conduct extensive experiments on three real-world networks and demonstrate that SAHNE outperforms state-of-the-art methods in various data mining tasks.
KNOWLEDGE AND INFORMATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhisheng Yang, Jinyong Cheng
Summary: This paper introduces a framework that combines attributed multiplex heterogeneous networks with an attention mechanism, using the softsign function characteristics to address deficiencies in processing large network models and improve recommendation accuracy.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
David McDonald, Shan He
Summary: Network embedding, specifically in hierarchical, directed networks with attributes, is a challenging problem in machine learning. The emerging approach of embedding complex networks into hyperbolic space can better represent the hierarchical structure of real-world systems. However, existing hyperbolic embedding approaches are not suitable for embedding attributed directed networks to an arbitrary dimension. To address this, we introduce HEADNet, an algorithm that extends previous works to embed directed attributed networks to Gaussian distributions in hyperbolic space of any dimension. Experimental results show that HEADNet performs well on predicting directed links for new nodes, providing an inductive hyperbolic embedding method for directed attributed networks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Jieyi Yang, Feng Zhu, Yihong Dong, Jiangbo Qian
Summary: In the real world, networks are complex with various types of nodes and edges, forming a heterogeneous network. Existing attribution network embedding algorithms fail to capture the impact of multimodal attributes on the topology effectively. To address this issue, a proposed algorithm called FHIANE utilizes deep heterogeneous convolutional networks to extract features from multimodal information and projects them into a consistent semantic space while preserving structural information. The FHIANE algorithm outperforms other baselines in tasks such as link prediction and node classification.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jiaxuan Liang, Jun Wang, Guoxian Yu, Wei Guo, Carlotta Domeniconi, Maozu Guo
Summary: This paper proposes a method called HetDAG to learn causal relationships between nodes in heterogeneous networks. By embedding node attributes and using prior network structure to update node representations, and then using attention mechanism for DAG learning, HetDAG is able to learn DAG efficiently and performs well in experiments.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Information Systems
Zhongying Zhao, Hui Zhou, Chao Li, Jie Tang, Qingtian Zeng
Summary: DeepEmLAN is a deep model-based embedding learning method for attributed networks, which smoothly projects different types of attributes into the same semantic space through a deep attention model while maintaining topological structures. Experimental results demonstrate that DeepEmLAN outperforms competitive state-of-the-art methods in tasks such as node classification and network reconstruction.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Jun Zhao, Xudong Liu, Qiben Yan, Bo Li, Minglai Shao, Hao Peng, Lichao Sun
Summary: Predicting cyber attack preference of intruders is essential for security organizations to proactively handle cyber threats, and this paper proposes a novel framework, HinAp, using attributed heterogeneous attention network and transductive learning to achieve this goal. By constructing an attributed heterogeneous information network and attack preference prediction model based on attention mechanism and transductive learning, the automated model for predicting cyber attack preferences outperforms existing methods in capturing attackers' preferences effectively.
COMPUTERS & SECURITY
(2021)
Article
Computer Science, Information Systems
Haodong Zou, Zhen Duan, Xinru Guo, Shu Zhao, Jie Chen, Yanping Zhang, Jie Tang
Summary: SANE extracts node sequence, attribute sequence, and label sequence in attributed networks, providing different insights into networks. By extracting bidirectional features from attribute sequence and using them to decode node and label sequences, SANE can scale to large networks and alleviate over-smoothing caused by attribute-only aggregation.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yu Ding, Hao Wei, Guyu Hu, Zhisong Pan, Shuaihui Wang
Summary: In this paper, a novel model is proposed to jointly solve the network embedding and community detection problems, utilizing network local information, global information, and node attributes collaboratively. Empirical findings demonstrate that by tackling these two issues together, the model significantly enhances community detection capabilities, as well as learns better network embedding compared to existing baseline methods. The proposed model is evaluated on various datasets, with experimental results showcasing its effectiveness and advancement.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Lin Shu, Chuan Chen, Xingxing Xing, Xiangke Liao, Zibin Zheng
Summary: The AHNA method is proposed for generating high-quality node representations on attributed heterogeneous networks by adaptively fusing topological structures and node attributes. It outperforms state-of-the-art approaches in link prediction, community detection, and node classification tasks by accurately balancing the importance of attributes and structures.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Xin Sun, Yongbo Yu, Yao Liang, Junyu Dong, Claudia Plant, Christian Bohm
Summary: The paper proposes the FATNet algorithm, which aims to integrate global topology and attribute relations into network embedding. By using non-local attribute relations and attribute smoothing filter, it complements the structure and attribute, achieving superior performance in various downstream tasks according to experiments.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Longcan Wu, Daling Wang, Kaisong Song, Shi Feng, Yifei Zhang, Ge Yu
Summary: The text introduces the importance of graph embedding in network data analysis and the proposed Dual-view HyperGraph Neural Network (DHGNN) model for attributed graph learning. The model unifies the expression form of different information sources, constructs dual hypergraphs, and utilizes the attention mechanism to achieve more effective graph embedding. Extensive experiments demonstrate that the performance of DHGNN surpasses state-of-the-art graph embedding methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Shaowei Tang, Zaiqiao Meng, Shangsong Liang
Summary: In this article, the authors propose a dynamic co-embedding model for temporal attributed networks (DCTANs) based on the dynamic stochastic state-space framework. The model captures the dynamics of a temporal attributed network and learns dynamic embeddings for both nodes and attributes while preserving the affinities between them.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Piotr Bielak, Tomasz Kajdanowicz, Nitesh Chawla
Summary: Representation learning has proposed a novel unsupervised method called AttrE2Vec to learn low-dimensional vector representations for edges in attributed networks. The experimental results demonstrate that the proposed method builds more powerful edge vector representations compared to contemporary approaches, reflected by higher quality measures in downstream tasks.
INFORMATION SCIENCES
(2022)
Article
Automation & Control Systems
Jun Liu, Hang Song, Huiwen Sun, Hongyan Zhao
Summary: This article proposes a high-precision machine learning-based PQD identification model, which combines the advantages of the modified fast independent component analysis method and the improved random forest classifier, improving the accuracy and feasibility of PQD identification. By establishing ten types of PQD models, denoising, feature extraction, and model construction steps, efficient identification of PQD under strong noise environment is achieved.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Yanxiang Ling, Fei Cai, Xuejun Hu, Jun Liu, Wanyu Chen, Honghui Chen
Summary: In this study, a context-controlled topic-aware neural response generation model is proposed to balance response informativeness and coherence by integrating dialog context with topic representation, and a topic transition strategy is introduced to generate relevant transition words.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Cell Biology
Lei Lei, Xiaofeng Yang, Yanhong Su, Huiqiang Zheng, Jun Liu, Haiyan Liu, Yujing Zou, Anjun Jiao, Xin Wang, Cangang Zhang, Xingzhe Zhang, Jiahui Zhang, Dan Zhang, Xiaobo Zhou, Lin Shi, Enqi Liu, Liang Bai, Chenming Sun, Baojun Zhang
Summary: Med1 plays an important role in maintaining CD8(+) T cells through IL-7R alpha/STAT5 pathway-mediated cell survival. Med1 deficiency leads to increased cell death, decreased expression of IL-7R alpha, and down-regulation of pSTAT5 in CD8(+) T cells.
JOURNAL OF CELLULAR AND MOLECULAR MEDICINE
(2021)
Article
Thermodynamics
Xiaojun Xue, Jiarui Li, Jun Liu, Yunyun Wu, Heng Chen, Gang Xu, Tong Liu
Summary: This study presents a novel design to enhance the energy efficiency of the compressed air energy storage (CAES) system by integrating it with a biomass integrated gasification combined cycle (BIGCC) system. The heat from compressed air cooling is recycled during the charging process, and the compressed air is directed to the BIGCC system for combustion, resulting in improved energy efficiency. Various analyses were conducted to evaluate the performance of the integrated system, showing significant improvements in round-trip efficiency and overall system efficiency.
Review
Biochemistry & Molecular Biology
Jun Liu, Hui Zhang, Yanhong Su, Baojun Zhang
Summary: Dysregulation of auto-reactive T cells and autoantibody-producing B cells, as well as excessive inflammation, contribute to the development of autoimmune diseases. Pattern recognition receptors (PRRs) play a significant role in autoimmune diseases and targeting these receptors may be a viable therapeutic strategy. This review summarizes the advancements in PRRs signaling pathways, their association with autoimmune diseases, and the application of inhibitors targeting PRRs.
CELL AND BIOSCIENCE
(2022)
Article
Thermodynamics
Xinglei Liu, Jun Liu, Kezheng Ren, Xiaoming Liu, Jiacheng Liu
Summary: In this paper, an effective index system and evaluation method are proposed to reliably assess the multi-energy transaction performance of the energy internet market. By combining fuzzy decision-making, structural modeling, and credibility analysis, a 14-indicator index system is extracted and a non-deterministic method is developed to handle the vagueness and uncertainty in expert judgement.
Article
Computer Science, Artificial Intelligence
Qika Lin, Rui Mao, Jun Liu, Fangzhi Xu, Erik Cambria
Summary: Knowledge graph completion (KGC) is crucial for many downstream applications. Existing language model-based methods for KGC often overlook the importance of modeling the deeper semantic information, such as topology contexts and logical rules. In this paper, we propose a unified framework FTL-LM that effectively incorporates topology contexts and logical rules in language models, and experimental results demonstrate its superiority over the state-of-the-art methods.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Jie Ma, Jun Liu, Yaxian Wang, Junjun Li, Tongliang Liu
Summary: In this study, a relation-aware fine-grained reasoning network is proposed to address the diagram reasoning problem in textbook question answering (TQA) tasks. By utilizing semantic dependencies and relative positions between nodes in diagrams, the network is able to extract and reason over the node information of question diagrams, achieving the best performance on the TQA dataset.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Energy & Fuels
Kezheng Ren, Jun Liu, Xinglei Liu, Yongxin Nie
Summary: Due to its efficiency and environmental friendliness, gas-fired units (GFU) are playing an increasingly important role in both electric power systems and natural gas systems. This study proposes a bi-level strategic bidding model that considers price and quantity factors to investigate GFU's performance in integrated electricity and natural gas markets. The model incorporates demand response management and user comfort level considerations. A modified reinforcement learning-based method, combining the deep deterministic policy gradient algorithm with autocorrelated noise, is proposed to solve the model. Test results on an integrated electricity-gas system show that the proposed method effectively reflects GFU's strategic behaviors and outperforms traditional algorithms.
Article
Computer Science, Artificial Intelligence
Jie Ma, Jun Liu, Qika Lin, Bei Wu, Yaxian Wang, Yang You
Summary: Visual question answering (VQA) is a task where machines are required to provide accurate natural language answers based on given images and questions. However, current VQA methods often heavily rely on surface correlation and statistical bias in the training data, lacking sufficient image grounding. To tackle this problem, researchers have proposed a novel end-to-end architecture that adopts multitask learning to enhance image grounding and learn effective multimodality representations. Experimental results show that the model achieves state-of-the-art performance on various datasets without additional data.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yanxiang Ling, Fei Cai, Jun Liu, Honghui Chen, Maarten de Rijke
Summary: Hierarchical context modeling is crucial for the response generation in multi-turn conversational systems. We propose a model named KS-CQ, which utilizes the Keep and Select modules to generate neighbor-aware context representation and context-enriched query representation. Extensive experiments demonstrate the effectiveness of our approach compared to state-of-the-art baselines in both automatic and human evaluations.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Energy & Fuels
Kezheng Ren, Jun Liu, Zeyang Wu, Xinglei Liu, Yongxin Nie, Haitao Xu
Summary: This paper presents a novel data-driven deep reinforcement learning-based optimization framework for home energy management systems (HEMS) considering uncertain household parameters. By utilizing a thermal comfort evaluation model and a bidirectional gated recurrent unit neural network (BiGRU-NN) prediction model, an optimal decision-making method is established. The experimental results demonstrate that this method can effectively reduce household electricity costs and total costs.
Article
Computer Science, Artificial Intelligence
Jie Ma, Qi Chai, Jingyue Huang, Jun Liu, Yang You, Qinghua Zheng
Summary: This paper proposes a weakly supervised learning method for textbook question answering, which learns deep text understanding and excellent diagram semantics through text matching and relation detection tasks. Experimental results demonstrate significant improvements in performance.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Proceedings Paper
Computer Science, Information Systems
Dandan Hong, Zhan Gao, Junfeng Luo, Jun Liu, Mo Xu, Zhihai Suo, Xiangting Ji
Summary: By analyzing student comments in the teaching evaluation system using Baidu AI technology, this method helps teaching management departments understand students' emotional inclinations towards each course, accurately grasp trends and distributions of teaching quality, and provide decision-making references for teaching management departments and teachers.
2020 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE COMMUNICATION AND NETWORK SECURITY (CSCNS2020)
(2021)
Proceedings Paper
Computer Science, Information Systems
Zhan Gao, Zhihai Suo, Jun Liu, Mo Xu, Dandan Hong, Hua Wen, Xiangting Ji
Summary: The paper discusses the importance of student evaluation in monitoring teaching quality and improving teachers' teaching level. By constructing a multi-level student evaluation system and developing an online evaluation system, it establishes an Internet plus evaluation model to improve efficiency and enthusiasm. Additionally, utilizing AI platform analysis of student comments provides data support for enhancing learning levels and optimizing teaching evaluation.
2020 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE COMMUNICATION AND NETWORK SECURITY (CSCNS2020)
(2021)
Article
Computer Science, Artificial Intelligence
C. Lopez-Molina, S. Iglesias-Rey, B. De Baets
Summary: Quantitative image comparison is a critical topic in image processing literature, with diverse applications. Existing measures of comparison often overlook the context in which the comparison takes place. This paper presents a context-aware comparison method for binary images, tested on the BSDS500 benchmark.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Lorenz Linhardt, Klaus-Robert Mueller, Gregoire Montavon
Summary: This paper investigates the issue of mismatches between the decision strategy of the explainable model and the user's domain knowledge, and proposes a new method EGEM to mitigate hidden flaws in the model. Experimental results demonstrate that the approach can significantly reduce reliance on Clever Hans strategies and improve the accuracy of the model on new data.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Zhimin Shao, Weibei Dou, Yu Pan
Summary: This paper proposes a novel algorithm, Dual-level Deep Evidential Fusion (DDEF), to integrate multimodal information at both the BBA level and multimodal level, aiming to enhance accuracy, robustness, and reliability. The DDEF approach utilizes the Dirichlet framework and BBA methods for effective uncertainty estimation and employs the Dempster-Shafer Theory for dual-level fusion. The experimental results show that the proposed DDEF outperforms existing methods in synthetic digit classification and real-world medical prognosis after BCI treatment.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Abhishek K. Ghosh, Danilo S. Catelli, Samuel Wilson, Niamh C. Nowlan, Ravi Vaidyanathan
Summary: The inability of current FM monitoring methods to be used outside clinical environments has made it challenging to understand the nature and evolution of FM. This investigation introduces a novel wearable FM monitor with a heterogeneous sensor suite and a data fusion architecture to efficiently capture and separate FM from interfering artifacts. The performance of the device and architecture were validated through at-home use, demonstrating high accuracy in detecting and recognizing FM events. This research is a major milestone in the development of low-cost wearable FM monitors for pervasive monitoring of FM in unsupervised environments.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jianlei Kong, Xiaomeng Fan, Min Zuo, Muhammet Deveci, Xuebo Jin, Kaiyang Zhong
Summary: In this study, we propose an intelligent traffic flow prediction framework based on the adaptive dual-graphic transformer with a cross-fusion strategy, aiming to uncover latent graphic feature representations that transcend temporal and spatial limitations. By establishing a traffic spatiotemporal prediction model using a cross-fusion attention mechanism, our proposed model achieves superior prediction performance on practical urban traffic flow datasets, particularly for long-term predictions.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huilai Zhi, Jinhai Li
Summary: This article addresses the issue that conflict analysis based on single-valued information systems is no longer valid. It proposes a conflict analysis method based on component similarity, which uses three-way n-valued concept lattices to handle set-valued formal contexts and realizes fast conflict analysis from an information fusion viewpoint. Experimental results verify the effectiveness of this method in reducing time consumption.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huchang Liao, Jiaxin Qi, Jiawei Zhang, Chonghui Zhang, Fan Liu, Weiping Ding
Summary: In this paper, a hospital selection approach based on a fuzzy multi-criterion decision-making method is proposed. This approach considers sentiment evaluation values of unstructured data from online reviews and structured data of public indexes simultaneously. The methodology involves collecting and processing online reviews, classifying topics and sentiments, quantifying sentiment analysis results using fuzzy numbers, and obtaining final preference scores of hospitals based on patients' preferences. A case study and robustness analysis are conducted to validate the effectiveness of the method.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Faramarz Farhangian, Rafael M. O. Cruz, George D. C. Cavalcanti
Summary: The proliferation of social networks has posed challenges in combating fake news, but automatic fake news detection using artificial intelligence has become more feasible. This paper revisits the definitions and perspectives of fake news and proposes an updated taxonomy, based on multiple criteria, for the field. The study finds that optimal feature extraction techniques vary depending on the dataset, and context-dependent models based on transformer models consistently exhibit superior performance.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Mariana A. Souza, Robert Sabourin, George D. C. Cavalcanti, Rafael M. O. Cruz
Summary: In this study, a dynamic selection technique is proposed to handle sparse and overlapped data. The technique leverages the relationships between instances and classifiers to learn a dynamic classifier combination rule. Experimental results show that the proposed method outperforms static selection and other dynamic selection techniques.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Bin Yu, Ruihui Xu, Mingjie Cai, Weiping Ding
Summary: This paper introduces a clustering method based on non-Euclidean metric and multi-granularity staged clustering to address the challenges posed by complex spatial structure data to traditional clustering methods. The method improves the similarity measure and employs an attenuation-diffusion pattern for local to global clustering, achieving good clustering results.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jian Zhu, Pengbo Hu, Bingqian Li, Yi Zhou
Summary: The acquisition of multi-view hash representation for heterogeneous data is highly important for multimedia retrieval. Current approaches suffer from limited retrieval precision due to insufficient integration of multi-view features and failure to effectively utilize metric information from diverse samples. In this paper, we propose an innovative method called Fast Metric Multi-View Hashing (FMMVH), which demonstrates the superiority of gate-based fusion over traditional methods. We also introduce a novel deep metric loss function to leverage metric information from dissimilar samples. By optimizing and employing model compression techniques, our FMMVH method significantly outperforms existing state-of-the-art methods on benchmark datasets, with up to 7.47% improvement in mean Average Precision (mAP).
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Fayaz Ali Dharejo, Iyyakutti Iyappan Ganapathi, Muhammad Zawish, Basit Alawode, Moath Alathbah, Naoufel Werghi, Sajid Javed
Summary: The resource-limited nature of underwater vision equipment affects underwater robotics and ocean engineering tasks. Super-resolution methods, particularly using Vision Transformers (ViTs), have emerged to enhance low-resolution underwater images. However, ViTs face challenges in handling severe degradation in underwater imaging. In contrast, Multi-scale ViTs (MViTs) overcome these challenges by preserving long-range dependencies through evolving channel capacity. This study proposes a novel algorithm, SwinWave-SR, for efficient and accurate multi-scale super-resolution for underwater images.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Weiwei Jiang, Haoyu Han, Yang Zhang, Jianbin Mu
Summary: This study incorporates federated learning and split learning paradigms with satellite-terrestrial integrated networks and introduces a split-then-federated learning framework and federated split learning with long short-term memory to handle sequential data in STINs. The proposed solution is demonstrated to be effective through a case study of electricity theft detection based on a real-world dataset.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Najah Abuali, Mohammad Bilal Khan, Farman Ullah, Mohammad Hayajneh, Hikmat Ullah, Shahid Mumtaz
Summary: The demand for innovative solutions in biomedical systems for precise diagnosis and management of critical diseases is increasing. A promising technology, non-invasive and intelligent Internet of Medical Things (IoMT) system, emerges to assess patients with reduced health risks. This research introduces a comprehensive framework for early diagnosis of respiratory abnormalities through RF sensing and SDR technology. The results highlight the superior performance of deep learning frameworks in classifying respiratory anomalies.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Shichen Huang, Weina Fu, Zhaoyue Zhang, Shuai Liu
Summary: In the era of adversarial machine learning (AML), developing robust and generalized algorithms has become a key research topic. This study proposes a global similarity matching module and a global-local cognition fusion training mechanism based on relationship adversarial sample generation to improve image-text matching algorithm. Experimental results show significant improvements in accuracy and robustness, performing well in facing security challenges and promoting the fusion of visual and linguistic modalities.
INFORMATION FUSION
(2024)