Information Fusion最新文献_第9页

Leveraging dependency and constituent graphs for aspect sentiment triplet extraction 利用依赖关系图和成分图提取方面情感三元组

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103723

Wang Zou , Xia Sun , Maofu Liu , Yaqiong Xing , Xiaodi Zhao , Jun Feng

{"title":"Leveraging dependency and constituent graphs for aspect sentiment triplet extraction","authors":"Wang Zou , Xia Sun , Maofu Liu , Yaqiong Xing , Xiaodi Zhao , Jun Feng","doi":"10.1016/j.inffus.2025.103723","DOIUrl":"10.1016/j.inffus.2025.103723","url":null,"abstract":"<div><div>Aspect Sentiment Triplet Extraction task (ASTE) aims to extract aspect terms, opinion terms, and determine their corresponding sentiment polarity from the text. Most current studies overlook the impact of dependency noise and sentence structure noise, while a few studies attempt to incorporate constituent features to mitigate such noise. However, they lack fine-grained fusion and alignment between dependency and constituent features. To address the above issue, this paper proposes a method that leverages dependency and constituent graphs (Dual-GNN). First, the model uses GCN to learn the dependency features and employs HGNN to capture the constituent features. Then, we enhance the dependency features with dependency related features and the constituent features with constituent related features. Additionally, we design a fine-grained word-level fusion and alignment matrices that combine dependency and constituent features to reduce the impact of noise and enable fine-grained triplet extraction. Finally, we adopt an efficient table-filling decoding strategy to extract the triplets. We conducted experimental validation on the ASTE-Data-v1, ASTE-Data-v2, and DMASTE datasets. The main results show that, compared with baseline methods, Dual-GNN achieves an F1 score improvement of 0.7 %-2.1 % on the ASTE-Data-v1 dataset and 0.6 %-1.5 % on the ASTE-Data-v2 dataset. Constituent features not only effectively reduce the impact of dependency noise and sentence structure noise but also help the model perceive multi-word term boundaries and accurately pair aspect terms with opinion terms. Combining the advantages of both dependency and constituent features enables more effective execution of the ASTE task.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103723"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PGF-Net: fusing physical imaging model with self-attention for robust underwater feature detection PGF-Net：融合自关注物理成像模型的鲁棒水下特征检测

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103732

Zheng Cong , Yifeng Zhou , Li Wu , Lin Tian , Zhipeng Chen , Minglei Guan , Li He

{"title":"PGF-Net: fusing physical imaging model with self-attention for robust underwater feature detection","authors":"Zheng Cong , Yifeng Zhou , Li Wu , Lin Tian , Zhipeng Chen , Minglei Guan , Li He","doi":"10.1016/j.inffus.2025.103732","DOIUrl":"10.1016/j.inffus.2025.103732","url":null,"abstract":"<div><div>Robust feature detection in underwater environments is severely impeded by image degradation from light absorption and scattering. Traditional algorithms fail in these low-contrast, blurred conditions, while deep learning methods suffer from the domain gap between terrestrial and underwater imagery and a scarcity of annotated data. To address these challenges, this paper introduces PGF-Net, a systematic framework that fuses physical imaging principles with deep learning. The framework leverages a dual-fusion strategy: First, a parametric underwater imaging model is proposed to guide the synthesis of a large-scale, physically realistic training dataset, effectively injecting prior knowledge of the degradation process into the data domain. Second, a novel detection network architecture is designed, which incorporates a self-attention mechanism to fuse local features with global contextual information, enhancing robustness against detail loss. This end-to-end network is trained on the synthesized data using a curriculum learning strategy, progressing from mild to severe degradation conditions. Extensive experiments on public datasets demonstrate that PGF-Net significantly outperforms classic and state-of-the-art deep learning methods in both keypoint detection and matching, particularly in turbid water. The proposed framework validates the efficacy of integrating physical priors with data-driven models for challenging computer vision tasks and provides a robust solution for underwater visual perception.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103732"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fusing sequential recommender and ad-hoc planner for multi-faceted preference understanding in conversational recommendation 会话推荐中融合顺序推荐和特别计划的多面偏好理解

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103735

Sangyeop Kim , Jaewon Jung , Taeseung You , Sungzoon Cho

{"title":"Fusing sequential recommender and ad-hoc planner for multi-faceted preference understanding in conversational recommendation","authors":"Sangyeop Kim , Jaewon Jung , Taeseung You , Sungzoon Cho","doi":"10.1016/j.inffus.2025.103735","DOIUrl":"10.1016/j.inffus.2025.103735","url":null,"abstract":"<div><div>Recent advances in Large Language Models (LLMs) have accelerated the development of Conversational Recommender Systems (CRS). However, existing CRS approaches face two critical challenges: limited incorporation of historical user interactions and unrealistic experimental settings that fail to reflect real-world scenarios. To address these challenges, we propose FuseRec, a novel framework that enables any Sequential Recommender System (SRS) to function as a conversational recommender through integration with an ad-hoc Planner. The integration leverages the inherent strength of SRS in processing long-term historical interactions while the Planner learns conversation strategies. Additionally, a CRS module refines recommendations by incorporating conversational context, effectively fusing sequential patterns with real-time dialogue insights. To create realistic evaluation environments, we implement an advanced GenAI-based user simulator with stratified personas reflecting varying degrees of preference awareness, from users with clear preferences to those with abstract, uncertain preferences. To handle multi-faceted user behaviors, the Planner employs four sophisticated actions: Chitchat, semantic questioning (Semantic Q), attribute questioning (Attribute Q), and Recommend, dynamically adjusting based on user response patterns. We train the Planner through reinforcement learning with curriculum strategy based on user difficulty levels. Through extensive experiments, we demonstrate that FuseRec significantly outperforms existing approaches in recommendation accuracy while showing remarkable adaptability across different user types and recommendation scenarios.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103735"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Beyond embedding-mapping: Social network alignment via generative information fusion and LLM-guided iterative mechanism 超越嵌入映射：通过生成信息融合和llm引导迭代机制的社会网络对齐

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103733

Jibing Gong , Jiquan Peng , Wei Wang , Wei Zhou , Chaozhuo Li , Philip S. Yu

{"title":"Beyond embedding-mapping: Social network alignment via generative information fusion and LLM-guided iterative mechanism","authors":"Jibing Gong , Jiquan Peng , Wei Wang , Wei Zhou , Chaozhuo Li , Philip S. Yu","doi":"10.1016/j.inffus.2025.103733","DOIUrl":"10.1016/j.inffus.2025.103733","url":null,"abstract":"<div><div>Social Network Alignment (SNA) aims to identify and match user accounts belonging to the same real-world individual across multiple social platforms, which has garnered growing research interest. Existing methods typically encode textual and structural information into a latent space and learn a mapping function from annotated user alignments to accomplish SNA. However, the inherent sparsity and noise in social data limit these models’ ability to fully capture user characteristics. Moreover, direct alignment based on latent space often overlooks critical details from the original information, reducing both alignment quality and interpretability. To address these limitations, we propose LLM-SNA, a novel framework that integrates generative information fusion and LLM-guided iterative mechanism. The generative information fusion leverages LLMs to transform sparse user attributes, microblogs, and neighbor descriptions into enriched, comprehensive user profiles. We further perform intra-network and inter-network graph learning on enriched user profiles to incorporate structural information. To balance accuracy and efficiency, the LLM-guided iterative mechanism first applies a coarse filter based on embedding similarities to collect potential alignment candidates. The LLM then evaluates these candidates by reasoning over their original textual information. If the LLM deems the candidates misaligned, the candidate set is expanded until confident matches emerge. Comprehensive experiments on three widely used datasets demonstrate the advantages of LLM-SNA over state-of-the-art baseline methods and highlight the potential of LLMs for SNA tasks.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103733"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MFA-NRM: A novel framework for multimodal fusion and semantic alignment in visual neural decoding MFA-NRM：视觉神经解码中多模态融合和语义对齐的新框架

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103717

Wei Huang , Hengjiang Li , Fan Qin , Jingpeng Li , Sizhuo Wang , Pengfei Yang , Luan Zhang , Yunshuang Fan , Jing Guo , Kaiwen Cheng , Huafu Chen

{"title":"MFA-NRM: A novel framework for multimodal fusion and semantic alignment in visual neural decoding","authors":"Wei Huang , Hengjiang Li , Fan Qin , Jingpeng Li , Sizhuo Wang , Pengfei Yang , Luan Zhang , Yunshuang Fan , Jing Guo , Kaiwen Cheng , Huafu Chen","doi":"10.1016/j.inffus.2025.103717","DOIUrl":"10.1016/j.inffus.2025.103717","url":null,"abstract":"<div><div>Integrating multimodal semantic features, such as images and text, to enhance visual neural representations has proven to be an effective strategy in brain visual decoding. However, previous studies have either focused solely on unimodal enhancement techniques or have inadequately addressed the alignment ambiguity between different modalities, leading to an underutilization of the complementary benefits of multimodal features or a reduction in the semantic richness of the resulting neural representations. To address these limitations, we propose a Multimodal Fusion Alignment Neural Representation Model (MFA-NRM), which enhances visual neural decoding by integrating multimodal semantic features from images and text. The MFA-NRM incorporates a fusion module that utilizes a Variational Autoencoder (VAE) and a self-attention mechanism to integrate multimodal features into a unified latent space, thereby facilitating robust semantic alignment with neural activity. Additionally, we introduce prompt techniques that adapt neural representations to individual differences, improving cross-subject generalization. Our approach also leverages the semantic knowledge from ten large pre-trained models to further enhance performance. Experimental results on the Natural Scenes Dataset (NSD) show that, compared to unimodal alignment methods, our method improves recognition tasks by 18.8 % and classification tasks by 4.30 %, compared to other multimodal alignment methods without the fusion module, our approach improves recognition tasks by 33.59 % and classification tasks by 4.26 %. These findings indicate that the MFA-NRM effectively resolves the problem of alignment ambiguity and enables richer semantic extraction from brain responses to multimodal visual stimuli, offering new perspectives for visual neural decoding.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103717"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ObjSegAD-Net: Region-aware pseudo-defect injection and dual-branch architecture for unsupervised industrial anomaly detection ObjSegAD-Net：基于区域感知的伪缺陷注入和双分支架构的无监督工业异常检测

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103707

Shaohua Dong, Fangxu Hu, Bing Wei, Yi Wu

{"title":"ObjSegAD-Net: Region-aware pseudo-defect injection and dual-branch architecture for unsupervised industrial anomaly detection","authors":"Shaohua Dong, Fangxu Hu, Bing Wei, Yi Wu","doi":"10.1016/j.inffus.2025.103707","DOIUrl":"10.1016/j.inffus.2025.103707","url":null,"abstract":"<div><div>Anomaly detection in industrial manufacturing identifies product defects. However, limited anomalous samples and background noise often reduce accuracy and increase false alarms. To solve this, we propose ObjSegAD-Net, an unsupervised anomaly detection method. It separates each image into foreground and background regions. It uses foreground-guided pseudo-defect synthesis to inject diverse synthetic anomalies, boosting data diversity with more pseudo-samples. For the background, it adds noise such as Gaussian blur, helping the model distinguish true defects from irrelevant variations. During inference, ObjSegAD-Net adopts a dual-branch architecture with region-aware attention mechanisms, which adaptively enhances responses to foreground anomalies while suppressing background interference. This design significantly reduces false positives and improves detection accuracy under complex noisy conditions. ObjSegAD-Net achieves state-of-the-art results on multiple industrial anomaly detection benchmarks, demonstrating the robustness and generalization capabilities of its region-aware pseudo-defect generation and dual-task architecture.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103707"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Channel-adaptive generative reconstruction and fusion for multi-sensor graph features in few-shot fault diagnosis 基于通道自适应的多传感器图特征生成重建与融合

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103742

Peijie You , Lei Wang , Anh Nguyen , Xin Zhang , Baoru Huang

{"title":"Channel-adaptive generative reconstruction and fusion for multi-sensor graph features in few-shot fault diagnosis","authors":"Peijie You , Lei Wang , Anh Nguyen , Xin Zhang , Baoru Huang","doi":"10.1016/j.inffus.2025.103742","DOIUrl":"10.1016/j.inffus.2025.103742","url":null,"abstract":"<div><div>Recently, multi-sensor feature fusion has been proven to be an effective strategy for improving the accuracy of few-shot fault diagnosis. However, existing fault diagnosis models based on multi-sensor feature fusion often overlook significant inter-channel discrepancies and struggle to mitigate noise pollution inherent in multi-source signals. To address these limitations, this paper proposes a channel-adaptive generative reconstruction and fusion framework that integrates a contrastive variational graph autoencoder feature fusion (CogFusion) module for robust few-shot fault representation learning. The CogFusion module leverages the generative capability of a contrastive variational graph autoencoder (CGE) to reconstruct noise-suppressed node features while explicitly modeling latent distributions of multi-sensor signals. By incorporating a multi-channel parallel graph contrastive learning strategy, CogFusion enhances discriminative feature separation by contrasting topological structures of positive and negative sample pairs, effectively isolating fault-related patterns from noisy embeddings. To adaptively fuse multi-channel information, a channel discrepancy-guided weighting mechanism dynamically prioritizes high-credibility sensor features, mitigating the impact of low-quality data. To further enhance feature learning in few-shot diagnosis, a dual-scale topological Transformer (DSTT) model is introduced to deeply mine the reconstructed multi-channel topological graph, enabling high-precision few-shot fault diagnosis. Experimental results on the axial flow pump and HUSTgearbox datasets demonstrate that the proposed method outperforms both single-channel and existing multi-sensor feature fusion methods, highlighting its superiority in feature fusion and cross-channel information integration.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103742"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving deepfake detection with predictive inter-modal alignment and feature reconstruction in audio–visual asynchrony scenarios 在视听异步场景下，利用预测的多模态对齐和特征重建改进深度伪造检测

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103708

Yan Wang , Qindong Sun , Jingpeng Zhang , Dongzhu Rong , Chao Shen , Xiaoxiong Wang

{"title":"Improving deepfake detection with predictive inter-modal alignment and feature reconstruction in audio–visual asynchrony scenarios","authors":"Yan Wang , Qindong Sun , Jingpeng Zhang , Dongzhu Rong , Chao Shen , Xiaoxiong Wang","doi":"10.1016/j.inffus.2025.103708","DOIUrl":"10.1016/j.inffus.2025.103708","url":null,"abstract":"<div><div>Existing multimodal deepfake detection methods primarily rely on capturing correlations between audio–visual modalities to improve detection performance. However, in scenarios such as instant messaging and online video conferencing, network jitter often leads to audio–visual asynchrony, disrupting inter-modal associations and limiting the effectiveness of these methods. To address this issue, we propose a deepfake detection framework specifically designed for audio–visual asynchrony scenarios. First, based on the theory of open balls in metric space, we analyze the variation mechanism of joint features in both audio–visual synchrony and asynchrony scenarios, revealing the impact of audio–visual asynchrony on detection performance. Second, we design a multimodal subspace representation module that incorporates hierarchical cross-modal semantic similarity to address inconsistencies in audio–visual data distributions and representation heterogeneity. Furthermore, we formulate audio–visual feature alignment as an integer linear programming task and employ the Hungarian algorithm to reconstruct missing inter-modal associations. Finally, we introduce a self-supervised masked reconstruction mechanism to restore missing features and construct a joint correlation matrix to measure cross-modal dependencies, enhancing the robustness of detection. Theoretical analysis and experimental results show that our method outperforms baselines in audio–visual synchrony and asynchrony scenarios and exhibits robustness against unknown disturbances.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103708"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AirGPT: Spatio-temporal large language model for air quality prediction AirGPT：空气质量时空大语言预测模型

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-12 DOI: 10.1016/j.inffus.2025.103730

Zhonghang Li , Tianyi Chen , Yong Xu

{"title":"AirGPT: Spatio-temporal large language model for air quality prediction","authors":"Zhonghang Li , Tianyi Chen , Yong Xu","doi":"10.1016/j.inffus.2025.103730","DOIUrl":"10.1016/j.inffus.2025.103730","url":null,"abstract":"<div><div>Air pollution poses a critical threat to public health, ecosystems, and climate stability worldwide. Accurate air quality prediction is essential for informed policy-making, health risk mitigation, and environmental management, enabling proactive responses to pollution events and long-term planning for sustainable urban development. Despite advances, deep learning models for air quality prediction still face three critical challenges: heavy reliance on abundant historical data, difficulty in effectively fusing diverse information sources, and a lack of interpretability. To address these issues, we propose AirGPT, a large language model framework for air quality prediction. AirGPT integrates a specialized spatio-temporal encoder with a novel spatio-temporal instruction-tuning paradigm, enabling it to efficiently model complex spatio-temporal dependencies and perform sophisticated data fusion. Furthermore, our Chain-of-Thought distillation mechanism allows the model to externalize its predictive reasoning in a transparent, human-readable format, thereby enhancing interpretability. Experimental results demonstrate that AirGPT achieves state-of-the-art accuracy on air quality prediction tasks, particularly in data-scarce and zero-shot scenarios. By integrating interpretable reasoning with transparent predictive outputs, AirGPT provides a robust and reliable framework to support informed environmental decision-making. Our source code is available at: <span><span>https://anonymous.4open.science/r/AirGPT-6ACC</span><svg><path></path></svg></span></div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103730"},"PeriodicalIF":15.5,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Review of pedestrian trajectory prediction based on graph neural networks 基于图神经网络的行人轨迹预测研究进展

IF 15.5 1区计算机科学

Information Fusion Pub Date : 2025-09-11 DOI: 10.1016/j.inffus.2025.103727

Haifeng Sang, Wangxing Chen, Zishan Zhao

{"title":"Review of pedestrian trajectory prediction based on graph neural networks","authors":"Haifeng Sang, Wangxing Chen, Zishan Zhao","doi":"10.1016/j.inffus.2025.103727","DOIUrl":"10.1016/j.inffus.2025.103727","url":null,"abstract":"<div><div>Accurately predicting pedestrian trajectories is crucial for the development of autonomous driving, robot navigation, and intelligent surveillance systems. However, this task remains extremely challenging due to the complexity of social interactions between pedestrians. Graph neural networks (GNNs) have been widely adopted in pedestrian trajectory prediction tasks due to their powerful interaction modeling capabilities and scalability. The GNN-based trajectory prediction methods construct different graph structures and then utilize graph convolution and its variants to capture pedestrian interaction features, thereby improving model prediction performance. To systematically review the research progress in this direction, this paper proposes a new classification method that divides the existing GNN-based methods into five types: conventional graph-based methods, sparse graph-based methods, multi-graph-based methods, heterogeneous graph-based methods, and higher-order graph-based methods. This paper systematically analyzes the modeling strategies, advantages, and disadvantages of each type of method to provide further guidance for subsequent researchers. In addition, we evaluate the prediction performance and inference time of these methods on public datasets and then discuss the current challenges and potential future directions of GNN-based trajectory prediction methods. A summary of related papers and codes is publicly available at <span><span>https://github.com/Chenwangxing/Review-of-PTP-Based-on-GNNs</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"127 ","pages":"Article 103727"},"PeriodicalIF":15.5,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0