IEEE transactions on artificial intelligence最新文献_第10页

Boundary-Aware Distracted Attention Network for Camouflaged Object Detection 基于边界感知的分散注意网络伪装目标检测

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-03-03 DOI: 10.1109/TAI.2026.3669547

Yihan Shang;Lin Wang;Junyu Dong;Xinghui Dong

{"title":"Boundary-Aware Distracted Attention Network for Camouflaged Object Detection","authors":"Yihan Shang;Lin Wang;Junyu Dong;Xinghui Dong","doi":"10.1109/TAI.2026.3669547","DOIUrl":"https://doi.org/10.1109/TAI.2026.3669547","url":null,"abstract":"Camouflaged object detection (COD) involves precisely segmenting objects, which are seamlessly blended into the surroundings, due to the similarities between the surroundings and them in color, texture, and other camouflaging techniques. To address the challenges that such similarities pose, distraction mining approaches have been proposed. However, they normally struggle with boundary delineation and extraction of relevant features. To get rid of this dilemma, we introduce a boundary-aware distracted attention network (BADANet), which exploits both the boundary cue and the distraction mining strategy. Specifically, we first use a pretrained network as the encoder for feature extraction. Then the features extracted are sent to a boundary shrinking module (BSM) that we design. After the output is processed by a multiple dense atrous spatial pyramid pooling (MDASPP) module, a boundary map is produced. Given an encoder block, the features extracted are also fed into a multibranch bidirectional fusion block (MBBFB), which performs the bidirectional fusion at the channel dimension, followed by the multiple fusion conducted at the spatial dimension via an individual MDASPP module. We further propose a boundary-aware distracted attention (BADA) block, which receives both the features fused and the boundary map. With regard to the encoder blocks, a series of BADA blocks are comprised of a distracted attention decoder. Finally, the detection mask is generated by the last BADA block. We have conducted a series of experiments on four popular COD datasets. Experimental results demonstrate that the proposed BADANet normally outperforms 18 baseline methods. These promising results should be due to the BADA mechanism that we design.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4690-4702"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148747149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transfer Learning for Human Motion Prediction: Improving Accuracy Under Data Scarcity 基于迁移学习的人体运动预测：提高数据稀缺下的准确性

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-03-04 DOI: 10.1109/TAI.2026.3670340

Marco Casarin;Michael Vanuzzo;Mattia Guidolin;Monica Reggiani;Stefano Michieletto

{"title":"Transfer Learning for Human Motion Prediction: Improving Accuracy Under Data Scarcity","authors":"Marco Casarin;Michael Vanuzzo;Mattia Guidolin;Monica Reggiani;Stefano Michieletto","doi":"10.1109/TAI.2026.3670340","DOIUrl":"https://doi.org/10.1109/TAI.2026.3670340","url":null,"abstract":"Human motion prediction (HMP) consists of anticipating future human poses based on motion history. While recent approaches achieved strong performance on benchmark datasets, their applicability to real-world scenarios remains limited due to the scarcity of context-specific motion data. In this work, we propose a unified, model-agnostic transfer learning (TL) framework for HMP to improve prediction accuracy under data-scarce target domains. The framework leverages pretraining on a large dataset of generic motions to learn a transferable motion prior, followed by systematic adaptation to context-specific actions using different TL techniques. We present a comprehensive evaluation protocol to characterize prediction accuracy across multiple representative HMP architectures, target datasets, and TL strategies and to evaluate training efficiency by introducing dedicated TL metrics. Beyond performance gains, we analyze the impact of source-target dataset distance and model complexity on TL effectiveness. The results show that TL consistently improves accuracy across all models and target datasets, reducing error up to 32.95% compared with training from scratch. In addition, TL enhances convergence speed, significantly reducing training epochs. These findings demonstrate TL as an effective and versatile approach for improving HMP under data scarcity, and provide methodological insights for its deployment in real-world context-specific applications.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4714-4725"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421082","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148749591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

When Annotators Disagree: A Principled Approach to Learning With Noisy Labels 当注释者不同意时：使用嘈杂标签学习的原则方法

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-03-02 DOI: 10.1109/TAI.2026.3666527

Maria Sofia Bucarelli;Antonio Purificato;Andrea Bacciu;Lucas Cassano;Federico Siciliano;Anil Nelakanti;Amin Mantrach;Fabrizio Silvestri

引用次数: 0

Luminance Component Analysis for Exposure Correction 曝光校正的亮度成分分析

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-09 DOI: 10.1109/TAI.2026.3660821

Jingchao Peng;Thomas Bashford-Rogers;Jingkun Chen;Haitao Zhao;Zhengwei Hu;Kurt Debattista

{"title":"Luminance Component Analysis for Exposure Correction","authors":"Jingchao Peng;Thomas Bashford-Rogers;Jingkun Chen;Haitao Zhao;Zhengwei Hu;Kurt Debattista","doi":"10.1109/TAI.2026.3660821","DOIUrl":"https://doi.org/10.1109/TAI.2026.3660821","url":null,"abstract":"Exposure correction methods aim to adjust the luminance while maintaining other luminance-unrelated information. However, current exposure correction methods have difficulty in fully separating luminance-related and luminance-unrelated components, leading to distortions in color, loss of detail, and requiring extra restoration procedures. Inspired by principal component analysis (PCA), this article proposes an exposure correction method called luminance component analysis (LCA). LCA applies the orthogonal constraint to a U-Net structure to decouple luminance-related and luminance-unrelated features. With decoupled luminance-related features, LCA adjusts only the luminance-related components while keeping the luminance-unrelated components unchanged. To optimize the orthogonal constraint problem, LCA employs a geometric optimization algorithm, which converts the constrained problem in Euclidean space to an unconstrained problem in orthogonal Stiefel manifolds. Extensive experiments show that LCA can decouple the luminance feature from the RGB color space. Moreover, LCA achieves the best PSNR (21.33) and SSIM (0.88) in the exposure correction dataset with 28.72 FPS.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4326-4339"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DQEN: Dual Query Enhancement Network for DETR-Based HOI Detection 基于der的HOI检测双查询增强网络

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-16 DOI: 10.1109/TAI.2026.3665181

Zhehao Li;Yucheng Qian;Chong Wang;Yinghao Lu;Yi Chen;Jiong Wang;Jiafei Wu

{"title":"DQEN: Dual Query Enhancement Network for DETR-Based HOI Detection","authors":"Zhehao Li;Yucheng Qian;Chong Wang;Yinghao Lu;Yi Chen;Jiong Wang;Jiafei Wu","doi":"10.1109/TAI.2026.3665181","DOIUrl":"https://doi.org/10.1109/TAI.2026.3665181","url":null,"abstract":"Human–object interaction (HOI) detection focuses on localizing human–object pairs and recognizing their interactions. Recently, the DETR-based framework has been widely adopted in HOI detection. In DETR-based HOI models, queries with clear meaning are crucial for accurately detecting HOIs. However, prior works have typically relied on randomly initialized queries, leading to vague representations that limit the model’s effectiveness. Meanwhile, humans in the HOI categories are fixed, while objects and their interactions are variable. Therefore, we propose a dual query enhancement network (DQEN) to enhance object and interaction queries. Specifically, object queries are enhanced with object-aware encoder features, enabling the model to focus more effectively on humans interacting with objects in an object-aware way. On the other hand, we design a novel interaction semantic fusion module to exploit the HOI candidates that are promoted by the contrastive language-image pretraining model. Semantic features are extracted to enhance the initialization of interaction queries, thereby improving the model’s ability to understand interactions. Furthermore, we introduce an auxiliary prediction unit aimed at improving the representation of interaction features. Our proposed method achieves competitive performance on both the HICO-Det and the V-COCO datasets.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4504-4517"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Conditional Deep Unrolling for LiDAR Super-Resolution and Improved Segmentation: An End-to-End Solution 激光雷达超分辨率和改进分割的条件深度展开：端到端解决方案

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-13 DOI: 10.1109/TAI.2026.3664354

Alexandros Gkillas;Nikos Pipergikos;Aris S. Lalos;Duong-Van Nguyen

{"title":"Conditional Deep Unrolling for LiDAR Super-Resolution and Improved Segmentation: An End-to-End Solution","authors":"Alexandros Gkillas;Nikos Pipergikos;Aris S. Lalos;Duong-Van Nguyen","doi":"10.1109/TAI.2026.3664354","DOIUrl":"https://doi.org/10.1109/TAI.2026.3664354","url":null,"abstract":"light detection and ranging (LiDAR) segmentation is essential for autonomous driving, but its accuracy heavily depends on the sensor resolution. While high-resolution LiDAR offers precise environmental detail, its cost is prohibitive. Low-cost sensors, by contrast, produce sparse point clouds that degrade segmentation quality. Recent LiDAR super-resolution (SR) methods aim to address this, but face three key challenges: 1) they are optimized independently of segmentation, leading to suboptimal results; 2) they require costly postprocessing to remove outliers; and 3) they introduce significant computational overhead, often surpassing the complexity of the segmentation network. To address these challenges, we propose a novel conditional optimization problem for LiDAR SR, inspired by recent advances in conditional generative models, which use external guidance signals to influence the generation process. In our case, semantic priors are extracted from the low-resolution data to guide the reconstruction toward semantically meaningful regions. This conditional formulation is efficiently solved using a model-based deep unrolling strategy, yielding a highly efficient conditional SR network. To further enhance performance, the resulting SR model is seamlessly integrated with a high-resolution segmentation network to form a unified, end-to-end trainable architecture. Experiments on public benchmarks show that our method outperforms state-of-the-art LiDAR SR approaches, particularly in preserving semantically important structures. In addition, we successfully deploy the proposed framework on our demo vehicle equipped with an NVIDIA Orin and a 16-channel LiDAR sensor, confirming its practical applicability in real-world driving environments. The code will be available at the project repository.<xref>1</xref><fn><label>1</label><uri>http://github.com/alexandrosgk/Conditional-DU-3D-segmentation</uri></fn>","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4421-4435"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing PLS in UAV-Aided Backscatter Networks: A Multiagent DRL Framework with Federated Learning 增强无人机辅助后向散射网络中的PLS：一个具有联邦学习的多智能体DRL框架

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-03-04 DOI: 10.1109/TAI.2026.3669890

Shivam Sarsawat;Korampalli Jaya Satwik;Mahendra K. Shukla;Manish Pratap Singh;Om Jee Pandey

{"title":"Enhancing PLS in UAV-Aided Backscatter Networks: A Multiagent DRL Framework with Federated Learning","authors":"Shivam Sarsawat;Korampalli Jaya Satwik;Mahendra K. Shukla;Manish Pratap Singh;Om Jee Pandey","doi":"10.1109/TAI.2026.3669890","DOIUrl":"https://doi.org/10.1109/TAI.2026.3669890","url":null,"abstract":"In recent years, enhancing physical layer security (PLS) in UAV-aided backscatter networks has received huge attention among the research community due to its various applications, such as smart farming, cognitive healthcare, and intelligent industrial automation, among others. It results in secure and reliable data transmission over the network. In this context, this article proposes a novel federated learning (FL)-enabled multiagent deep reinforcement learning (DRL) framework to enhance the PLS of unmanned aerial vehicle (UAV) -aided backscatter communication networks. We consider a system comprising a UAV assisting a passive backscatter tag (BT) in the presence of a potential eavesdropper (EV). To protect the backscattered information from interception, artificial noise (AN) is injected by the UAV. The objective is to maximize the secrecy rate by jointly optimizing the UAV’s hovering position, power allocation factor, and the BT’s reflection coefficient. To tackle this challenging optimization task, we employ a multiagent DRL approach in which dedicated agents collaboratively learn optimal policies for each parameter. Furthermore, to ensure privacy and improve training efficiency, we integrate an FL scheme where the agents share model updates instead of raw data. Experimental results validate that the proposed framework significantly enhances secrecy performance while enabling decentralized and privacy-preserving learning in UAV-assisted backscatter networks. The results are also compared with other existing methods and varying parameters value, which validate the significance of the utilization of the proposed method.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4703-4713"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148749033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ECGNextFormer: A Lightweight, Scalable, and Explainable Architecture for Estimating Cardiovascular Well-Being From Electrocardiograms ECGNextFormer：一个轻量级的、可扩展的、可解释的架构，用于从心电图估计心血管健康状况

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-19 DOI: 10.1109/TAI.2026.3656125

Mohammed Yusuf Ansari;Md Rabiul Islam;Khalid Qaraqe;Erchin Serpedin;Raffaella Righetti;Marwa Qaraqe

{"title":"ECGNextFormer: A Lightweight, Scalable, and Explainable Architecture for Estimating Cardiovascular Well-Being From Electrocardiograms","authors":"Mohammed Yusuf Ansari;Md Rabiul Islam;Khalid Qaraqe;Erchin Serpedin;Raffaella Righetti;Marwa Qaraqe","doi":"10.1109/TAI.2026.3656125","DOIUrl":"https://doi.org/10.1109/TAI.2026.3656125","url":null,"abstract":"An electrocardiogram (ECG) is a widely utilized noninvasive test in healthcare for diagnosing cardiac diseases. Recent studies have validated that the delta between neural network-derived ECG age and chronological age represents a measure of cardiovascular well-being. Typically, ECG age estimation studies rely on neural networks designed for ECG disease diagnosis, resulting in networks that are often computationally heavy, difficult to scale, and challenging to interpret. To address this gap, we propose ECGNextFormer, a lightweight hybrid CNN and transformer architecture for efficient ECG age estimation. ECGNextFormer features a novel shallow backbone with modified ECGNext blocks for ECG feature extraction and integrates a custom self-attention layer with a multiscale pooling block to enhance the receptive field. The bottleneck drop key self-attention provides a global receptive field and reweighs the feature maps, while multiscale pooling retains fine-grained spatial details crucial for age estimation. These innovations make ECGNextFormer a lightweight and scalable alternative to existing networks with superior performance. The lite variant of ECGNextFormer surpasses the best network in the literature by 14.7% in performance and 53<inline-formula><tex-math>$times$</tex-math></inline-formula> lower parameter count. ECGNextFormer is comprehensively explained through fine-grained heatmaps generated using guided backpropagation. Subsequently, a novel lead scoring scheme quantifies lead significance in healthy and diseased groups, and human-interpretable concepts highlight essential ECG features for age estimation.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4311-4325"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11400535","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Delay-Aware Reinforcement Learning With Encoder-Enhanced State Representations 基于编码器增强状态表示的延迟感知强化学习

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-16 DOI: 10.1109/TAI.2026.3664781

Bo Xia;Yilun Kong;Yongzhe Chang;Bo Yuan;Zhiheng Li;Xueqian Wang;Bin Liang

{"title":"Delay-Aware Reinforcement Learning With Encoder-Enhanced State Representations","authors":"Bo Xia;Yilun Kong;Yongzhe Chang;Bo Yuan;Zhiheng Li;Xueqian Wang;Bin Liang","doi":"10.1109/TAI.2026.3664781","DOIUrl":"https://doi.org/10.1109/TAI.2026.3664781","url":null,"abstract":"In real-world decision-making systems, nonnegligible observation and action delays arising from sensing and actuation break the standard Markov assumption and can significantly degrade reinforcement learning (RL) performance. We present delay-resilient encoder-enhanced RL (DEER), a practical framework that systematically integrates well-established techniques, including sequence-to-sequence representation learning, information-state construction, and offline-to-online RL, to support robust performance in delayed environments. DEER first pretrains an encoder on offline delay-free trajectories and subsequently deploys it online to map delayed observations together with recent action histories into fixed-length context vectors suitable for standard RL agents. We further develop a theoretical decomposition that relates reconstruction error, distributional mismatch, latent-policy generalization, and environment mismatch to overall performance, thereby providing interpretable guidance for design choices. Empirically, integrating DEER with soft actor–critic yields competitive and stable performance across a range of constant and stochastic delay settings on six continuous-control benchmarks. Accordingly, this work makes two contributions: 1) a practical, deployable engineering solution for delayed RL that effectively leverages existing building blocks; and 2) a quantitative analysis that clarifies when and why this integration is effective.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4476-4490"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HiCo-STEP: Causality Informed Hierarchical Spatiotemporal Network for Traffic Emission Prediction HiCo-STEP：基于因果关系的分层时空网络交通排放预测

IEEE transactions on artificial intelligence Pub Date : 2026-08-01 Epub Date: 2026-02-18 DOI: 10.1109/TAI.2026.3665658

Guoan Zhang;Lihong Pei;Yang Cao;Yu Kang;Jiahu Qin

{"title":"HiCo-STEP: Causality Informed Hierarchical Spatiotemporal Network for Traffic Emission Prediction","authors":"Guoan Zhang;Lihong Pei;Yang Cao;Yu Kang;Jiahu Qin","doi":"10.1109/TAI.2026.3665658","DOIUrl":"https://doi.org/10.1109/TAI.2026.3665658","url":null,"abstract":"Traffic emission has emerged as a primary source of urban air pollution due to the rapid increase in vehicle ownership. Therefore, achieving fine-grained traffic emission prediction is crucial for the comprehensive supervision of mobile source emission and the formulation of targeted mitigation policies. Traffic emissions exhibit spatiotemporal heterogeneity and complex spatial interactions. Existing emission prediction methods utilize predefined graph structure to model spatiotemporal dependency, ignoring the complex interaction mechanism among road segments, which may introduce spurious correlations to interfere with spatio-temporal representation learning. In this article, we propose a <underline>hierarchical <underline>causality-inf<underline>ormed <underline>spatiotemporal network to realize fine-grained <underline>traffic <underline>emission <underline>prediction (HiCo-STEP). Specifically, we train the model in a dual-stage manner and propose a contrastive spatiotemporal clustering (CSTC) module in hierarchical prediction stage, which generates macro emission semantics and forms hierarchical spatiotemporal graphs. Then we discover and optimize the causal relationship between road-segment level and region level in causal learning stage, realizing <underline>causal <underline>fusion of spatiotemporal representations from <underline>coarse to <underline>fine grained (CF2). The proposed method is evaluated on the Xi’an and Beijing emission datasets, and the experiments demonstrate the superiority of our method compared with the existing baselines.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 8","pages":"4541-4552"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0