Query：
学者姓名：冯心欣
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Multimodal information plays an important role in the advanced Internet of Things (IoT) in the era of 6G, which provides reliable and comprehensive assistance for downstream tasks through further fusion and analysis via federated learning (FL). One of the primary challenges in FL is data heterogeneity, which may lead to domain shifts and sharply different local long-tailed category distribution across nodes. These issues hinder the large-scale deployment of FL in IoT applications equipped with multiple various multimodal sensors due to performance deterioration. In this paper, we propose a novel multimodal fusion framework to tackle the aforementioned coupled problems arising during the cooperative fusion of multimodal information without privacy exposure among decentralized nodes equipped with diverse sensors. Specifically, we introduce a flexible global logit alignment (GLA) method based on multi-view domains. This method enables the fusion of diverse multimodal information with the consideration of domain shifts caused by modality-based data heterogeneity. Furthermore, we propose a novel local angular margin (LAM) scheme, which dynamically adjusts decision boundaries for locally seen categories while preserving global decision boundaries for unseen categories. This effectively mitigates severe model divergence caused by significantly different category distributions. Extensive simulations demonstrate the superiority of the proposed framework, which exhibits significant merits in tackling model degeneration caused by data heterogeneity and enhancing modality-based generalization for heterogeneous scenarios.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gao, Min , Zheng, Haifeng , Feng, Xinxin et al. Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning [J]. | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 16 , 2025 : 16736-16744 . |
| MLA | Gao, Min et al. "Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning" . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 16 (2025) : 16736-16744 . |
| APA | Gao, Min , Zheng, Haifeng , Feng, Xinxin , Tao, Ran . Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 16 , 2025 , 16736-16744 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Antimony sulfide (Sb2S3) thin film have a suitable band gap (1.73 eV) and high absorption coefficient, indicating potential prospects in indoor photovoltaics. The open-circuit voltage (VOC) attenuation under indoor weak light limits the performance and application, which is affected by the heterojunction interface quality. Hence, we propose a hole transport layer free Sb2S3 indoor photovoltaic cell using Li-doped TiO2 as the electron transport layer to overcome weak-light VOC loss. The Li-doped TiO2 films prepared by spray pyrolysis LiCl additive precursor reveal higher surface potentials, enhancing electron collections. The doped interface also promoted subsequent grain growth of Sb2S3 thin film. The champion device, configured as FTO/TiO2:Li/Sb2S3/Au, achieves an efficiency of 6.12% with an optimal Li doping ratio of 8% in the TiO2 layer. The Li introduction at the junction interface suppresses the photocarrier recombinations under indoor light, thus improving device performance. The indoor power conversion efficiency of the Li-TiO2 based Sb2S3 device reaches 12.7% under the irradiation of 1000-lux LED, showing 48% improvement compared with the undoped device. The Li-doped TiO2/Sb2S3 photovoltaic device demonstrates significant advantages, particularly in cold and monochromatic light conditions, opening new prospects for indoor application.
Keyword ：
conversion efficiency conversion efficiency indoor photovoltaics indoor photovoltaics Li-doped TiO2 Li-doped TiO2 Sb2S3 Sb2S3 VOC improvement VOC improvement
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Kefei , Deng, Hui , Feng, Xinxin et al. Suppressing weak-light voltage attenuation in Sb2S3 indoor photovoltaics using Li-doped TiO2 layer [J]. | NANO RESEARCH , 2025 , 18 (10) . |
| MLA | Wu, Kefei et al. "Suppressing weak-light voltage attenuation in Sb2S3 indoor photovoltaics using Li-doped TiO2 layer" . | NANO RESEARCH 18 . 10 (2025) . |
| APA | Wu, Kefei , Deng, Hui , Feng, Xinxin , Hong, Jinwei , Wang, Guidong , Ishaq, Muhammad et al. Suppressing weak-light voltage attenuation in Sb2S3 indoor photovoltaics using Li-doped TiO2 layer . | NANO RESEARCH , 2025 , 18 (10) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In autonomous driving, accurately predicting the future trajectories of surrounding vehicles is essential for reliable navigation and planning. Unlike previous approaches that relied on high-definition maps and vehicle coordinates, recent research seeks to predict the future trajectories of both surrounding and ego vehicles from a bird's-eye view (BEV) perspective, leveraging data from multiple sensors on the vehicle in an end-to-end manner. A key challenge in this context is effectively modeling the spatiotemporal interactions between vehicles. In this paper, we propose a multi-scale spatiotemporal Transformer network that extracts multi-scale features from images and aligns them using a dedicated feature alignment module. We develop a divided space-time attention mechanism to capture spatiotemporal dependencies in the feature sequence. Extensive experiments on the nuScenes dataset demonstrate that the proposed framework achieves superior prediction accuracy compared to prior methods, with further performance gains as more historical information is incorporated. © 2025 IEEE.
Keyword ：
Autonomous vehicles Autonomous vehicles Behavioral research Behavioral research Forecasting Forecasting Intelligent systems Intelligent systems Intelligent vehicle highway systems Intelligent vehicle highway systems
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Han, Haoxuan , Zheng, Haifeng , Feng, Xinxin . Multi-Scale Spatiotemporal Transformer Networks for Trajectory Prediction of Autonomous Driving [C] . 2025 : 155-160 . |
| MLA | Han, Haoxuan et al. "Multi-Scale Spatiotemporal Transformer Networks for Trajectory Prediction of Autonomous Driving" . (2025) : 155-160 . |
| APA | Han, Haoxuan , Zheng, Haifeng , Feng, Xinxin . Multi-Scale Spatiotemporal Transformer Networks for Trajectory Prediction of Autonomous Driving . (2025) : 155-160 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multimodal information plays an important role in the advanced Internet of Things (IoT) in the era of 6G, which provides reliable and comprehensive assistance for downstream tasks through further fusion and analysis via federated learning (FL). One of the primary challenges in FL is data heterogeneity, which may lead to domain shifts and sharply different local long-tailed category distribution across nodes. These issues hinder the large-scale deployment of FL in IoT applications equipped with multiple various multimodal sensors due to performance deterioration. In this paper, we propose a novel multimodal fusion framework to tackle the aforementioned coupled problems arising during the cooperative fusion of multimodal information without privacy exposure among decentralized nodes equipped with diverse sensors. Specifically, we introduce a flexible global logit alignment (GLA) method based on multi-view domains. This method enables the fusion of diverse multimodal information with the consideration of domain shifts caused by modality-based data heterogeneity. Furthermore, we propose a novel local angular margin (LAM) scheme, which dynamically adjusts decision boundaries for locally seen categories while preserving global decision boundaries for unseen categories. This effectively mitigates severe model divergence caused by significantly different category distributions. Extensive simulations demonstrate the superiority of the proposed framework, which exhibits significant merits in tackling model degeneration caused by data heterogeneity and enhancing modality-based generalization for heterogeneous scenarios. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Federated learning Federated learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gao, Min , Zheng, Haifeng , Feng, Xinxin et al. Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning [C] . 2025 : 16736-16744 . |
| MLA | Gao, Min et al. "Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning" . (2025) : 16736-16744 . |
| APA | Gao, Min , Zheng, Haifeng , Feng, Xinxin , Tao, Ran . Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning . (2025) : 16736-16744 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
As an advanced spectral imaging technology, hyperspectral has critical applications in remote sensing. Unfortunately, hyperspectral images (HSIs) are frequently contaminated by diverse noise interference during capture. It is desirable to remove these mixed noises and recover clean HSIs accurately. Current approaches struggle to deliver great performance because they fail to effectively utilize the spectral correlations in hyperspectral data. This paper introduces an innovative hyperspectral image denoising algorithm based on the tensorial weighted Schatten-p norm and graph Laplacian regularization named TWSPGLR. Firstly, to improve the accuracy of low-rank tensor recovery, the tensorial weighted Schatten- p norm is introduced to recover clean hyperspectral data. Secondly, we introduce a spectral constraint to enhance restoration accuracy by efficiently exploiting the spectral correlations of hyperspectral data. Finally, experimental results demonstrate the superiority of TWSPGLR compared with the state-of-the-art methods for HSI denoising. © 2025 IEEE.
Keyword ：
Hyperspectral imaging Hyperspectral imaging Image denoising Image denoising Laplace transforms Laplace transforms Recovery Recovery Remote sensing Remote sensing Spectrum analysis Spectrum analysis Tensors Tensors
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Yufang , Feng, Xinxin , Zheng, Haifeng . Hyperspectral Image Denoising Using Tensorial Weighted Schatten-p Norm with Graph Laplacian Regularization [C] . 2025 : 420-425 . |
| MLA | Zhang, Yufang et al. "Hyperspectral Image Denoising Using Tensorial Weighted Schatten-p Norm with Graph Laplacian Regularization" . (2025) : 420-425 . |
| APA | Zhang, Yufang , Feng, Xinxin , Zheng, Haifeng . Hyperspectral Image Denoising Using Tensorial Weighted Schatten-p Norm with Graph Laplacian Regularization . (2025) : 420-425 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, human activity recognition (HAR) has gained significant attention as a research field, leading to the development of diverse technologies driven by its broad range of application scenarios. Radar technology has attracted much attention because of its unique advantages such as not being limited by environmental conditions such as light, shadow, and occlusion. In this article, a continuous HAR system based on multidomain radar data fusion (CMDN) is proposed. Firstly, in order to capture more detailed motion features of the human body, we apply the short-time fractional Fourier transform (STFrFT) to map radar data into the fractional domain, yielding a novel representation of human motion. Secondly, we develop an activity detector based on variable window length short-time average/long-time average (VW-STA/LTA) to accurately identify the start/end points of continuous human actions, addressing the challenge of difficult sequence segmentation in continuous activity recognition tasks. Finally, based on the multi-input multitask (MIMT) recognition network, the features of each domain are processed in parallel, and multiple input representations are fused to obtain the continuous activity classification results with high precision.
Keyword ：
Accuracy Accuracy Doppler radar Doppler radar Feature extraction Feature extraction Fractional Fourier transform (FrFT) Fractional Fourier transform (FrFT) frequency modulated continuous wave (FMCW) radar frequency modulated continuous wave (FMCW) radar human activity recognition (HAR) human activity recognition (HAR) Radar Radar Radar detection Radar detection Radar imaging Radar imaging Radar signal processing Radar signal processing Sensors Sensors Time-frequency analysis Time-frequency analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, Xinxin , Chen, Pengcheng , Weng, Yuxin et al. CMDN: Continuous Human Activity Recognition Based on Multidomain Radar Data Fusion [J]. | IEEE SENSORS JOURNAL , 2025 , 25 (6) : 10432-10443 . |
| MLA | Feng, Xinxin et al. "CMDN: Continuous Human Activity Recognition Based on Multidomain Radar Data Fusion" . | IEEE SENSORS JOURNAL 25 . 6 (2025) : 10432-10443 . |
| APA | Feng, Xinxin , Chen, Pengcheng , Weng, Yuxin , Zheng, Haifeng . CMDN: Continuous Human Activity Recognition Based on Multidomain Radar Data Fusion . | IEEE SENSORS JOURNAL , 2025 , 25 (6) , 10432-10443 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Federated learning (FL) has been extensively studied as a means of ensuring data privacy while cooperatively training a global model across decentralized devices. Among various FL approaches, asynchronous federated learning (AFL) has distinct advantages in overcoming the straggler problem via server-side aggregation as soon as it receives a local model. However, AFL still faces several challenges in large-scale real-world applications, such as stale model problems and modality heterogeneity across geographically distributed and industrial devices with different functions. In this article, we propose a multimodal fusion framework for AFL to address the aforementioned problems. Specifically, a novel multilinear block fusion model is designed to fuse various multimodal information, which serves as an enhancement for perceiving and transmitting the important modality and block during local training. An adaptive aggregation strategy is further developed to fully utilize heterogeneous data by allowing the global model to favor the received local model based on both freshness and the importance of the local data. Extensive simulations with different data distributions demonstrate the superiority of the proposed framework in heterogeneity scenarios, which exhibits significant merits in the improvement of modality-based generalization without sacrificing convergence speed and communication consumption.
Keyword ：
Asynchronous federated learning (AFL) Asynchronous federated learning (AFL) block term (BT) decomposition block term (BT) decomposition multimodal fusion multimodal fusion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gao, Min , Zheng, Haifeng , Du, Mengxuan et al. Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning [J]. | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS , 2024 , 20 (12) : 14083-14093 . |
| MLA | Gao, Min et al. "Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning" . | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 20 . 12 (2024) : 14083-14093 . |
| APA | Gao, Min , Zheng, Haifeng , Du, Mengxuan , Feng, Xinxin . Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning . | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS , 2024 , 20 (12) , 14083-14093 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Predicting traffic flow effectively alleviates congestion. However, traditional methods tend to rely solely on historical traffic flow data, overlooking the correlation between multimodal traffic data, such as speed and occupancy collected by sensors placed on the road. This limitation results in low tolerance for abnormal situations. Moreover, the decentralization of multimodal data on edge devices may pose data anomalies or partial modal missing due to equipment damage or absence. To address these challenges, we propose a Block-Term tensor decomposition-based multimodal data feature fusion algorithm for traffic prediction. This approach enhances the accuracy and robustness of traffic flow prediction by considering correlations between various modal data, such as speed and occupancy rate. In response to the issues of scattered multimodal data anomalies and missing data on edge devices, and to ensure address privacy and security issues, we employ federated learning methods to achieve adaptive extraction and fusion of multi-modal data at the edges. Our method is tested on a real highway dataset, demonstrating superior prediction performance and robustness compared to traditional methods, particularly in the context of data anomalies or missing modalities.
Keyword ：
Federated learning Federated learning Multimodal data Multimodal data Robustness Robustness Tensor decomposition Tensor decomposition Traffic flow Traffic flow
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, Shaofei , Feng, Xinxin , Xu, Lixia et al. BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion considering Anomalies [J]. | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 , 2024 : 462-467 . |
| MLA | Feng, Shaofei et al. "BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion considering Anomalies" . | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 (2024) : 462-467 . |
| APA | Feng, Shaofei , Feng, Xinxin , Xu, Lixia , Zheng, Haifeng . BTD-GTAN: Federated Traffic Flow Prediction with Multimodal Feature Fusion considering Anomalies . | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 , 2024 , 462-467 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Decentralized federated learning (DFL) is a novel distributed machine-learning paradigm where participants collaborate to train machine-learning models without the assistance of the central server. The decentralized framework can effectively overcome the communication bottleneck and single-point-of-failure issues encountered in federated learning (FL). However, most existing DFL methods may ignore the communication resource constraints of the system. This may result in these methods unsuitable for many practical scenarios because the given resource constraints cannot be guaranteed. In this article, we propose a novel DFL, called DFL with adaptive compression ratio (AdapCom-DFL), that can adaptively adjust the compression ratio of transmission data to keep the communication latency within the constraint. Furthermore, we propose a communication network topology pruning approach to reduce communication overhead by pruning poor links with low data rates while ensuring the convergence. Additionally, a power allocation approach is presented to improve the performance by reallocating the power of communication links while complying with the communication energy constraint. Extensive simulation results demonstrate that the proposed AdapCom-DFL with network pruning and power allocation approach achieves better performance and requires less bandwidth under the given resource constraints compared with some existing approaches.
Keyword ：
Decentralized federated learning (DFL) Decentralized federated learning (DFL) network topology pruning network topology pruning power allocation power allocation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Mengxuan , Zheng, Haifeng , Gao, Min et al. Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks [J]. | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (6) : 10739-10753 . |
| MLA | Du, Mengxuan et al. "Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks" . | IEEE INTERNET OF THINGS JOURNAL 11 . 6 (2024) : 10739-10753 . |
| APA | Du, Mengxuan , Zheng, Haifeng , Gao, Min , Feng, Xinxin . Adaptive Decentralized Federated Learning in Resource-Constrained IoT Networks . | IEEE INTERNET OF THINGS JOURNAL , 2024 , 11 (6) , 10739-10753 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Depth information is crucial for an autonomous driving system as it helps the system understand the environment and make decisions. Most deep learning-based depth completion methods are primarily designed for high-resolution lidars (e.g. 64 scanlines). However, when the number of lidar scanlines decreases, such as with 32 scanlines or 16 scanlines lidars, existing solutions may face challenges in reliably predicting dense depth maps. To address this issue, this paper proposes an effective framework based on knowledge distillation, which incorporates mixed-scanline resolution training and feature-level fusion to train a powerful teacher network that dynamically fuses features from high-scanline resolution and low-scanline resolution inputs. By supervising the student network based on the guidance of the teacher network, the knowledge from the multi-scale fusion teacher network is effectively transferred to the low-scanline resolution student network. For the inference process, only the student network is utilized. The proposed framework has been applied to various existing depth completion networks. The experimental results show the effectiveness of the proposed method by using the KITTI dataset, which shows that it can serve as a universal framework for depth completion tasks.
Keyword ：
deep learning deep learning depth completion depth completion knowledge distillation knowledge distillation LIDAR LIDAR multiple sensors multiple sensors
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huang, Junliang , Zheng, Haifeng , Feng, Xinxin . Multi-Scale Distillation for Low Scanline Resolution Depth Completion [J]. | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 , 2024 : 854-859 . |
| MLA | Huang, Junliang et al. "Multi-Scale Distillation for Low Scanline Resolution Depth Completion" . | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 (2024) : 854-859 . |
| APA | Huang, Junliang , Zheng, Haifeng , Feng, Xinxin . Multi-Scale Distillation for Low Scanline Resolution Depth Completion . | 2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024 , 2024 , 854-859 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
