NSTL国家科技图书文献中心

1. MMSISP: A Satellite Image Sequence Prediction Network with Multi-factor Decoupling and Multi-modal Fusion NSTL国家科技图书文献中心

Fanbin Mo | Yixiang Huang ... - 《Pattern Recognition,Part XXII》 - International Conference on Pattern Recognition - 2025, - 221～236 - 共16页

摘要： multi-modal fusion mechanisms for the two branches | MMSISP (Multi-Factor Multi-Modal* Satellite Image* | Satellite image sequence prediction is a | branch of spatio-temporal prediction, which holds | considerable potential for practical applications. However

关键词： Satellite image sequence prediction | Spatio-temporal prediction | Multi-modal fusion

2. An efficient multi-modal fusion bird's-eye view 3D object detection algorithm NSTL国家科技图书文献中心

Ke Zheng | Qingxia Li ... - 《Fifth International Conference on Signal Processing and Computer Science (SPCS 2024)》 - International Conference on Signal Processing and Computer Science - 2025, - 134420S.1～134420S.7 - 共7页

摘要： existing multi-modal* fusion perception methods based on* | computing resources, especially in the multi-camera view | address these defects, this paper proposes a novel multi | -modal* bird's-eye view perception algorithm. First* | method for the conversion of multi-view image features

关键词： Autopilot | Multi-modal fusion | Bird's-eye view perception | Index lookup

3. ESM-YOLO: Enhanced Small Target Detection Based on Visible and Infrared Multi-modal Fusion NSTL国家科技图书文献中心

Qianqian Zhang | Linwei Qiu ... - 《Computer Vision - ACCV 2024,Part VI》 - Asian Conference on Computer Vision - 2025, - 206～221 - 共16页

摘要： method, termed ESM-YOLO, which leverages multi-modal | fusion of visible and infrared data to enhance inter | Fusion (BEF) module to extract both shared and unique | Detecting small targets in remote sensing | imagery is frequently impeded by target faintness and

关键词： Multi-modal fusion | Visible light images | Infrared images | Small targets

4. A novel multi-modal fusion method based on uncertainty-guided meta-learning NSTL国家科技图书文献中心

Zhang, Duoyi | Abul Bashar, Md ... - 《Pattern Recognition》 - 2025,158 - 共13页

摘要：Multi-modal data fusion for effective feature | modalities. Existing multi-modal* data fusion methods often* | -Learning Multi-modal* Fusion and Classification (UMLMC) to* | multi-modal feature spaces at both the pre- and post | -fusion* levels by incorporating uncertainty estimates*

关键词： Multi-modal fusion | Neural networks | Feature-level bias | Uncertainty estimation | Meta-learning framework

5. Multi-modal Fusion Based Q-Distribution Prediction for Controlled Nuclear Fusion NSTL国家科技图书文献中心

Shiao Wang | Yifeng Wang ... - 《Advances in Brain Inspired Cognitive Systems,Part I》 - International Conference on Advances in Brain Inspired Cognitive Systems - 2025, - 115～125 - 共11页

摘要： research direction in controlled nuclear fusion, with | fusion methods in computer vision, integrating 2D line | interactive fusion* of bimodal information. Extensive* | Q-distribution prediction is a crucial | deep learning emerging as a key approach to solving

关键词： Q-distribution prediction | Multi-modal fusion | Controlled nuclear fusion

6. Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution NSTL国家科技图书文献中心

Junxiong Lin | Yan Wang ... - 《Computer Vision - ECCV 2024,Part LII》 - European Conference on Computer Vision - 2025, - 363～380 - 共18页

摘要： Adaptive Multi-modal* Fusion of Spatially Variant Kernel* | , we introduce the Adaptive Multi-Modal* Fusion (AMF* | Pre-trained diffusion models utilized for | image generation encapsulate a substantial reservoir | of a priori knowledge pertaining to intricate

关键词： Blind super-Resolution | Diffusion model | Adaptive multi-Modal fusion | Spatially variant kernel refinemen

7. A Cross-Multi-modal Fusion Approach for Enhanced Engagement Recognition NSTL国家科技图书文献中心

Denis Dresvyanskiy | Alexey Karpov ... - 《Speech and Computer,Part II》 - International Conference on Speech and Computer - 2025, - 3～17 - 共15页

摘要： novel cross-multi-modal* fusion approach is applied to* | research proposes a multi-modal* engagement recognition* | demonstrate that the proposed multi-modal* approach achieves* | visual engagement dynamics, the introduced multi-modal | Engagement recognition enables more natural

关键词： Engagement recognition | Affective computing | Face analysis | Body analysis

8. Enhanced Aiot Multi-Modal Fusion for Human Activity Recognition in Ambient Assisted Living Environment NSTL国家科技图书文献中心

Patel, Ankit D. | Jhaveri, Rutvij H.... - 《Software》 - 2025,55(4) - 731～747 - 共17页

摘要： Edge Computing. This work presents a fusion* HAR* | activities.ResultsThe performance of our fusion* approach is evaluated* | . The results demonstrate that the fusion* of LSTM and* | traditional fusion* methods, achieving an accuracy of 98* | models.ConclusionThe fusion* of LSTM and CNN models enables the*

关键词： CNN | deep learning | edge computing | edge devices | human activity recognition | LSTM | multi modal fusion | spatial features | time series analysis | FEATURES

9. Improved Alzheimer's Disease Detection with Dynamic Attention Guided Multi-modal Fusion NSTL国家科技图书文献中心

Arkaprabha Basu | Sourav Raha ... - 《Pattern Recognition,Part XI》 - International Conference on Pattern Recognition - 2025, - 432～446 - 共15页

摘要： Guided Multi-modal* Fusion (DAGMF) approach, broadly* | Attention-induced Multi-modal* Fusion block, which uses the* | Dynamic Attention Multi-modal* Solver block, which models* | iterations. Empirical studies on multi-modal* datasets* | performance than state-of-the-art multi-modal* deep learning*

关键词： Alzheimer's disease | Multi-modality | Attention modules | Neural ODE | Deep learning

10. Pedestrian Facial Attention Detection Using Deep Fusion and Multi-Modal Fusion Classifier NSTL国家科技图书文献中心

Jing Lian | Zhenghao Wang ... - 《IEEE Transactions on Circuits and Systems for Video Technology》 - 2025,35(1) - 967～980 - 共14页

摘要： semantic pose features. Moreover, a multi-modal fusion | framework adopts a deep feature fusion* strategy to achieve* | a deep-level fusion* of visual features and* | Pedestrian facial attention plays an essential | role in autonomous driving scenarios where a vehicle

摘要： multi-modal fusion mechanisms for the two branches | MMSISP (Multi-Factor Multi-Modal* Satellite Image* | Satellite image sequence prediction is a | branch of spatio-temporal prediction, which holds | considerable potential for practical applications. However

关键词： Satellite image sequence prediction | Spatio-temporal prediction | Multi-modal fusion

摘要： existing multi-modal* fusion perception methods based on* | computing resources, especially in the multi-camera view | address these defects, this paper proposes a novel multi | -modal* bird's-eye view perception algorithm. First* | method for the conversion of multi-view image features

关键词： Autopilot | Multi-modal fusion | Bird's-eye view perception | Index lookup

摘要： method, termed ESM-YOLO, which leverages multi-modal | fusion of visible and infrared data to enhance inter | Fusion (BEF) module to extract both shared and unique | Detecting small targets in remote sensing | imagery is frequently impeded by target faintness and

关键词： Multi-modal fusion | Visible light images | Infrared images | Small targets

摘要：Multi-modal data fusion for effective feature | modalities. Existing multi-modal* data fusion methods often* | -Learning Multi-modal* Fusion and Classification (UMLMC) to* | multi-modal feature spaces at both the pre- and post | -fusion* levels by incorporating uncertainty estimates*

关键词： Multi-modal fusion | Neural networks | Feature-level bias | Uncertainty estimation | Meta-learning framework

摘要： research direction in controlled nuclear fusion, with | fusion methods in computer vision, integrating 2D line | interactive fusion* of bimodal information. Extensive* | Q-distribution prediction is a crucial | deep learning emerging as a key approach to solving

关键词： Q-distribution prediction | Multi-modal fusion | Controlled nuclear fusion

摘要： Adaptive Multi-modal* Fusion of Spatially Variant Kernel* | , we introduce the Adaptive Multi-Modal* Fusion (AMF* | Pre-trained diffusion models utilized for | image generation encapsulate a substantial reservoir | of a priori knowledge pertaining to intricate

关键词： Blind super-Resolution | Diffusion model | Adaptive multi-Modal fusion | Spatially variant kernel refinemen

摘要： novel cross-multi-modal* fusion approach is applied to* | research proposes a multi-modal* engagement recognition* | demonstrate that the proposed multi-modal* approach achieves* | visual engagement dynamics, the introduced multi-modal | Engagement recognition enables more natural

关键词： Engagement recognition | Affective computing | Face analysis | Body analysis

关键词： CNN | deep learning | edge computing | edge devices | human activity recognition | LSTM | multi modal fusion | spatial features | time series analysis | FEATURES

关键词： Alzheimer's disease | Multi-modality | Attention modules | Neural ODE | Deep learning

摘要： semantic pose features. Moreover, a multi-modal fusion | framework adopts a deep feature fusion* strategy to achieve* | a deep-level fusion* of visual features and* | Pedestrian facial attention plays an essential | role in autonomous driving scenarios where a vehicle

关键词： Feature extraction | Pedestrians | Visualization | Estimation | Semantics | Adaptation models | Spatial resolution

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： multi-modal fusion mechanisms for the two branches | MMSISP (Multi-Factor Multi-Modal Satellite Image | Satellite image sequence prediction is a | branch of spatio-temporal prediction, which holds | considerable potential for practical applications. However

关键词： Satellite image sequence prediction | Spatio-temporal prediction | Multi-modal fusion

摘要： existing multi-modal fusion perception methods based on | computing resources, especially in the multi-camera view | address these defects, this paper proposes a novel multi | -modal bird's-eye view perception algorithm. First | method for the conversion of multi-view image features

关键词： Autopilot | Multi-modal fusion | Bird's-eye view perception | Index lookup

摘要： method, termed ESM-YOLO, which leverages multi-modal | fusion of visible and infrared data to enhance inter | Fusion (BEF) module to extract both shared and unique | Detecting small targets in remote sensing | imagery is frequently impeded by target faintness and

关键词： Multi-modal fusion | Visible light images | Infrared images | Small targets

摘要：Multi-modal data fusion for effective feature | modalities. Existing multi-modal data fusion methods often | -Learning Multi-modal Fusion and Classification (UMLMC) to | multi-modal feature spaces at both the pre- and post | -fusion levels by incorporating uncertainty estimates

关键词： Multi-modal fusion | Neural networks | Feature-level bias | Uncertainty estimation | Meta-learning framework

摘要： research direction in controlled nuclear fusion, with | fusion methods in computer vision, integrating 2D line | interactive fusion of bimodal information. Extensive | Q-distribution prediction is a crucial | deep learning emerging as a key approach to solving

关键词： Q-distribution prediction | Multi-modal fusion | Controlled nuclear fusion

摘要： Adaptive Multi-modal Fusion of Spatially Variant Kernel | , we introduce the Adaptive Multi-Modal Fusion (AMF | Pre-trained diffusion models utilized for | image generation encapsulate a substantial reservoir | of a priori knowledge pertaining to intricate

关键词： Blind super-Resolution | Diffusion model | Adaptive multi-Modal fusion | Spatially variant kernel refinemen

摘要： novel cross-multi-modal fusion approach is applied to | research proposes a multi-modal engagement recognition | demonstrate that the proposed multi-modal approach achieves | visual engagement dynamics, the introduced multi-modal | Engagement recognition enables more natural

关键词： Engagement recognition | Affective computing | Face analysis | Body analysis

关键词： CNN | deep learning | edge computing | edge devices | human activity recognition | LSTM | multi modal fusion | spatial features | time series analysis | FEATURES

摘要： Guided Multi-modal Fusion (DAGMF) approach, broadly | Attention-induced Multi-modal Fusion block, which uses the | Dynamic Attention Multi-modal Solver block, which models | iterations. Empirical studies on multi-modal datasets | performance than state-of-the-art multi-modal deep learning

关键词： Alzheimer's disease | Multi-modality | Attention modules | Neural ODE | Deep learning

摘要： semantic pose features. Moreover, a multi-modal fusion | framework adopts a deep feature fusion strategy to achieve | a deep-level fusion of visual features and | Pedestrian facial attention plays an essential | role in autonomous driving scenarios where a vehicle

关键词： Feature extraction | Pedestrians | Visualization | Estimation | Semantics | Adaptation models | Spatial resolution

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： multi-modal fusion mechanisms for the two branches | MMSISP (Multi-Factor Multi-Modal* Satellite Image* | Satellite image sequence prediction is a | branch of spatio-temporal prediction, which holds | considerable potential for practical applications. However

摘要： existing multi-modal* fusion perception methods based on* | computing resources, especially in the multi-camera view | address these defects, this paper proposes a novel multi | -modal* bird's-eye view perception algorithm. First* | method for the conversion of multi-view image features

摘要：Multi-modal data fusion for effective feature | modalities. Existing multi-modal* data fusion methods often* | -Learning Multi-modal* Fusion and Classification (UMLMC) to* | multi-modal feature spaces at both the pre- and post | -fusion* levels by incorporating uncertainty estimates*

摘要： research direction in controlled nuclear fusion, with | fusion methods in computer vision, integrating 2D line | interactive fusion* of bimodal information. Extensive* | Q-distribution prediction is a crucial | deep learning emerging as a key approach to solving

摘要： Adaptive Multi-modal* Fusion of Spatially Variant Kernel* | , we introduce the Adaptive Multi-Modal* Fusion (AMF* | Pre-trained diffusion models utilized for | image generation encapsulate a substantial reservoir | of a priori knowledge pertaining to intricate

摘要： novel cross-multi-modal* fusion approach is applied to* | research proposes a multi-modal* engagement recognition* | demonstrate that the proposed multi-modal* approach achieves* | visual engagement dynamics, the introduced multi-modal | Engagement recognition enables more natural

摘要： semantic pose features. Moreover, a multi-modal fusion | framework adopts a deep feature fusion* strategy to achieve* | a deep-level fusion* of visual features and* | Pedestrian facial attention plays an essential | role in autonomous driving scenarios where a vehicle