Keyan Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Keyan Cao has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Xinlei Wang
School of Computer Science and Engineering, Shenyang Jianzhu University, Shenyang 110168, China
7 shared publications - Zhongyang Wang
School of Computer Science and Engineering, Shenyang Jianzhu University, Shenyang, China
7 shared publications Gongjie Meng
Shenyang Jianzhu University
4 shared publicationsHaoli Liu
Shenyang Jianzhu University
3 shared publicationsYefan Liu
Shenyang Jianzhu University
3 shared publicationsGui Li
Shenyang Jianzhu University
2 shared publications
Latest Publications
- 21 October 2026
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 82 (16) , 797
An effective multimodal image inpainting network based on mask-guided multi-scale feature fusion and dynamic weighting strategy
- 21 October 2026
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 82 (16) , 797
An effective multimodal image inpainting network based on mask-guided multi-scale feature fusion and dynamic weighting strategy
- Open Access
Motion-Aware Graph Convolutional Network for Topology-Enhanced Skeleton-Based Action Recognition
Skeleton-based action recognition has achieved significant progress through spatio-temporal graph convolutional networks. However, existing topology-enhanced methods treat all skeletal joints uniformly, failing to emphasize task-relevant joints for coordination-level hand-centric actions. Moreover, the graph topology is defined by fixed spatial proximity or generic channel-wise refinement, ignoring the fact that joints engaged in correlated motion patterns carry stronger discriminative signals. Therefore, we propose a Motion-Aware Spatio-Temporal Graph Convolutional Network (MA-STGCN) with a unified motion-aware framework consisting of two tightly coupled modules. First, a Motion-Aware Joint Attention (MJA) module is proposed, enabling the model to dynamically emphasize joints with salient motion for different action categories. Then, a Motion-Correlated Graph Refinement (MCR) module constructs a sample-specific inter-joint motion correlation matrix and uses it to adaptively refine the graph adjacency, strengthening connections between joints that move in coordinated patterns. Experiments are performed on the NTU RGB+D 60/120 datasets, our method achieves 94.2% and 91.3% accuracy on the bone stream. Comprehensive ablation studies validate the effectiveness of each component.
Open AccessMotion-Aware Graph Convolutional Network for Topology-Enhanced Skeleton-Based Action Recognition
Skeleton-based action recognition has achieved significant progress through spatio-temporal graph convolutional networks. However, existing topology-enhanced methods treat all skeletal joints uniformly, failing to emphasize task-relevant joints for coordination-level hand-centric actions. Moreover, the graph topology is defined by fixed spatial proximity or generic channel-wise refinement, ignoring the fact that joints engaged in correlated motion patterns carry stronger discriminative signals. Therefore, we propose a Motion-Aware Spatio-Temporal Graph Convolutional Network (MA-STGCN) with a unified motion-aware framework consisting of two tightly coupled modules. First, a Motion-Aware Joint Attention (MJA) module is proposed, enabling the model to dynamically emphasize joints with salient motion for different action categories. Then, a Motion-Correlated Graph Refinement (MCR) module constructs a sample-specific inter-joint motion correlation matrix and uses it to adaptively refine the graph adjacency, strengthening connections between joints that move in coordinated patterns. Experiments are performed on the NTU RGB+D 60/120 datasets, our method achieves 94.2% and 91.3% accuracy on the bone stream. Comprehensive ablation studies validate the effectiveness of each component.
- Open Access
- 2 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8732
BPA-STGCN: Body-Part-Aware Spatio-Temporal Graph Convolutional Network for Stable Skeleton-Based Action Recognition
Skeleton-based action recognition via graph convolutional networks (GCNs) has achieved remarkable progress, yet two persistent bottlenecks limit practical deployment: (1) systematic confusion among fine-grained actions that differ primarily in hand or finger movements, which the standard 25-joint skeleton cannot disambiguate; and (2) training instability under small batch sizes caused by BatchNorm (BN) running-statistics pollution, leading to catastrophic accuracy drops during training. In this paper, we propose BPA-STGCN (Body-Part-Aware STGCN), which addresses both challenges through an integrated framework of architectural and training innovations. First, a Partition Attention (PA) module adapting the Squeeze-and-Excitation concept to anatomically defined joint groups that decomposes the 25-joint skeleton into four anatomical partitions and learns sample-specific importance weights for each partition, enabling the model to focus on the most discriminative body region for each action. Then, the information losing global average pooling is replaced by a Temporal Pyramid Pooling (TPP) module adapting the temporal-segment and pyramid-pooling concepts to skeleton feature maps that captures multi-scale temporal dynamics through segmented pooling. Moreover, we design a stability-first training protocol comprising low-momentum BN, Mixup augmentation, gradient clipping, and extended warmup. The experiments are performed on the NTU RGB+D 60 and NTU RGB+D 120 dataset, and BPA-STGCN achieves 93.7% and 90.9% accuracy. Comprehensive ablation studies reveal that the architectural innovations and the stability protocol contribute complementarily, and that BPA-STGCN achieves the best accuracy–stability trade-off among all tested configurations.
- 2 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8732
Open AccessBPA-STGCN: Body-Part-Aware Spatio-Temporal Graph Convolutional Network for Stable Skeleton-Based Action Recognition
Skeleton-based action recognition via graph convolutional networks (GCNs) has achieved remarkable progress, yet two persistent bottlenecks limit practical deployment: (1) systematic confusion among fine-grained actions that differ primarily in hand or finger movements, which the standard 25-joint skeleton cannot disambiguate; and (2) training instability under small batch sizes caused by BatchNorm (BN) running-statistics pollution, leading to catastrophic accuracy drops during training. In this paper, we propose BPA-STGCN (Body-Part-Aware STGCN), which addresses both challenges through an integrated framework of architectural and training innovations. First, a Partition Attention (PA) module adapting the Squeeze-and-Excitation concept to anatomically defined joint groups that decomposes the 25-joint skeleton into four anatomical partitions and learns sample-specific importance weights for each partition, enabling the model to focus on the most discriminative body region for each action. Then, the information losing global average pooling is replaced by a Temporal Pyramid Pooling (TPP) module adapting the temporal-segment and pyramid-pooling concepts to skeleton feature maps that captures multi-scale temporal dynamics through segmented pooling. Moreover, we design a stability-first training protocol comprising low-momentum BN, Mixup augmentation, gradient clipping, and extended warmup. The experiments are performed on the NTU RGB+D 60 and NTU RGB+D 120 dataset, and BPA-STGCN achieves 93.7% and 90.9% accuracy. Comprehensive ablation studies reveal that the architectural innovations and the stability protocol contribute complementarily, and that BPA-STGCN achieves the best accuracy–stability trade-off among all tested configurations.
- 2 July 2026
- Published by Springer Nature
- p. 128-140
FCD-YOLO: An Oriented Object Detector Based on Feature Extraction and Context Enhancement
- 2 July 2026
- Published by Springer Nature
- p. 128-140
FCD-YOLO: An Oriented Object Detector Based on Feature Extraction and Context Enhancement
- 2 July 2026
- Published by Springer Nature
- p. 350-361
CDP-Net: A Cross-Domain Deterministic-Guided Probabilistic Image Denoising Network
- 2 July 2026
- Published by Springer Nature
- p. 350-361
CDP-Net: A Cross-Domain Deterministic-Guided Probabilistic Image Denoising Network
- 30 January 2026
- Published by Springer Nature
- p. 115-129
A Lightweight Pavement Defect Detection Method Based on Multi-branch Attention with Contextual Guidance
- 30 January 2026
- Published by Springer Nature
- p. 115-129
A Lightweight Pavement Defect Detection Method Based on Multi-branch Attention with Contextual Guidance
- Open Access
- 23 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12420
FASwinNet: Frequency-Aware Swin Transformer for Remote Sensing Image Super-Resolution via Enhanced High-Similarity-Pass Attention and Octave Residual Blocks
Remote Sensing Image Super-Resolution (RSISR) plays a vital role in enhancing the spatial details and interpretability of satellite imagery. However, existing methods often struggle to recover fine textures and high-frequency information effectively. In this paper, we propose a frequency-aware super-resolution network for remote sensing images, termed FASwinNet. The network introduces an Enhanced High-Similarity-Pass Attention (EHSPA) module, which improves high-frequency detail modeling through a similarity-aware mechanism guided by edge and positional information. Additionally, we design an Octave-based Residual Attention Block that explicitly separates and optimizes high- and low-frequency features, further enhancing texture reconstruction. Experimental results demonstrate that FASwinNet outperforms state-of-the-art methods in both visual quality and quantitative metrics, achieving the best PSNR and SSIM performance on the AID and UCMerced datasets.
- 23 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12420
Open AccessFASwinNet: Frequency-Aware Swin Transformer for Remote Sensing Image Super-Resolution via Enhanced High-Similarity-Pass Attention and Octave Residual Blocks
Remote Sensing Image Super-Resolution (RSISR) plays a vital role in enhancing the spatial details and interpretability of satellite imagery. However, existing methods often struggle to recover fine textures and high-frequency information effectively. In this paper, we propose a frequency-aware super-resolution network for remote sensing images, termed FASwinNet. The network introduces an Enhanced High-Similarity-Pass Attention (EHSPA) module, which improves high-frequency detail modeling through a similarity-aware mechanism guided by edge and positional information. Additionally, we design an Octave-based Residual Attention Block that explicitly separates and optimizes high- and low-frequency features, further enhancing texture reconstruction. Experimental results demonstrate that FASwinNet outperforms state-of-the-art methods in both visual quality and quantitative metrics, achieving the best PSNR and SSIM performance on the AID and UCMerced datasets.
- Open Access
- 30 October 2025
- Published by MDPI AG in Preprints.org
FASwinNet: Frequency-Aware Swin Transformer for Remote Sensing Image Super-Resolution via Enhanced High-Similarity-Pass Attention and Octave Residual Blocks
Remote Sensing Image Super-Resolution (RSISR) plays a vital role in enhancing the spatial details and interpretability of satellite imagery. However, existing methods often struggle to recover fine textures and high-frequency information effectively. In this paper, we propose a frequency-aware super-resolution network for remote sensing images, termed FASwinNet. The network introduces an Enhanced High-Similarity-Pass Attention (EHSPA) module, which improves high-frequency detail modeling through a similarity-aware mechanism guided by edge and positional information. Additionally, we design an Octave-based Residual Attention Block that explicitly separates and optimizes high and low-frequency features, further enhancing texture reconstruction. Experimental results demonstrate that FASwinNet outperforms state-of-the-art methods in both visual quality and quantitative metrics, achieving the best PSNR and SSIM performance on the AID and UCMerced datasets.
- 30 October 2025
- Published by MDPI AG in Preprints.org
Open AccessFASwinNet: Frequency-Aware Swin Transformer for Remote Sensing Image Super-Resolution via Enhanced High-Similarity-Pass Attention and Octave Residual Blocks
Remote Sensing Image Super-Resolution (RSISR) plays a vital role in enhancing the spatial details and interpretability of satellite imagery. However, existing methods often struggle to recover fine textures and high-frequency information effectively. In this paper, we propose a frequency-aware super-resolution network for remote sensing images, termed FASwinNet. The network introduces an Enhanced High-Similarity-Pass Attention (EHSPA) module, which improves high-frequency detail modeling through a similarity-aware mechanism guided by edge and positional information. Additionally, we design an Octave-based Residual Attention Block that explicitly separates and optimizes high and low-frequency features, further enhancing texture reconstruction. Experimental results demonstrate that FASwinNet outperforms state-of-the-art methods in both visual quality and quantitative metrics, achieving the best PSNR and SSIM performance on the AID and UCMerced datasets.
- Open Access
- 2 November 2023
- Published by Frontiers Media SA in Frontiers in Physiology
- Vol. 14, 1239453
Human behavior recognition based on sparse transformer with channel attention mechanism
Human activity recognition (HAR) has recently become a popular research field in the wearable sensor technology scene. By analyzing the human behavior data, some disease risks or potential health issues can be detected, and patients’ rehabilitation progress can be evaluated. With the excellent performance of Transformer in natural language processing and visual tasks, researchers have begun to focus on its application in time series. The Transformer model models long-term dependencies between sequences through self-attention mechanisms, capturing contextual information over extended periods. In this paper, we propose a hybrid model based on the channel attention mechanism and Transformer model to improve the feature representation ability of sensor-based HAR tasks. Extensive experiments were conducted on three public HAR datasets, and the results show that our network achieved accuracies of 98.10%, 97.21%, and 98.82% on the HARTH, PAMAP2, and UCI-HAR datasets, respectively, The overall performance is at the level of the most advanced methods.
- 2 November 2023
- Published by Frontiers Media SA in Frontiers in Physiology
- Vol. 14, 1239453
Open AccessHuman behavior recognition based on sparse transformer with channel attention mechanism
Human activity recognition (HAR) has recently become a popular research field in the wearable sensor technology scene. By analyzing the human behavior data, some disease risks or potential health issues can be detected, and patients’ rehabilitation progress can be evaluated. With the excellent performance of Transformer in natural language processing and visual tasks, researchers have begun to focus on its application in time series. The Transformer model models long-term dependencies between sequences through self-attention mechanisms, capturing contextual information over extended periods. In this paper, we propose a hybrid model based on the channel attention mechanism and Transformer model to improve the feature representation ability of sensor-based HAR tasks. Extensive experiments were conducted on three public HAR datasets, and the results show that our network achieved accuracies of 98.10%, 97.21%, and 98.82% on the HARTH, PAMAP2, and UCI-HAR datasets, respectively, The overall performance is at the level of the most advanced methods.