Yan Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yan Song has a total of 153 co-authors. Here are the top co-authors by number of shared publications:
- Guoliang Wei
Business School, University of Shanghai for Science and Technology
13 shared publications Guoliang Wei
12 shared publications- Derui Ding
Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
11 shared publications - Ru Zeng
Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
9 shared publications Ming Li
Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
8 shared publicationsJianhua Wang
Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
7 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (11) , 17350-17361
Gradient-Enhanced Singular Value Shrinkage for Low-Rank Tensor Learning
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (11) , 17350-17361
Gradient-Enhanced Singular Value Shrinkage for Low-Rank Tensor Learning
- 21 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
RMTSFMC: A reverse multi-scale time series forecasting method with Mamba and 1D-CNN
- 21 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
RMTSFMC: A reverse multi-scale time series forecasting method with Mamba and 1D-CNN
- 10 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. PP  (5) , 1-14
Adaptive fuzzy double c-means clustering via knowledge transferring latent factor analysis
Fuzzy c-means clustering for incomplete data has gained special concern, but many results cannot make a delicate imputation and perfect clustering. To this aim, a Nonlinear Representative Non-negative Latent Factor with Knowledge transfer (NRNLF_KT) and Adaptive Fuzzy Double c-means with Sparse Self-representation (AFD_SS) algorithm, namely NA clustering, is developed. The proposed NA algorithm has three remarkable merits: 1) the NRNLF_KT model employs a nonlinear mapping to intentionally relax the non-negativity constraint and constitutes an unconstrained optimization problem; 2) the NRNLF_KT model establishes an auxiliary matrix related to the target matrix but in a different pattern, which contributes greatly to extracting useful knowledge; and 3) the SS technique is introduced to facilitate the simultaneous consideration of global and local information, meanwhile, the particle swarm optimization algorithm is applied to find an appropriate parameter concerning the specific dataset. Finally, experiment results on real-world datasets verify the superiority of the proposed method.
- 10 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. PP  (5) , 1-14
Adaptive fuzzy double c-means clustering via knowledge transferring latent factor analysis
Fuzzy c-means clustering for incomplete data has gained special concern, but many results cannot make a delicate imputation and perfect clustering. To this aim, a Nonlinear Representative Non-negative Latent Factor with Knowledge transfer (NRNLF_KT) and Adaptive Fuzzy Double c-means with Sparse Self-representation (AFD_SS) algorithm, namely NA clustering, is developed. The proposed NA algorithm has three remarkable merits: 1) the NRNLF_KT model employs a nonlinear mapping to intentionally relax the non-negativity constraint and constitutes an unconstrained optimization problem; 2) the NRNLF_KT model establishes an auxiliary matrix related to the target matrix but in a different pattern, which contributes greatly to extracting useful knowledge; and 3) the SS technique is introduced to facilitate the simultaneous consideration of global and local information, meanwhile, the particle swarm optimization algorithm is applied to find an appropriate parameter concerning the specific dataset. Finally, experiment results on real-world datasets verify the superiority of the proposed method.
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (14) , 31612-31624
Robust Model Predictive Control for Polytopic Uncertain Systems With Energy Harvesting Sensors Under Round-Robin Protocol
This paper addresses the robust model predictive control problem for a class of networked control systems with polytopic uncertainties and hard constraints, where the controller design is complicated by the joint presence of an energy harvesting sensor in the forward channel and the round-robin protocol in the backward channel. In such a setting, stochastic transmission behavior caused by random energy availability, together with fixed communication scheduling and immeasurable states, makes it difficult to guarantee recursive feasibility of the online optimization and mean-square stability of the closed-loop system. To capture these features, the mathematical expectation of a quadratic function depending on both the sensor energy level and the transmission order over an infinite horizon is constructed to formulate the optimization problem. In order to cope with the terminal constraint set and the immeasurability of system states, an auxiliary optimization problem with guaranteed solvability is developed by employing inequality analysis and slack-matrix techniques, through which a sub-optimal solution is obtained. Furthermore, sufficient conditions are derived to ensure the recursive feasibility of the proposed algorithm and the mean-square stability of the resulting closed-loop system with and without hard constraints. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed method.
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (14) , 31612-31624
Robust Model Predictive Control for Polytopic Uncertain Systems With Energy Harvesting Sensors Under Round-Robin Protocol
This paper addresses the robust model predictive control problem for a class of networked control systems with polytopic uncertainties and hard constraints, where the controller design is complicated by the joint presence of an energy harvesting sensor in the forward channel and the round-robin protocol in the backward channel. In such a setting, stochastic transmission behavior caused by random energy availability, together with fixed communication scheduling and immeasurable states, makes it difficult to guarantee recursive feasibility of the online optimization and mean-square stability of the closed-loop system. To capture these features, the mathematical expectation of a quadratic function depending on both the sensor energy level and the transmission order over an infinite horizon is constructed to formulate the optimization problem. In order to cope with the terminal constraint set and the immeasurability of system states, an auxiliary optimization problem with guaranteed solvability is developed by employing inequality analysis and slack-matrix techniques, through which a sub-optimal solution is obtained. Furthermore, sufficient conditions are derived to ensure the recursive feasibility of the proposed algorithm and the mean-square stability of the resulting closed-loop system with and without hard constraints. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed method.
- 2 May 2026
- Published by Elsevier in Neural Networks
- Vol. 202, 109054
MB-GLOM: An attentive GLOM with multi-head projection and bottleneck residual
- 2 May 2026
- Published by Elsevier in Neural Networks
- Vol. 202, 109054
MB-GLOM: An attentive GLOM with multi-head projection and bottleneck residual
- 25 April 2026
- Published by Elsevier in ISA Transactions
- Vol. 173, 316-327
N-step model predictive control with persistent bounded disturbances under AF cooperation protocol
- 25 April 2026
- Published by Elsevier in ISA Transactions
- Vol. 173, 316-327
N-step model predictive control with persistent bounded disturbances under AF cooperation protocol
- 24 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-13
SG-HAT: Semantic-Guided Hybrid-Attention Transformer for Unsupervised Video Summarization
Video summarization (VS) aims to generate a representative summary of original video content, thereby promoting research in social behavior prediction and analysis. Most existing approaches analyze social behaviors and thematic content in a video from a purely visual perspective, failing to account for cross-modal thematic consistency. Furthermore, these methods suffer from several limitations in capturing both local and holistic perception and modeling long-range dependencies. Meanwhile, we are motivated to explore the intrinsic thematic consistency across different modalities. We observe a part-to-whole relationship, where the semantics of individual frames constitute the global semantic summary of a video. To quantify this relationship, we design a frame-level semantic-aligned attention (FSA) mechanism inspired by CLIP-style contrastive learning. Based on this, we propose an unsupervised VS method termed the semantic-guided hybrid-attention transformer (SG-HAT). Building upon the SUM-GAN-AAE framework, we replace the traditional LSTM-based architecture with an encoder–decoder Transformer to capture thematic consistency. Specifically, we incorporate FSA into the decoder, enabling both local and holistic perception by measuring the similarity between frame-level and global features. In addition, multihead cross-attention enables effective cross-modal interaction. By adding FSA into the frame selector, we construct a semantically driven GAN training strategy to achieve precise video reconstruction. Furthermore, with the help of vision–language models, we introduce textual information by generating dense captions and text summaries for each video in the TVSum and SumMe datasets. Experimental results on the multimodal summarization task (video-to-video, V2V) and conventional VS benchmarks demonstrate that our proposed SG-HAT achieves competitive performance.
- 24 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP, 1-13
SG-HAT: Semantic-Guided Hybrid-Attention Transformer for Unsupervised Video Summarization
Video summarization (VS) aims to generate a representative summary of original video content, thereby promoting research in social behavior prediction and analysis. Most existing approaches analyze social behaviors and thematic content in a video from a purely visual perspective, failing to account for cross-modal thematic consistency. Furthermore, these methods suffer from several limitations in capturing both local and holistic perception and modeling long-range dependencies. Meanwhile, we are motivated to explore the intrinsic thematic consistency across different modalities. We observe a part-to-whole relationship, where the semantics of individual frames constitute the global semantic summary of a video. To quantify this relationship, we design a frame-level semantic-aligned attention (FSA) mechanism inspired by CLIP-style contrastive learning. Based on this, we propose an unsupervised VS method termed the semantic-guided hybrid-attention transformer (SG-HAT). Building upon the SUM-GAN-AAE framework, we replace the traditional LSTM-based architecture with an encoder–decoder Transformer to capture thematic consistency. Specifically, we incorporate FSA into the decoder, enabling both local and holistic perception by measuring the similarity between frame-level and global features. In addition, multihead cross-attention enables effective cross-modal interaction. By adding FSA into the frame selector, we construct a semantically driven GAN training strategy to achieve precise video reconstruction. Furthermore, with the help of vision–language models, we introduce textual information by generating dense captions and text summaries for each video in the TVSum and SumMe datasets. Experimental results on the multimodal summarization task (video-to-video, V2V) and conventional VS benchmarks demonstrate that our proposed SG-HAT achieves competitive performance.
- 4 April 2026
- Published by Elsevier in ISA Transactions
- Vol. 173, 382-394
Perturbation-based model predictive control for uncertain systems with amplify-and-forward relays
- 4 April 2026
- Published by Elsevier in ISA Transactions
- Vol. 173, 382-394
Perturbation-based model predictive control for uncertain systems with amplify-and-forward relays
- Open Access
- 9 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (2) , 1-20
GAT-NeRF: Geometry-Aware-Transformer-Enhanced Neural Radiance Fields for High-Fidelity 4D Facial Avatars
High-fidelity 4D dynamic facial avatar reconstruction from monocular video is a critical yet challenging task, driven by increasing demands for immersive virtual human applications. While Neural Radiance Fields (NeRF) have advanced scene representation, their capacity to capture high-frequency facial details, such as dynamic wrinkles and subtle textures from information-constrained monocular streams, requires significant enhancement. To tackle this challenge, we propose a novel hybrid NeRF framework, called Geometry-Aware-Transformer-Enhanced NeRF (GAT-NeRF) for high-fidelity and controllable 4D facial avatar reconstruction, which integrates the Transformer mechanism into the NeRF pipeline. GAT-NeRF synergistically combines a coordinate-aligned Multilayer Perceptron (MLP) with a lightweight Transformer module, termed as Geometry-Aware Transformer (GAT) due to its processing of multi-modal inputs containing explicit geometric priors. The GAT module is enabled by fusing multi-modal input features, including 3D spatial coordinates, 3D Morphable Model (3DMM) expression parameters, and learnable latent codes to effectively learn and enhance feature representations pertinent to fine-grained geometry. The Transformer’s effective feature learning capabilities are leveraged to significantly augment the modeling of complex local facial patterns like dynamic wrinkles and acne scars. Comprehensive experiments unequivocally demonstrate GAT-NeRF’s state-of-the-art performance in visual fidelity and high-frequency detail recovery, forging new pathways for creating realistic dynamic digital humans for multimedia applications.
- 9 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (2) , 1-20
Open AccessGAT-NeRF: Geometry-Aware-Transformer-Enhanced Neural Radiance Fields for High-Fidelity 4D Facial Avatars
High-fidelity 4D dynamic facial avatar reconstruction from monocular video is a critical yet challenging task, driven by increasing demands for immersive virtual human applications. While Neural Radiance Fields (NeRF) have advanced scene representation, their capacity to capture high-frequency facial details, such as dynamic wrinkles and subtle textures from information-constrained monocular streams, requires significant enhancement. To tackle this challenge, we propose a novel hybrid NeRF framework, called Geometry-Aware-Transformer-Enhanced NeRF (GAT-NeRF) for high-fidelity and controllable 4D facial avatar reconstruction, which integrates the Transformer mechanism into the NeRF pipeline. GAT-NeRF synergistically combines a coordinate-aligned Multilayer Perceptron (MLP) with a lightweight Transformer module, termed as Geometry-Aware Transformer (GAT) due to its processing of multi-modal inputs containing explicit geometric priors. The GAT module is enabled by fusing multi-modal input features, including 3D spatial coordinates, 3D Morphable Model (3DMM) expression parameters, and learnable latent codes to effectively learn and enhance feature representations pertinent to fine-grained geometry. The Transformer’s effective feature learning capabilities are leveraged to significantly augment the modeling of complex local facial patterns like dynamic wrinkles and acne scars. Comprehensive experiments unequivocally demonstrate GAT-NeRF’s state-of-the-art performance in visual fidelity and high-frequency detail recovery, forging new pathways for creating realistic dynamic digital humans for multimedia applications.
- 21 January 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37  (2) , 25
A general two-stage framework of tensor low-rank representation for enhanced image denoising and clustering
- 21 January 2026
- Published by Springer Nature in Machine Vision and Applications
- Vol. 37  (2) , 25
A general two-stage framework of tensor low-rank representation for enhanced image denoising and clustering