Yun Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yun Song has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Fei Yu
School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha 410114, China
6 shared publications - Shuo Cai
School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, China
6 shared publications - Dengyong Zhang
Changsha University of Science and Technology
4 shared publications - Li Liu
School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China
4 shared publications - Miaohui Wang
Shenzhen University
4 shared publications - Zelin Deng
School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, China
4 shared publications
Latest Publications
- 17 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109263
Unsupervised visible-infrared person re-identification via locally reliable matching and global distribution alignment
- 17 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109263
Unsupervised visible-infrared person re-identification via locally reliable matching and global distribution alignment
- 3 February 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (2) , 136
Channel-level feature selection and fusion network for visible-infrared person re-identification
- 3 February 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (2) , 136
Channel-level feature selection and fusion network for visible-infrared person re-identification
- Open Access
- 6 November 2025
- Published by Springer Nature in Research Square
Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification
Visible-infrared person re-identification aims to identify person images between infrared and visible cameras. Existing methods generally embed shared features and specific features into the same space directly, which may impair the high discriminative features and therefore limit the recognition accuracy. To address this issue, this paper proposes a channel-level feature selection and fusion network (CFSFNet), in which the contributions of features are evaluated at the channel level for weighted fusion to enhance the discriminability of the features. The proposed CFSFNet consists of three main components including a feature extraction module (FEM), a feature selection module (FSM), and a channel-level feature fusion module (CFFM). Modality-shared and modality-specific features are first extracted by different multi-channel feature extractors in the FEM. The contributions of different features to identification are then evaluated at the channel level in the FSM. According to their contributions, modality-shared and modality-specific features are combined on selected high-response channels by a dual-channel-attention mean-weighted fusion in the CFFM. Through the collaboration between the CFFM and the FSM, the proposed method not only exploits both modality-shared properties and modality-specific characteristics but enhances the high discriminative features. Moreover, a novel tri-directional center triplet loss is proposed to combine with other loss constraints to guide the model to tighten the intra-class individuals and widen the inter-class gaps. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the superiority of the proposed method over state-of-the-art methods. Ablation studies also illustrate the effectiveness of each component of the proposed network. The source code of this work is publicly available at https://github.com/CV-ReID/CFSFNet.
- 6 November 2025
- Published by Springer Nature in Research Square
Open AccessChannel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification
Visible-infrared person re-identification aims to identify person images between infrared and visible cameras. Existing methods generally embed shared features and specific features into the same space directly, which may impair the high discriminative features and therefore limit the recognition accuracy. To address this issue, this paper proposes a channel-level feature selection and fusion network (CFSFNet), in which the contributions of features are evaluated at the channel level for weighted fusion to enhance the discriminability of the features. The proposed CFSFNet consists of three main components including a feature extraction module (FEM), a feature selection module (FSM), and a channel-level feature fusion module (CFFM). Modality-shared and modality-specific features are first extracted by different multi-channel feature extractors in the FEM. The contributions of different features to identification are then evaluated at the channel level in the FSM. According to their contributions, modality-shared and modality-specific features are combined on selected high-response channels by a dual-channel-attention mean-weighted fusion in the CFFM. Through the collaboration between the CFFM and the FSM, the proposed method not only exploits both modality-shared properties and modality-specific characteristics but enhances the high discriminative features. Moreover, a novel tri-directional center triplet loss is proposed to combine with other loss constraints to guide the model to tighten the intra-class individuals and widen the inter-class gaps. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the superiority of the proposed method over state-of-the-art methods. Ablation studies also illustrate the effectiveness of each component of the proposed network. The source code of this work is publicly available at https://github.com/CV-ReID/CFSFNet.
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 11232-11245
IEIRNet: Inconsistency Exploiting Based Identity Rectification for Face Forgery Detection
Face forgery detection has attracted much attention due to the ever-increasing social concerns caused by facial manipulation techniques. Recently, identity-based detection methods have made considerable progress, which is especially suitable in the celebrity protection scenario. However, they still suffer from two main limitations: (a) generic identity extractor is not specifically designed for forgery detection, leading to nonnegligible Identity Representation Bias to forged images. (b) existing methods only analyze the identity representation of each image individually, but ignores the query-reference interaction for inconsistency exploiting. To address these issues, a novel Inconsistency Exploiting based Identity Rectification Network (IEIRNet) is proposed in this paper. Firstly, for the identity bias rectification, the IEIRNet follows an effective two-branches structure. Besides the Generic Identity Extractor (GIE) branch, an essential Bias Diminishing Module (BDM) branch is proposed to eliminate the identity bias through a novel Attention-based Bias Rectification (ABR) component, accordingly acquiring the ultimate discriminative identity representation. Secondly, for query-reference inconsistency exploiting, an Inconsistency Exploiting Module (IEM) is applied in IEIRNet to comprehensively exploit the inconsistency clues from both spatial and channel perspectives. In the spatial aspect, an innovative region-aware kernel is derived to activate the local region inconsistency with deep spatial interaction. Afterward in the channel aspect, a co-attention mechanism is utilized to model the channel interaction meticulously, and accordingly highlight the channel- wise inconsistency with adaptive weight assignment and channel- wise dropout. Our IEIRNet has shown effectiveness and superiority in various generalization and robustness experiments. Specifically, in the challenging DFDCp dataset, IEIRNet achieves the 12.1% and 7.3% advantages compared with binary-based and identity-based methods respectively.
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 11232-11245
IEIRNet: Inconsistency Exploiting Based Identity Rectification for Face Forgery Detection
Face forgery detection has attracted much attention due to the ever-increasing social concerns caused by facial manipulation techniques. Recently, identity-based detection methods have made considerable progress, which is especially suitable in the celebrity protection scenario. However, they still suffer from two main limitations: (a) generic identity extractor is not specifically designed for forgery detection, leading to nonnegligible Identity Representation Bias to forged images. (b) existing methods only analyze the identity representation of each image individually, but ignores the query-reference interaction for inconsistency exploiting. To address these issues, a novel Inconsistency Exploiting based Identity Rectification Network (IEIRNet) is proposed in this paper. Firstly, for the identity bias rectification, the IEIRNet follows an effective two-branches structure. Besides the Generic Identity Extractor (GIE) branch, an essential Bias Diminishing Module (BDM) branch is proposed to eliminate the identity bias through a novel Attention-based Bias Rectification (ABR) component, accordingly acquiring the ultimate discriminative identity representation. Secondly, for query-reference inconsistency exploiting, an Inconsistency Exploiting Module (IEM) is applied in IEIRNet to comprehensively exploit the inconsistency clues from both spatial and channel perspectives. In the spatial aspect, an innovative region-aware kernel is derived to activate the local region inconsistency with deep spatial interaction. Afterward in the channel aspect, a co-attention mechanism is utilized to model the channel interaction meticulously, and accordingly highlight the channel- wise inconsistency with adaptive weight assignment and channel- wise dropout. Our IEIRNet has shown effectiveness and superiority in various generalization and robustness experiments. Specifically, in the challenging DFDCp dataset, IEIRNet achieves the 12.1% and 7.3% advantages compared with binary-based and identity-based methods respectively.
- Open Access
- 14 August 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (6) , 8179-8196
TARGCN: temporal attention recurrent graph convolutional neural network for traffic prediction
- 14 August 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (6) , 8179-8196
Open AccessTARGCN: temporal attention recurrent graph convolutional neural network for traffic prediction
- 1 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 959-963
Fast CU Partition for VVC Intra-Frame Coding via Texture Complexity
In versatile video coding (VVC), the quadtree with nested multi-type tree (QTMT) partition module significantly improves encoding performance compared to other coding tools. However, it also introduces notable computational complexity in intra-frame coding, occupying over 90% of the encoding time. This paper presents a fast coding unit (CU) partition method based on texture complexity to achieve a balance between compression efficiency and computational complexity for VVC intra-frame coding. In particular, the texture complexity of CUs is quantitatively measured by the ratio of horizontal to vertical gradient and that of sub-block variances. Firstly, directions with higher texture complexity are identified as unlikely coding modes and eliminated from the candidate set. Next, the subblock variances of binary and ternary partitions are compared to determine a fine-grained CU partition pattern, avoiding unlikely partition modes. Experimental results show that our method is simple but efficient, and achieves higher computation efficiency compared to recent machine learning-based and handcraftedbased methods. The implementation of the proposed method is publicly available at https://github.com/csust-sonie/fastCU.
- 1 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 959-963
Fast CU Partition for VVC Intra-Frame Coding via Texture Complexity
In versatile video coding (VVC), the quadtree with nested multi-type tree (QTMT) partition module significantly improves encoding performance compared to other coding tools. However, it also introduces notable computational complexity in intra-frame coding, occupying over 90% of the encoding time. This paper presents a fast coding unit (CU) partition method based on texture complexity to achieve a balance between compression efficiency and computational complexity for VVC intra-frame coding. In particular, the texture complexity of CUs is quantitatively measured by the ratio of horizontal to vertical gradient and that of sub-block variances. Firstly, directions with higher texture complexity are identified as unlikely coding modes and eliminated from the candidate set. Next, the subblock variances of binary and ternary partitions are compared to determine a fine-grained CU partition pattern, avoiding unlikely partition modes. Experimental results show that our method is simple but efficient, and achieves higher computation efficiency compared to recent machine learning-based and handcraftedbased methods. The implementation of the proposed method is publicly available at https://github.com/csust-sonie/fastCU.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5526-5534
msLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression
LiDAR sensors are widely used in autonomous driving, and the growing storage and transmission demands have made LiDAR point cloud compression (LPCC) a hot research topic. To address the challenges posed by the large-scale and uneven-distribution (spatial and categorical) of LiDAR point data, this paper presents a new multimodal-driven scalable LPCC framework. For the large-scale challenge, we decouple the original LiDAR data into multi-layer point subsets, compress and transmit each layer separately, so as to ensure the reconstruction quality requirement under different scenarios. For the uneven-distribution challenge, we extract, align, and fuse heterologous feature representations, including point modality with position information, depth modality with spatial distance information, and segmentation modality with category information. Extensive experimental results on the benchmark SemanticKITTI database validate that our method outperforms 14 recent representative LPCC methods.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5526-5534
Open AccessmsLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression
LiDAR sensors are widely used in autonomous driving, and the growing storage and transmission demands have made LiDAR point cloud compression (LPCC) a hot research topic. To address the challenges posed by the large-scale and uneven-distribution (spatial and categorical) of LiDAR point data, this paper presents a new multimodal-driven scalable LPCC framework. For the large-scale challenge, we decouple the original LiDAR data into multi-layer point subsets, compress and transmit each layer separately, so as to ensure the reconstruction quality requirement under different scenarios. For the uneven-distribution challenge, we extract, align, and fuse heterologous feature representations, including point modality with position information, depth modality with spatial distance information, and segmentation modality with category information. Extensive experimental results on the benchmark SemanticKITTI database validate that our method outperforms 14 recent representative LPCC methods.
- 10 February 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (7) , 2827-2841
MSSTN: a multi-scale spatio-temporal network for traffic flow prediction
- 10 February 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (7) , 2827-2841
MSSTN: a multi-scale spatio-temporal network for traffic flow prediction
- Open Access
- 6 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2) , 1-19
L 2 BEC 2 : Local Lightweight Bidirectional Encoding and Channel Attention Cascade for Video Frame Interpolation
Video frame interpolation (VFI) is of great importance for many video applications, yet it is still challenging even in the era of deep learning. Some existing VFI models directly exploit existing lightweight network frameworks, thus making synthesized in-between frames blurry and creating artifacts due to imprecise motion representation. The other existing VFI models typically depend on heavy model architectures with a large number of parameters, preventing them from being deployed on small terminals. To address these issues, we propose a local lightweight VFI network ( L 2 BEC 2 ) that leverages bidirectional encoding structure with channel attention cascade. Specifically, we improve visual quality by introducing a forward and backward encoding structure with channel attention cascade to better characterize motion information. Furthermore, we introduce a local lightweight strategy into the state-of-the-art Adaptive Collaboration of Flows (AdaCoF) model to simplify its model parameters. Compared with the original AdaCoF model, the proposed L 2 BEC 2 obtains performance gain at the cost of only one-third of the number of parameters and performs favorably against the state-of-the-art works on public datasets. Our source code is available at https://github.com/Pumpkin123709/LBEC.git .
- 6 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2) , 1-19
Open AccessL 2 BEC 2 : Local Lightweight Bidirectional Encoding and Channel Attention Cascade for Video Frame Interpolation
Video frame interpolation (VFI) is of great importance for many video applications, yet it is still challenging even in the era of deep learning. Some existing VFI models directly exploit existing lightweight network frameworks, thus making synthesized in-between frames blurry and creating artifacts due to imprecise motion representation. The other existing VFI models typically depend on heavy model architectures with a large number of parameters, preventing them from being deployed on small terminals. To address these issues, we propose a local lightweight VFI network ( L 2 BEC 2 ) that leverages bidirectional encoding structure with channel attention cascade. Specifically, we improve visual quality by introducing a forward and backward encoding structure with channel attention cascade to better characterize motion information. Furthermore, we introduce a local lightweight strategy into the state-of-the-art Adaptive Collaboration of Flows (AdaCoF) model to simplify its model parameters. Compared with the original AdaCoF model, the proposed L 2 BEC 2 obtains performance gain at the cost of only one-third of the number of parameters and performs favorably against the state-of-the-art works on public datasets. Our source code is available at https://github.com/Pumpkin123709/LBEC.git .
- 10 October 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (10) , 14859-14877
SRTNet: a spatial and residual based two-stream neural network for deepfakes detection
- 10 October 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (10) , 14859-14877
SRTNet: a spatial and residual based two-stream neural network for deepfakes detection