Yongsheng Liang

Prof. Dr. Yongsheng Liang

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 September 2024 in Electronics
Verified
Journal Article
Open access
PDF file
QMQingyu Mao
Qingyu Mao
WZWenzhe Zhai
Wenzhe Zhai
XLXiang Lei
Xiang Lei
WZWang Zenghui
Wang Zenghui
YLYongsheng Liang
Yongsheng Liang
The fusion of multimodal medical images, particularly CT and MRI, is driven by the need to enhance the diagnostic process by providing clinicians with a single, comprehensive image that encapsulates all necessary details. Existing fusion methods often exhibit a bias towards features from one of the source images, making it challenging to simultaneously preserve both structural information and textural details. Designing an effective fusion method that can preserve more discriminative information is therefore crucial. In this work, we propose a Coupled Feature-Learning GAN (CFGAN) to fuse the multimodal medical images into a single informative image. The proposed method establishes an adversarial game between the discriminators and a couple of generators. First, the coupled generators are trained to generate two real-like fused images, which are then used to deceive the two coupled discriminators. Subsequently, the two discriminators are devised to minimize the structural distance to ensure the abundant information in the original source images is well-maintained in the fused image. We further empower the generators to be robust under various scales by constructing a discriminative feature extraction (DFE) block with different dilation rates. Moreover, we introduce a cross-dimension interaction attention (CIA) block to refine the feature representations. The qualitative and quantitative experiments on common benchmarks demonstrate the competitive performance of the CFGAN compared to other state-of-the-art methods.

30 November 2023 in Journal of Real-Time Image Processing
Verified
Journal Article
Closed access
PDF file
JCJiacong Chen
Jiacong Chen
QMQingyu Mao
Qingyu Mao
YBYouneng Bao
Youneng Bao
YHYingcong Huang
Yingcong Huang
FMFanyang Meng
Fanyang Meng
YLYongsheng Liang
Yongsheng Liang

14 January 2026
Verified
Book Chapter
Closed access
PDF file
ZLZiyi Li
Ziyi Li
QMQingyu Mao
Qingyu Mao
SLShuai Liu
Shuai Liu
QLQilei Li
Qilei Li
FMFanyang Meng
Fanyang Meng
YLYongsheng Liang
Yongsheng Liang

7 April 2025 in arXiv
Verified
Preprint
Open access
PDF file
SLShuai Liu
Shuai Liu
QMQingyu Mao
Qingyu Mao
CLChao Li
Chao Li
JCJiacong Chen
Jiacong Chen
FMFanyang Meng
Fanyang Meng
YLYongsheng Liang
Yongsheng Liang
The content and distortion are widely recognized as the two primary factors affecting the visual quality of an image. While existing No-Reference Image Quality Assessment (NR-IQA) methods have modeled these factors, they fail to capture the complex interactions between content and distortions. This shortfall impairs their ability to accurately perceive quality. To confront this, we analyze the key properties required for interaction modeling and propose a robust NR-IQA approach termed CoDI-IQA (Content-Distortion high-order Interaction for NR-IQA), which aggregates local distortion and global content features within a hierarchical interaction framework. Specifically, a Progressive Perception Interaction Module (PPIM) is proposed to explicitly simulate how content and distortions independently and jointly influence image quality. By integrating internal interaction, coarse interaction, and fine interaction, it achieves high-order interaction modeling that allows the model to properly represent the underlying interaction patterns. To ensure sufficient interaction, multiple PPIMs are employed to hierarchically fuse multi-level content and distortion features at different granularities. We also tailor a training strategy suited for CoDI-IQA to maintain interaction stability. Extensive experiments demonstrate that the proposed method notably outperforms the state-of-the-art methods in terms of prediction accuracy, data efficiency, and generalization ability.

13 August 2026 in Electronics
Verified
Journal Article
Open access
PDF file
QMQingyu Mao
Qingyu Mao
JCJiacong Chen
Jiacong Chen
SLShuai Liu
Shuai Liu
FMFanyang Meng
Fanyang Meng
YLYongsheng Liang
Yongsheng Liang
YBYouneng Bao
Youneng Bao
Implicit neural representations (INRs) encode video frames as network weights, offering a new compression paradigm. A persistent limitation is that existing INR codecs train one model per target bitrate, so multi-rate deployment needs separate runs, separate checkpoints, and model reloading, costs that grow with the number of rate points. We propose a Generalized Slimmable Framework that replaces standard layers with width-configurable counterparts in most INR decoders, letting a single checkpoint serve multiple bitrates through nested weight tensors without topology changes. To recover the quality lost in shared-weight training, we introduce Slimmable Conditional Decoder Modulation (SCDM), which blends slimmable expert convolutions via width- and frame-conditioned gating. For encoder-based backbones, encoder output caching separates encoder computation from multi-width training. Across four INR backbones on DAVIS and Bunny, the framework cuts multi-rate storage by about 2.3–2.5×, and SCDM recovers substantial quality at all rate points while surpassing independently trained fixed-width models at narrow widths.

14 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
ZLZiyi Li
Ziyi Li
QMQingyu Mao
Qingyu Mao
SLShuai Liu
Shuai Liu
QLQilei Li
Qilei Li
FMFanyang Meng
Fanyang Meng
YLYongsheng Liang
Yongsheng Liang
Neural Video Representation~(NVR) is a promising paradigm for video compression, showing great potential in improving video storage and transmission efficiency. While recent advances have made efforts in architectural refinements to improve representational capability, these methods typically involve complex designs, which may incur increased computational overhead and lack the flexibility to integrate into other frameworks. Moreover, the inherent limitation in model capacity restricts the expressiveness of NVR networks, resulting in a performance bottleneck. To overcome these limitations, we propose Online-RepNeRV, a NVR framework based on online structural reparameterization. Specifically, we propose a universal reparameterization block named ERB, which incorporates multiple parallel convolutional paths to enhance the model capacity. To mitigate the overhead, an online reparameterization strategy is adopted to dynamically fuse the parameters during training, and the multi-branch structure is equivalently converted into a single-branch structure after training. As a result, the additional computational and parameter complexity is confined to the encoding stage, without affecting the decoding efficiency. Extensive experiments on mainstream video datasets demonstrate that our method achieves an average PSNR gain of 0.37-2.7 dB over baseline methods, while maintaining comparable training time and decoding speed.