Query：
学者姓名：林丽群
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
由于网络环境的多变性，视频播放过程中容易出现卡顿、比特率波动等情况，严重影响了终端用户的体验质量. 为优化网络资源分配并提升用户观看体验，准确评估视频质量至关重要. 现有的视频质量评价方法主要针对短视频，普遍关注人眼视觉感知特性，较少考虑人类记忆特性对视觉信息的存储和表达能力，以及视觉感知和记忆特性之间的相互作用. 而用户观看长视频的时候，其质量评价需要动态评价，除了考虑感知要素外，还要引入记忆要素.为了更好地衡量长视频的质量评价，本文引入深度网络模型，深入探讨了视频感知和记忆特性对用户观看体验的影响，并基于两者特性提出长视频的动态质量评价模型. 首先，本文设计主观实验，探究在不同视频播放模式下，视觉感知特性和人类记忆特性对用户体验质量的影响，构建了基于用户感知和记忆的视频质量数据库（Video Quality Database with Perception and Memory，PAM-VQD）；其次，基于 PAM-VQD 数据库，采用深度学习的方法，结合视觉注意力机制，提取视频的深层感知特征，以精准评估感知对用户体验质量的影响；最后，将前端网络输出的感知质量分数、播放状态以及自卡顿间隔作为三个特征输入长短期记忆网络，以建立视觉感知和记忆特性之间的时间依赖关系. 实验结果表明，所提出的质量评估模型在不同视频播放模式下均能准确预测用户体验质量，且泛化性能良好.
Keyword ：
体验质量 体验质量 注意力机制 注意力机制 深度学习 深度学习 视觉感知特性 视觉感知特性 记忆效应 记忆效应
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林丽群 , 暨书逸 , 何嘉晨 et al. 基于感知和记忆的视频动态质量评价 [J]. | 电子学报 , 2024 . |
| MLA | 林丽群 et al. "基于感知和记忆的视频动态质量评价" . | 电子学报 (2024) . |
| APA | 林丽群 , 暨书逸 , 何嘉晨 , 赵铁松 , 陈炜玲 , 郭宗明 . 基于感知和记忆的视频动态质量评价 . | 电子学报 , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Face Super-Resolution (FSR) plays a crucial role in enhancing low-resolution face images, which is essential for various face-related tasks. However, FSR may alter individuals’ identities or introduce artifacts that affect recognizability. This problem has not been well assessed by existing Image Quality Assessment (IQA) methods. In this paper, we present both subjective and objective evaluations for FSR-IQA, resulting in a benchmark dataset and a reduced reference quality metrics, respectively. First, we incorporate a novel criterion of identity preservation and recognizability to develop our Face Super-resolution Quality Dataset (FSQD). Second, we analyze the correlation between identity preservation and recognizability, and investigate effective feature extractions for both of them. Third, we propose a training-free IQA framework called Face Identity and Recognizability Evaluation of Super-resolution (FIRES). Experimental results using FSQD demonstrate that FIRES achieves competitive performance. IEEE
Keyword ：
Biometrics Biometrics Face recognition Face recognition face super-resolution face super-resolution Feature extraction Feature extraction identity preservation identity preservation Image quality Image quality Image recognition Image recognition Image reconstruction Image reconstruction Measurement Measurement quality assessment quality assessment recognizability recognizability Superresolution Superresolution
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, W. , Lin, W. , Xu, X. et al. Face Super-Resolution Quality Assessment Based On Identity and Recognizability [J]. | IEEE Transactions on Biometrics, Behavior, and Identity Science , 2024 , 6 (3) : 1-1 . |
| MLA | Chen, W. et al. "Face Super-Resolution Quality Assessment Based On Identity and Recognizability" . | IEEE Transactions on Biometrics, Behavior, and Identity Science 6 . 3 (2024) : 1-1 . |
| APA | Chen, W. , Lin, W. , Xu, X. , Lin, L. , Zhao, T. . Face Super-Resolution Quality Assessment Based On Identity and Recognizability . | IEEE Transactions on Biometrics, Behavior, and Identity Science , 2024 , 6 (3) , 1-1 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Natural video capturing suffers from visual blurriness due to high-motion of cameras or objects. Until now, the video blurriness removal task has been extensively explored for both human vision and machine processing. However, its computational cost is still a critical issue and has not yet been fully addressed. In this paper, we propose a novel Lightweight Video Deblurring (LightViD) method that achieves the top-tier performance with an extremely low parameter size. The proposed LightViD consists of a blur detector and a deblurring network. In particular, the blur detector effectively separate blurriness regions, thus avoid both unnecessary computation and over-enhancement on non-blurriness regions. The deblurring network is designed as a lightweight model. It employs a Spatial Feature Fusion Block (SFFB) to extract hierarchical spatial features, which are further fused by ConvLSTM for effective spatial-temporal feature representation. Comprehensive experiments with quantitative and qualitative comparisons demonstrate the effectiveness of our LightViD method, which achieves competitive performances on GoPro and DVD datasets, with reduced computational costs of 1.63M parameters and 96.8 GMACs. Trained model available: https://github.com/wgp/LightVid. IEEE
Keyword ：
Blur Detection Blur Detection Computational efficiency Computational efficiency Computational modeling Computational modeling Detectors Detectors Feature extraction Feature extraction Image restoration Image restoration Kernel Kernel Spatial-Temporal Feature Fusion Spatial-Temporal Feature Fusion Task analysis Task analysis Video Deblurring Video Deblurring
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, L. , Wei, G. , Liu, K. et al. LightViD: Efficient Video Deblurring with Spatial-Temporal Feature Fusion [J]. | IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 (8) : 1-1 . |
| MLA | Lin, L. et al. "LightViD: Efficient Video Deblurring with Spatial-Temporal Feature Fusion" . | IEEE Transactions on Circuits and Systems for Video Technology 34 . 8 (2024) : 1-1 . |
| APA | Lin, L. , Wei, G. , Liu, K. , Feng, W. , Zhao, T. . LightViD: Efficient Video Deblurring with Spatial-Temporal Feature Fusion . | IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 (8) , 1-1 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Underwater images often suffer from color distortion, blurred details, and low contrast. Therefore, more researchers are exploring underwater image enhancement (UIE) methods. However, UIE models based on deep learning suffer from high computational complexity, thus limiting their integration into underwater devices. In this work, we propose a lightweight UIE network based on knowledge distillation (UKD-Net), which includes a teacher network (T-Net) and a student network (S-Net). T-Net uses our designed multi-scale fusion block and parallel attention block to achieve excellent performance. We utilize knowledge distillation technology to transfer the rich knowledge of the T-Net onto a deployable S-Net. Additionally, S-Net employs blueprint separable convolutions and multistage distillation block to reduce parameter count and computational complexity. Results demonstrate that our UKD-Net successfully achieves a lightweight model design while maintaining superior enhanced performance.
Keyword ：
knowledge distillation knowledge distillation lightweight lightweight underwater image enhancement underwater image enhancement
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Xiaoyan , Cai, Xiaowen , Xue, Ying et al. UKD-Net: efficient image enhancement with knowledge distillation [J]. | JOURNAL OF ELECTRONIC IMAGING , 2024 , 33 (2) . |
| MLA | Zhao, Xiaoyan et al. "UKD-Net: efficient image enhancement with knowledge distillation" . | JOURNAL OF ELECTRONIC IMAGING 33 . 2 (2024) . |
| APA | Zhao, Xiaoyan , Cai, Xiaowen , Xue, Ying , Liao, Yipeng , Lin, Liqun , Zhao, Tiesong . UKD-Net: efficient image enhancement with knowledge distillation . | JOURNAL OF ELECTRONIC IMAGING , 2024 , 33 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对现有去雾方法色彩失真、去雾不彻底、细节丢失等问题,提出一种模块化的端到端的单幅图像深度去雾网络.首先,利用多尺度卷积核对输入有雾图像提取充分的关键特征;其次,构建由残差密集块及上、下采样单元形成的行和列的网格网络结构,行列之间通过一种新颖的注意力机制进行特征融合与提取;最后,由残差密集块和卷积层构成的后处理模块进一步减少去雾图像的残余伪影.定量和定性实验结果表明,所提方法去雾性能优越.
Keyword ：
图像去雾 图像去雾 多尺度 多尺度 密集连接 密集连接 注意力机制 注意力机制 网格网络 网格网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黄小芬 , 林丽群 , 卢宇 . 注意力残差密集网络的单幅图像去雾算法 [J]. | 福建师范大学学报（自然科学版） , 2023 , 39 (1) : 68-74 . |
| MLA | 黄小芬 et al. "注意力残差密集网络的单幅图像去雾算法" . | 福建师范大学学报（自然科学版） 39 . 1 (2023) : 68-74 . |
| APA | 黄小芬 , 林丽群 , 卢宇 . 注意力残差密集网络的单幅图像去雾算法 . | 福建师范大学学报（自然科学版） , 2023 , 39 (1) , 68-74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Compressed videos often exhibit visually annoying artifacts, known as Perceivable Encoding Artifacts (PEAs), which dramatically degrade video visual quality. Subjective and objective measures capable of identifying and quantifying various types of PEAs are critical in improving visual quality. In this letter, we investigate the influence of four spatial PEAs (i.e. blurring, blocking, bleeding, and ringing) and two temporal PEAs (i.e. flickering and floating) on video quality. For spatial artifacts, we propose a visual saliency model with a low computational cost and higher consistency with human visual perception. In terms of temporal artifacts, self-attention based TimeSFormer is improved to detect temporal artifacts. Based on the six types of PEAs, a quality metric called Saliency-Aware Spatio-Temporal Artifacts Measurement (SSTAM) is proposed. Experimental results demonstrate that the proposed method outperforms state-of-the-art metrics. We believe that SSTAM will be beneficial for optimizing video coding techniques.
Keyword ：
compression artifact compression artifact Perceivable Encoding Artifacts (PEAs) Perceivable Encoding Artifacts (PEAs) saliency detection saliency detection Video quality assessment Video quality assessment
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Liqun , Zheng, Yang , Chen, Weiling et al. Saliency-Aware Spatio-Temporal Artifact Detection for Compressed Video Quality Assessment [J]. | IEEE SIGNAL PROCESSING LETTERS , 2023 , 30 : 693-697 . |
| MLA | Lin, Liqun et al. "Saliency-Aware Spatio-Temporal Artifact Detection for Compressed Video Quality Assessment" . | IEEE SIGNAL PROCESSING LETTERS 30 (2023) : 693-697 . |
| APA | Lin, Liqun , Zheng, Yang , Chen, Weiling , Lan, Chengdong , Zhao, Tiesong . Saliency-Aware Spatio-Temporal Artifact Detection for Compressed Video Quality Assessment . | IEEE SIGNAL PROCESSING LETTERS , 2023 , 30 , 693-697 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Video quality assessment is critical in optimizing video coding techniques. However, the state-of-the-art methods have limited performance, which is largely due to the lack of large-scale subjective databases for training. In this work, a semi-automatic labeling method is adopted to build a large-scale compressed video quality database, which allows us to label a large number of compressed videos with manageable human workload. The resulting Compressed Video quality database with Semi-Automatic Ratings (CVSAR), so far the largest of compressed video quality database. We train a no-reference compressed video quality assessment model with a 3D CNN for SpatioTemporal Feature Extraction and Evaluation (STFEE). Experimental results demonstrate that the proposed method outperforms state-of-the-art metrics and achieves promising generalization performance in cross-database tests. The CVSAR database has been made publicly available. It can be accessed at https://github.com/Rocknroll194/CVSAR.
Keyword ：
compressed video compressed video Databases Databases deep network deep network Feature extraction Feature extraction Image coding Image coding Labeling Labeling Quality assessment Quality assessment semi-auto rating semi-auto rating Video coding Video coding Video quality assessment Video quality assessment Videos Videos
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Liqun , Wang, Zheng , He, Jiachen et al. Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2023 , 33 (6) : 2616-2626 . |
| MLA | Lin, Liqun et al. "Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33 . 6 (2023) : 2616-2626 . |
| APA | Lin, Liqun , Wang, Zheng , He, Jiachen , Chen, Weiling , Xu, Yiwen , Zhao, Tiesong . Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2023 , 33 (6) , 2616-2626 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Deep learning has been widely used in single image rain removal and demonstrated favorable universality. However, it is still challenging to remove rain streaks, especially in the nightscape rain map which exists heavy rain and rain streak accumulation. To solve this problem, a single image nightscape rain removal algorithm based on Multi-scale Fusion Residual Network is proposed in this paper. Firstly, based on the motion blur model, evenly distributed rain streaks are generated and the dataset is recon-structed to solve the lack of nightscape rain map datasets. Secondly, according to the characteristics of the night rain map, multi-scale residual blocks are drawn on to reuse and propagate the feature, so as to ex-ploit the rain streaks details representation. Meanwhile, the linear sequential connection structure of multi-scale residual blocks is changed to a u-shaped codec structure, which tackles the problem that features cannot be extracted effectively due to insufficient scale. Finally, the features of different scales are com-bined with the global self-attention mechanism to get different rain streak components, then a cleaner re-stored image is obtained. The quantitative and qualitative results show that, compared to the existing algo-rithms, the proposed algorithm can effectively remove rain streaks while retaining detailed information and ensuring the integrity of image information. © 2023 Computer Society of the Republic of China. All rights reserved.
Keyword ：
Deep learning Deep learning Image fusion Image fusion Rain Rain
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | He, Jia-Chen , Fu, Ming-Jian , Lin, Li-Qun . Multi-scale Fusion Residual Network For Single Image Rain Removal [J]. | Journal of Computers (Taiwan) , 2023 , 34 (2) : 129-140 . |
| MLA | He, Jia-Chen et al. "Multi-scale Fusion Residual Network For Single Image Rain Removal" . | Journal of Computers (Taiwan) 34 . 2 (2023) : 129-140 . |
| APA | He, Jia-Chen , Fu, Ming-Jian , Lin, Li-Qun . Multi-scale Fusion Residual Network For Single Image Rain Removal . | Journal of Computers (Taiwan) , 2023 , 34 (2) , 129-140 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The rate-distortion optimization plays a key role in video coding, which aims to achieve a tradeoff between compression efficiency and video quality distortion. The existing rate-distortion optimization algorithms mainly aim to eliminate time and space redundancy, which ignore subjective perception of video content and result in a large amount of perceptual redundancy in video. To address these issues, a rate distortion algorithm based on visual perception is proposed in this article. Firstly, the Lagrangian multiplier factor is obtained based on the data-driven just noticeable distortion prediction mode, which is more in line with the perception of the human eye. Secondly, the Lagrangian multiplier weight coefficient is based on salient model. Finally, the fusion of two models is applied to rate-distortion optimization, and SW-SSIM is used to evaluate video quality and achieve perceptual video coding optimization. Compared with the third generation audio and video coding standard algorithm, experimental results show that the proposed algorithm reduces bitrate by 12.15% averagely, and the salience weighted-structural similarity index metric increases by 0.004 3. Furthermore, the proposed algorithm reduces the perceptual redundancy in video content, and improves the video perceptual quality and coding performance. © 2022, Science Press. All right reserved.
Keyword ：
Electric distortion Electric distortion Image coding Image coding Lagrange multipliers Lagrange multipliers Redundancy Redundancy Signal distortion Signal distortion Video recording Video recording Video signal processing Video signal processing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wei, Hongan , Liu, Jiaqi , Lin, Liqun et al. A rate-distortion optimization algorithm based on visual perception [J]. | Chinese Journal of Scientific Instrument , 2022 , 43 (5) : 175-182 . |
| MLA | Wei, Hongan et al. "A rate-distortion optimization algorithm based on visual perception" . | Chinese Journal of Scientific Instrument 43 . 5 (2022) : 175-182 . |
| APA | Wei, Hongan , Liu, Jiaqi , Lin, Liqun , Yang, Jing , Chen, Weiling . A rate-distortion optimization algorithm based on visual perception . | Chinese Journal of Scientific Instrument , 2022 , 43 (5) , 175-182 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
率失真优化在视频编码中起着关键作用，其目的是在压缩效率和视频质量失真之间取得平衡。现有的率失真算法主要针对视频中时间和空间冗余的消除，未充分考虑视频内容的主观感知冗余。本文提出了一种基于视觉感知的率失真优化算法，通过数据驱动的JND预测模型推导拉格朗日乘数因子，并使用显著性模型优化拉格朗日乘子权重系数，最终融合应用于率失真优化，并采用SW-SSIM评估视频质量，实现视频编码的感知优化。实验结果表明，与AVS3标准率失真算法相比，本文所提算法平均节省12.15%的码率，SW-SSIM提高了0.004 3,有效降低了视频内容中的感知冗余，提高了视频感知质量和编码性能。
Keyword ：
恰可察觉失真 恰可察觉失真 显著性模型 显著性模型 率失真优化 率失真优化 第三代国家数字音视频编码技术标准 第三代国家数字音视频编码技术标准
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 魏宏安 , 刘嘉棋 , 林丽群 et al. 基于视觉感知的率失真优化算法 [J]. | 仪器仪表学报 , 2022 , 43 (05) : 175-182 . |
| MLA | 魏宏安 et al. "基于视觉感知的率失真优化算法" . | 仪器仪表学报 43 . 05 (2022) : 175-182 . |
| APA | 魏宏安 , 刘嘉棋 , 林丽群 , 杨静 , 陈炜玲 . 基于视觉感知的率失真优化算法 . | 仪器仪表学报 , 2022 , 43 (05) , 175-182 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
