检索结果-内蒙古大学图书馆

AMTrans:Auto-Correlation Multi-Head Attention Transformer for Infrared Spectral Deconvolution

清华大学学报自然科学版（英文版） 2025年第3期30卷 1329-1341页

作者： Lei Gao Liyuan Cui Shuwen Chen Lizhen Deng Xiaokang Wang Xiaohong Yan Hu Zhu College of Electronic and Optical Engineering & College of Flexible Electronics(Future Technology) Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China School of Computer Science and Technology Hainan UniversityHaikou 570228China

Infrared spectroscopy analysis has found widespread applications in various fields due to advancements in technology and industry *** improve the quality and reliability of infrared spectroscopy signals,deconvolution is a crucial preprocessing *** by the transformer model,we propose an Auto-correlation Multi-head attention Transformer(AMTrans)for infrared spectrum sequence *** auto-correlation attention model improves the scaled dot-product attention in the *** utilizes attention mechanism for feature extraction and implements attention computation using the auto-correlation *** auto-correlation attention model is used to exploit the inherent sequence nature of spectral data and to effectively recovery spectra by capturing auto-correlation patterns in the *** proposed model is trained using supervised learning and demonstrates promising results in infrared spectroscopic *** comparing the experiments with other deconvolution techniques,the experimental results show that the method has excellent deconvolution performance and can effectively recover the texture details of the infrared spectrum.

关键词： spectroscopy spectral deconvolution transformer auto-correlation mechanism

来源：评论

学校读者我要写书评

暂无评论

M-RAT: a Multi-grained Retrieval Augmentation Transformer for image Captioning 17th

M-RAT: a Multi-grained Retrieval Augmentation Transformer f...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Song, Jiayan Pan, Renjie Zhou, Jun Yang, Hua Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai200240 China

ISBN: (纸本)9789819609079

Current encoder-decoder methods for image captioning mai-nly consist of an object detection module (two-stage), or rely on big models with large-scale datasets to improve the effectiveness, which leads to increasing computation costs and cannot introduce new external knowledge. In this paper, we propose a novel end-to-end method Multi-grained Retrieval Augmentation Transformer (M-RAT) that innovatively fuses retrieved text derived from a changeable datastore with input visual feature through a Multi-modal Aligned Encoder, and introduce a specialized attention mechanism, Multi-MSA, to exploit both local and global interactions for delicate fine-grained details. Additionally, we enhance the decoder generation ability by employing low-level and high-level fused embeddings. Experiments demonstrate that M-RAT achieves comparable performance to state-of-the-art baselines with remarkable accuracy and details, as well as showing excellent domain adaptability for novel objects. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

IRSEnet: Differentially Private image Generation with Multi-Scale Feature Extraction and Residual Channel Attention 13

IRSEnet: Differentially Private Image Generation with Multi-...

引用

13th International Conference on Intelligent Control and Information processing, ICICIP 2025

作者： Li, Jiahao Wang, Zhongshuai Ghazali, Kamarul Hawari Bin Yan, Suqing Lan, Rushi Sun, Xiyan Luo, Xiaonan Guangxi Key Lab. of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Centre for Advanced Industrial Technology University of Malaysia Pahang Al-Sultan Abdullah Pahang Pekan26600 Malaysia Int. Joint Research Lab. of Spatio-temporal Information and Intelligent Location Services Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9798331516147

Privacy-preserving image generation is particularly crucial in fields like healthcare, where data are both sensitive and limited. However, effective privacy preservation often compromises the visual quality and utility of the generated images due to privacy budget constraints. To address this issue, in this paper, We propose a novel network architecture, IRSEnet, which combines multi-scale feature extraction technology and residual channel attention mechanisms, aiming to enhance the visual quality of generated images and improve the performance of downstream classification tasks under differential privacy. The differential privacy mechanism ensures the security of sensitive data during training, while the multi-scale feature extraction module enhances feature extraction capabilities through parallel convolutional layers at multiple scales. Additionally, the channel attention module dynamically adjusts channel weights to focus on the most discriminative features. Experimental results demonstrate that this model significantly improves the utility of generated images and the accuracy of downstream classification tasks while preserving privacy. Future work will explore the application of this approach on larger datasets and across more diverse tasks. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

IRSEnet: Differentially Private image Generation with Multi-Scale Feature Extraction and Residual Channel Attention

IRSEnet: Differentially Private Image Generation with Multi-...

引用

International Conference on Intelligent Control and Information processing (ICICIP)

作者： Jiahao Li Zhongshuai Wang Kamarul Hawari Bin Ghazali Suqing Yan Rushi Lan Xiyan Sun Xiaonan Luo Guangxi Key Lab. of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China Centre for Advanced Industrial Technology University of Malaysia Pahang Al-Sultan Abdullah Pekan Pahang Malaysia Int. Joint Research Lab. of Spatio-temporal Information and Intelligent Location Services Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

关键词： Training Differential privacy Privacy Visualization Accuracy image synthesis Computational modeling Feature extraction Security Synthetic data

来源：评论

学校读者我要写书评

暂无评论

image super-resolution based on sparse representation and nonlocal regularization

引用

Journal of Computational Information Systems 2014年第5期10卷 2107-2116页

作者： Li, Xin Zhu, Xiuchang Jiangsu Province Key Lab. on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

To solve the super-resolution reconstruction problem for single-frame image, an algorithm based on sparse representation and nonlocal regularization is proposed. By training the joint dictionaries, this algorithm looks for sparse representation in low-resolution dictionary for the input low-resolution image patch, and maps the sparse representation to high-resolution dictionary to construct high-resolution image patch. Then the reconstructed image patch is further regularized by the image's nonlocal self-similarity a priori information. Experimental results show that this algorithm can effectively ensure the quality of the reconstructed image, and greatly reduce the computation time. © 2014 Binary Information Press.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Super-resolution based on two dictionary-pairs

引用

Sensors and Transducers 2013年第10期157卷 289-294页

作者： Li, Xin Zhu, Xiuchang Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

For learning-based super-resolution reconstruction, the selection and training of dictionary play an important role in improving image reconstruction quality. A super-resolution algorithm based on two dictionary-pairs is proposed in this paper. This algorithm selects image's high- and mid-frequency components as the features of high- and low-resolution patches respectively, and gets the first dictionary-pair, i.e. joint-basic high/low-resolution dictionary-pair, by means of joint training. Then it calculates the difference between original high/mid-frequency components and reconstructed high/mid-frequency components with the first dictionary-pair, and composes the second dictionary-pair, i.e. residual high- and low-resolution dictionary-pair. During super-resolution reconstruction, the high-frequency component and residual high-frequency component of low-resolution image are reconstructed respectively with the above two dictionary-pairs. The experiment results show that, the subjective and objective reconstruction quality could be effectively improved by our proposed algorithm. © 2013 IFSA.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fuzzy reasoning based temporal error concealment

Fuzzy reasoning based temporal error concealment

引用

6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

作者： Zhan, Xuefeng Zhu, Xiuchang Nanjing University of Posts and Telecommunications Image Processing and Image Communication Lab. Nanjing China

ISBN: (纸本)9780769537351

A novel temporal error concealment based on fuzzy reasoning is proposed in this paper. On temporal error concealment, motion vector (MV) of the lost block can be selected from candidate MVs. Generally, side match distortion (SMD) which reflects the continuity across the boundary and sum of absolute difference (SAD) which shows the degree of similarity of matching area are two widely used criterions to make the decision. Each criterion describes the status partly. Combining these two measures, a refined measure based on fuzzy reasoning is calculated to balance the effects of SMD and SAD. According to the experimental results, our method can perform better than the others. © 2009 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Adaptive correlation noise model based Wyner-Ziv distributed video coding

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第14期6卷 456-468页

作者： Xiaofei, Hu Xiuchang, Zhu Key Lab of Image Processing and Image Communication College of Geography and Biological Information Nanjing University of Posts and Telecommunications Nanjing 210003 China Key Lab of Image Processing and Image Communication Key Lab ofBroadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing 210003 China

Distributed video coding (DVC) is a novel video coding paradigm. One approach to DVC is Wyner-Ziv distributed video coding. The accuracy of the correlation noise model can influence the performance of the video coder directly. In order to enhance the accuracy of the distribution model, EM algorithm based mixture Laplace-uniform distribution model and basic Laplace-uniform distribution model for DCT alternating current coefficients are established. Then the model is selected adaptively using fuzzy inference. Experimental results suggest that the proposed mixture correlation noise model can describe the heavy tail and sudden change of the noise accurately at high rate and make significant improvement on the coding efficiency compared with the DISCOVER's noise model. Meanwhile, fuzzy inference based adaptive noise model selection method can reduce the operation complexity to some extent, while not influencing rate-distortion performance.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Refined spatial error concealment with directional entropy

Refined spatial error concealment with directional entropy

引用

5th International Conference on Wireless communications, Networking and Mobile Computing, WiCOM 2009

作者： Xuefeng, Zhan Xiuchang, Zhu Image Processing and Image Communication Lab. Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781424436934

A refined error concealment method for intra frame in H.264 is proposed in this work. Directional entropy of neighboring edges is used to classify the content of the lost block. Some techniques aimed to shorten the computation time without degrading quality of reconstructed video are presented to enforce multi-directional interpolation. As for block with high texture, either bilinear or multi-directional interpolation alone is not so well to recover, we integrate the two methods to get the final result. Experimental results demonstrate the efficiency and better performance of proposed method as compared to other interpolation based methods. ©2009 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

SSIM-based content adaptive frame skipping for low bit rate H.264 video coding

SSIM-based content adaptive frame skipping for low bit rate ...

引用

2010 IEEE 12th International Conference on communication Technology, ICCT'2010

作者： Cui, Ziguan Zhu, Xiuchang Image Processing and Image Communication Lab. Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781424468690

Conventional rate control schemes for H.264/AVC video coding usually regulate output bit rate to match channel bandwidth by adjusting quantization parameter at fixed full frame rate, and the passive frame skipping to avoid buffer overflow usually occurs when scene changes or high motions exist in video sequences especially at low bit rate, which degrades spatial-temporal quality and causes jerky effect. In this paper, an active content adaptive frame skipping scheme is proposed instead of passive methods, which skips subjectively trivial frames by structural similarity (SSIM) measurement. The saved bits from skipped frames are allocated to coded key ones to enhance their spatial quality, and the skipped frames are well recovered from adjacent key ones at the decoder side to maintain constant frame rate. Experimental results show that the proposed scheme acquires better and more consistent spatial-temporal quality both in objective (PSNR) and subjective (SSIM) sense with low complexity compared to classic fixed frame rate control methods JVT-G012. © 2010 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：