检索结果-内蒙古大学图书馆

27th International Conference on pattern recognition, ICPR 2024

作者： Tang, Zhenchen Wang, Zichuan Peng, Bo Dong, Jing New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031781247

With the rapid development of generative technologies, AI-Generated Images (AIGIs) have been widely applied in various aspects of daily life. However, due to the immaturity of the technology, the quality of the generated images varies, so it is important to develop quality assessment techniques for the generated images. Although some models have been proposed to assess the quality of generated images, they are inadequate when faced with the ever-increasing and diverse categories of generated images. Consequently, the development of more advanced and effective models for evaluating the quality of generated images is urgently needed. Recent research has explored the significant potential of the visual language model CLIP in image quality assessment, finding that it performs well in evaluating the quality of natural images. However, its application to generated images has not been thoroughly investigated. In this paper, we build on this idea and further explore the potential of CLIP in evaluating the quality of generated images. We design CLIP-AGIQA, a CLIP-based regression model for quality assessment of generated images, leveraging rich visual and textual knowledge encapsulated in CLIP. Particularly, we implement multi-category learnable prompts to fully utilize the textual knowledge in CLIP for quality assessment. Extensive experiments on several generated image quality assessment benchmarks, including AGIQA-3K and AIGCIQA2023, demonstrate that CLIP-AGIQA outperforms existing IQA models, achieving excellent results in evaluating the quality of generated images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Hong-Ou-Mandel interference with absorption and dispersion from rare earth ions 2

Hong-Ou-Mandel interference with absorption and dispersion f...

引用

2nd International Conference on Optical Communication and Optical Information Processing, OCOIP 2024

作者： Li, Wei Wang, Hong-Wei Ding, Chunling Hao, Xiangying Yuan, Chenzhi Jin, Rui-Bo Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan430205 China

ISBN: (数字)9781510688995

ISBN: (纸本)9781510688988

The coherent interactions between photons and rare earth ion ensembles are crucial for quantum storage and quantum information processing. Hong-Ou-Mandel (HOM) interference, a well-known quantum interference phenomenon, has been widely used in precision measurement applications. However, there have been no reports to date on observing coherent interactions between light and ionic ensembles using HOM interferometry. In this study, we experimentally generated entangled photons from two 10-mm-long type-0 phase-matched PPKTP crystals. Then we constructed a HOM interferometer and achieved a HOM dip with a visibility of 82.4% and a width of 152.5 ± 0.2 fs. Finally, we inserted a Nd3+ : YVO4 (rare earth ion) crystal into the optical path and successfully observed the splitting of the HOM dip. This experiment may provide valuable insights into light-matter interactions and could be beneficial for quantum storage applications. © 2025 SPIE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Parameter-Selective Continual Test-Time Adaptation 17th

Parameter-Selective Continual Test-Time Adaptation

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Tian, Jiaxu Lyu, Fan Unmanned System Research Institute Northwestern Polytechnical University Xi’an China New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819609659

Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which contains a student and a teacher model, where the student is updated using the pseudo-labels from the teacher model, and the teacher is then updated by exponential moving average strategy. However, these methods update the MT model indiscriminately on all parameters of the model. That is, some critical parameters involving sharing knowledge across different domains may be erased, intensifying error accumulation and catastrophic forgetting. In this paper, we introduce Parameter-Selective Mean Teacher (PSMT) method, which is capable of effectively updating the critical parameters within the MT network under domain shifts. First, we introduce a selective distillation mechanism in the student model, which utilizes past knowledge to regularize novel knowledge, thereby mitigating the impact of error accumulation. Second, to avoid catastrophic forgetting, in the teacher model, we create a mask through Fisher information to selectively update parameters via exponential moving average, with preservation measures applied to crucial parameters. Extensive experimental results verify that PSMT outperforms state-of-the-art methods across multiple benchmark datasets. Our code is available at https://***/JiaxuTian/PSMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Interaction Confidence Attention for Human–Object Interaction Detection

引用

International Journal of Computer Vision 2025年 1-20页

作者： Zhang, Hong-Bo Lin, Wang-Kai Su, Hang Lei, Qing Liu, Jing-Hua Du, Ji-Xiang Department of Computer Science and Technology Huaqiao University Xiamen361021 China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen361021 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen361021 China Fujian Province University Xiamen361021 China

In human–object interaction (HOI) detection task, ensuring that interactive pairs receive higher attention weights while reducing the weight of non-interaction pairs is imperative for enhancing HOI detection accuracy. Guiding attention learning is also a key aspect of existing transformer-based algorithms. To tackle this challenge, this study proposes a novel approach termed Interaction Confidence Score Learning Attention (ICSLA), which introduces weakening and augmentation operations into the original attention weight calculation and feature extraction processes. In ICSLA, feature learning is coupled with confidence score learning, simultaneously. Leveraging ICSLA, a new and universal decoder is devised, establishing a transformer-based one-stage HOI detection architecture. Experimental results demonstrate the effectiveness of the proposed method in improving HOI detection accuracy, offering valuable insights for further optimization of attention mechanisms. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Augmentation operation Human–object interaction detection Interaction confidence score learning attention Weakening operation

来源：评论

学校读者我要写书评

暂无评论

A temporal-spatial feature coordination network for change detection of VHR images 3

A temporal-spatial feature coordination network for change d...

引用

3rd International Conference on Geographic Information and Remote Sensing Technology, GIRST 2024

作者： Zeng, Yuxian Zhang, Xinxin College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781510689077

Deep learning techniques have significantly improved the accuracy and efficiency of change detection of very high resolution (VHR) images. However, many current models ignore the inherent heterogeneity of bi-temporal remote sensing images, thus making it difficult to distinguish between target changes and background variations. To address this problem, we propose a deep learning (DL) framework, namely temporal-spatial feature coordination network (TSFCN), to improve the accuracy of detection by enhancing the differentiation of change pixel features and improving the extraction and processing of change information. Further comparison and ablation experiments on the SVCD dataset show that the proposed model, compared with other models, improves the F1 scores and IoU by 2.09% and 3.81%, respectively. The results demonstrate that our model can achieve better accuracy and performance improvement. © 2025 SPIE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Adjustable Gating Prompt Transformer for Facial Attribute recognition with Limited Labeled Data 27th

Adjustable Gating Prompt Transformer for Facial Attribute R...

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Ye, Qinxian Chen, Si Wang, Da-Han Jiang, Nanfeng Su, Yanfei Yan, Yan Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Informatics Xiamen University Xiamen361005 China

ISBN: (纸本)9783031781032

Existing supervised facial attribute recognition (FAR) methods that rely on large labeled datasets can pose a challenge in real-world scenarios. In the case of limited labeled data, the current methods that introduce auxiliary tasks with a large number of parameters are not conducive to the embedded applications of FAR. To overcome these challenges, this paper develops an adjustable gating prompt Transformer that can handle the limited labeled FAR task with a small number of training parameters. Specifically, we employ an effective image-guided prompt tuning, where the image-related prompt sequence is first generated by feeding image tokens into an image-guided prompt generation network (IPG-Net). Then, the prompt sequence can learn facial image information and guide the frozen pre-trained Transformer to fine-tune the model. In addition, dynamically adjustable gating is applied to the prompt sequence to adaptively adjust the contribution of the prompts from different encoder layers, which enhances the interaction between the different encoder layers and retains effective feature information during the iterative process. Experimental results on the CelebA and LFWA datasets demonstrate that our method outperforms competitive methods with a very small amount of training parameters when only limited labeled data are used. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Dual-path Interactive U-Net for Unsupervised Hyperspectral Image Super-Resolution

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11751-11766页

作者： Deng, Wenchen Liu, Jianjun Yang, Jinlong Wu, Zebin Xiao, Liang Jiangnan University Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Wuxi214122 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

Combining low-spatial-resolution hyperspectral image (LrHSI) with high-spatial-resolution multispectral image (HrMSI) serves as an effective strategy for enhancing the spatial fidelity of LrHSI. Nevertheless, most existing methods still face challenges in effectively leveraging the complementary information between the two distinct modalities and maintaining internal consistency, leading to suboptimal fusion results. Previous studies have demonstrated that U-shaped networks can capture spatial structural features within images. Inspired by this, we propose a dual-path interactive U-Net architecture to preserve spatial and spectral integrity. Specifically, we use a standard U-Net and a reversed U-Net as the backbone to extract image information and generate abundance maps of the input images. By enabling interaction between the encoders and decoders of both U-Nets, our architecture integrates information across different scales and modes, leading to enhanced fusion results. To further improve the feature extraction capability, we construct a multi-mode decomposition and reconstruction module, which adaptively fuses the features of LrHSI and HrMSI. This module extracts and combines correlations between the images through Canonical Polyadic decomposition and attention mechanism, capturing global features across different modes. Additionally, we design a weight-sharing U-Net that leverages the similarities and differences between two abundance maps, ensuring internal consistency while reducing computational cost. Thorough evaluations conducted using four publicly available datasets, along with one real-world dataset, and under various noise conditions confirm the validity of our proposed model. © 2008-2012 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

EmoFake: An Initial Dataset for Emotion Fake Audio Detection 23rd

EmoFake: An Initial Dataset for Emotion Fake Audio Detectio...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhao, Yan Yi, Jiangyan Tao, Jianhua Wang, Chenglong Dong, Yongfeng School of Artificial Intelligence Hebei University of Technology Tianjin China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (纸本)9789819783663

To enhance the effectiveness of fake audio detection techniques, researchers have developed multiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focus on capturing non-emotional characteristics in speech, such as the identity of the speaker and the authenticity of the content. However, they often overlook changes in the emotional state of the audio, which is another crucial dimension affecting the authenticity of speech. Therefore, this study reports our progress in developing such an emotion fake audio detection dataset involving changing emotion state of the origin audio named EmoFake. The audio samples in EmoFake are generated using open-source emotional voice conversion models, intended to simulate potential emotional tampering scenarios in real-world settings. We conducted a series of benchmark experiments on this dataset, and the results show that even advanced fake audio detection models trained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challenges with EmoFake. The EmoFake is publicly available (https://***/records/10443769) now. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： emotion fake emotion voice conversion fake audio detection dataset

来源：评论

学校读者我要写书评

暂无评论

Automatic Weight Allocation: optimizing remote sensing image retrieval from contrastive learning perspective

引用

Multimedia Systems 2025年第3期31卷 1-19页

作者： Wang, Sijia Ge, Yun Liu, Qiyang Zeng, Yan School of Software Nanchang Hangkong University Nanchang China Jiangxi Province Key Laboratory of Image Processing and Pattern Recognition Nanchang China

Traditional supervised learning methods achieve remarkable performance in high-resolution remote sensing image retrieval, but are limited by the dependence on large-scale annotated images. Contrastive learning can leverage unlabeled images to learn powerful visual features, demonstrating its potential in many unsupervised tasks. Moreover, hash algorithms show significant potential in the field of image retrieval with their advantages in efficiency and storage. Therefore, we propose the Contrastive Hashing Framework based on Automatic Weight Allocation. The framework employs a two-stage training strategy. In the feature learning stage, we propose the Automatic Weighted Contrastive Loss (AWCLoss). It incorporates Gaussian weighting and dynamic adjustment strategies to improve loss functions, enabling them to focus on the distinctiveness and importance of samples. Gaussian weighting assigns different weight values based on the similarity of sample pairs, enhancing the learning of critical sample pairs. Meanwhile, the dynamic adjustment strategy sets a threshold to identify hard negative samples and then adjusts the weight values to weaken the model from being disturbed by hard negative samples. In the hashing learning stage, a hashing layer is added to the end of the network, which converts high-dimensional representations into hash codes. The Quantization loss is introduced to learn the hash codes so that the semantic similarity structure between data can be preserved in hamming space. Additionally, the AWCLoss is utilized to enhance the discriminative power of the hash codes. Extensive experiments on three remotely sensed datasets UCM, AID and NWPU-RESISC45 have demonstrated the significant superiority of our approach in remote sensing image retrieval. Our source code is available at https://***/WANGSJ77/AWCH .

关键词：

来源：评论

学校读者我要写书评

暂无评论

DFL: cross-view cross-layer discriminative feature learning for fine-grained 3D shape classification

引用

Neural Computing and Applications 2025年 1-22页

作者： Jiang, Jinzhe Bai, Jing Ma, Xiangyu The School of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images Processing and Pattern Recognition Laboratory North Minzu University Yinchuan China

Fine-grained 3D shape classification poses challenges in effectively capturing and integrating discriminative features residing in subtle local regions. Previous methods typically extract features independently from individual views of 3D shapes, with a focus on various strategies for fusing these extracted view features. However, this approach neglects interview correlations and potential redundancies among different views. In this study, we introduce $$\hbox {C}^2$$ DFL, which consists of two primary modules: cross-view discriminative feature extraction (CV-DFE) and cross-layer discriminative feature fusion (CL-DFF). CV-DFE integrates discriminative features by merging inputs from multiple views, mitigating limitations associated with isolated feature extraction. CL-DFF dynamically selects key tokens using a transformer model to interactively fuse discriminative features from various levels. Extensive experiments conducted on three categories of the FG3D dataset demonstrate the exceptional efficacy of $$\hbox {C}^2$$ DFL in capturing and integrating discriminative features of 3D shapes. The proposed method achieves state-of-the-art accuracy in fine-grained 3D shape classification (FGSC).

关键词：

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：