检索结果-内蒙古大学图书馆

17th International Congress on Image and Signal processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Li, Shihao Liu, Feng Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology Nanjing China

ISBN: (纸本)9798331507398

Open world object detection aims to simulate the human process of recognizing objects in real life scenarios. It can identify categories not introduced during the training phase as unknown during the testing phase and recognize these unknowns in subsequent incremental learning. This capability is beyond the reach of traditional object detection, making it closer to real world human experiences and thus garnering significant attention from researchers. However, existing studies largely focus on generating better pseudo labels to improve the recall rate of unknown objects, which evidently neglects the intrinsic differences between objects and backgrounds. Considering important information such as the visual saliency and edge features of objects in realistic scenes, this paper proposes a novel solution called PEC, which directly extracts objects from their background to detect known and unknown objects more accurately. Comprehensive experiments on the M-OWODB benchmark demonstrate that our method outperforms other current mainstream approaches. © 2024 IEEE.

关键词： edge attention object detection open world unknown object recognition

来源：评论

学校读者我要写书评

暂无评论

DBST:a lightweight block cipher based on dynamic S-box

引用

Frontiers of Computer Science 2023年第3期17卷 177-185页

作者： Liuyan YAN Lang LI Ying GUO College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China

IoT devices have been widely used with the advent of *** devices contain a large amount of private data during *** is primely important for ensuring their ***,we proposed a lightweight block cipher based on dynamic S-box named *** is introduced for devices with limited hardware resources and high throughput *** is a 128-bit block cipher supporting 64-bit key,which is based on a new generalized Feistel variant *** retains the consistency and significantly boosts the diffusion of the traditional Feistel *** SubColumns of round function is implemented by combining bit-slice technology with *** S-box is dynamically associated with the *** has been demonstrated that DBST has a good avalanche effect,low hardware area,and high *** S-box has been proven to have fewer differential features than RECTANGLE *** security analysis of DBST reveals that it can against impossible differential attack,differential attack,linear attack,and other types of attacks.

关键词： internet of things 5G dynamic S-box bit-slice technology lightweight block cipher

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective Computing 2025年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. First, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

SepFE:Separable Fusion Enhanced Network for Retinal Vessel Segmentation

引用

Computer Modeling in Engineering & Sciences 2023年第9期136卷 2465-2485页

作者： Yun Wu Ge Jiao Jiahao Liu College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable ***,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular *** view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional *** complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for *** ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the ***,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct ***,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is *** superiority of SepFE is further demonstrated through comparisons with other advanced methods.

关键词： Retinal vessel segmentation U-Net depth-wise separable convolution feature fusion

来源：评论

学校读者我要写书评

暂无评论

Scene-Adaptive Reference Selection and Inter Prediction for Gaming Video Coding 5

Scene-Adaptive Reference Selection and Inter Prediction for ...

引用

5th International Seminar on Artificial Intelligence, Networking and information technology, AINIT 2024

作者： Lin, Chengda Lin, Simin Fang, Ying Yi, Shiqi Wei, Hongan Xu, Yiwen Fuzhou University Fujian Key Lab For Intelligent Processing and Wireless Transmission of Media Information Fuzhou350108 China

ISBN: (纸本)9798350385557

With the burgeoning growth of the e-sports industry, there has been a rapid proliferation of gaming videos on online platforms. Simultaneously, this surge undoubtedly presents significant challenges to the encoding of game videos. However, the recurring characteristic of gaming videos is not efficiently studied in the current standardization, such as Versatile Video Coding (VVC). Based on these observations, our general framework, utilizing the Structural SIMilarity index metric (SSIM), Hash SIMilarity index metric (HSIM), and Hash Matrix SIMilarity index metric (HMSIM), identifies recurring video clips and adjusts the reference frame of the first frame. Additionally, we analyze recurring patterns in different resolutions and types, proposing our Scene Adaptation (SA) optimization algorithm, which integrates SSIM, HSIM, and HMSIM to adapt to various resolutions and scenes. Experimental results show that the proposed approach can achieve a -4.71 % Bjontegaard Delta Bit Rate (BDBR) and 1.00% Time Save (TS), outperforming the benchmark. © 2024 IEEE.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

The blessing of Depth Anything:An almost unsupervised approach to crop segmentation with depth-informed pseudo labeling

引用

植物表型组学（英文） 2025年第1期7卷 49-65页

作者： Songliang Cao Binghui Xu Wei Zhou Letian Zhou Jiafei Zhang Yuhui Zheng Weijuan Hu Zhiguo Han Hao Lu National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan430074China PhenoTrait Technology Co. Ltd.Beijing100096China MetaPheno Laboratory Shanghai201114China National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan430074China PhenoTrait Technology Co. Ltd.Beijing100096China MetaPheno Laboratory Shanghai201114China SpeCloud Technology Co. Ltd.Sanya572025China State Key Laboratory of Plant Cell and Chromosome Engineering Institute of Genetics and Developmental BiologyChinese Academy of SciencesBeijing100101China

We present Depth-Informed Crop Segmentation(DepthCropSeg),an almost unsupervised crop segmentation approach without manual pixel-level *** segmentation is a fundamental vision task in agriculture,which benefits a number of downstream applications such as crop growth monitoring and yield *** the past decade,image-based crop segmentation approaches have shifted from classic color-based paradigms to recent deep learning-based *** latter,however,rely heavily on large amounts of data with high-quality manual annotation such that considerable human labor and time are *** this work,we leverage Depth Anything V2,a vision foundation model,to produce high-quality pseudo crop masks for training segmentation *** compile a dataset of 17,199 images from six public plant segmentation sources,generating pseudo masks from depth maps after normalization and *** a coarse-to-fine manual screening,1378 images with reliable masks are *** compare four semantic segmentation models and enhance the top-performing one with depth-informed two-stage self-training and depth-informed *** evaluate the feasibility and robustness of DepthCropSeg,we benchmark the segmentation performance on 10 public crop segmentation testing sets and a self-collect dataset covering in-field,laboratory,and unmanned aerial vehicle(UAV)*** results show that our DepthCropSeg approach can achieve crop segmentation performance comparable to the fully supervised model trained with manually annotated data(86.91 vs.87.10).For the first time,we demonstrate almost unsupervised,close-to-full-supervision crop segmentation successfully.

关键词： Crop segmentation Plant phenotyping Depth anything Segment anything Efficient labeling

来源：评论

学校读者我要写书评

暂无评论

TransCGAN-based Parameter Extraction Framework for SAR Image Simulation 2

TransCGAN-based Parameter Extraction Framework for SAR Image...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Deng, Sidan He, Jingfei Mao, Yongfei Zhao, Liangbo Chen, Liang Shi, Hao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Chongqing Innovation Center Chongqing China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Chongqing Innovation Center Beijing China

ISBN: (纸本)9798331515669

Synthetic Aperture Radar (SAR) images have a wide range of applications due to their all-weather and all-day working conditions. However, SAR images with different scenarios and imaging conditions are insufficient or even rare, which is required in specific SAR image tasks. Fortunately, SAR image simulation technology can provide ample simulated images under these conditions at a low cost, addressing the scarcity of specific real SAR data. Accurate parameters are crucial for obtaining high-quality simulated images. However, it is time-consuming and labour-intensive to adjust parameters manually, and it often fails to achieve accurate simulation parameters. To tackle this problem, this paper proposes a TransCGAN-based SAR image simulation method that combines deep learning with traditional methods. By training TransCGAN, a conditional generative adversarial network (CGAN) integrated with Transformer architecture, a mapping between SAR images and simulation parameters is established. This enables the extraction of simulation parameters directly from the real SAR image, guided by the corresponding real SAR image. Ultimately, the parameters are subsequently converted into simulated SAR images via simulation software. Experimental results demonstrate that our TransCGAN-based method can effectively extract accurate simulation parameters from real SAR images, resulting in simulated images holding high similarity to real images. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Graph Classification with Even a Single key Subgraph Per Class 24

Weakly-Supervised Graph Classification with Even a Single Ke...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhang, Lu Zhang, Chenbo Guan, Jihong Zhou, Shuigeng School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Tongji University Department of Computer Science & Technology China

ISBN: (纸本)9798331506681

Traditional graph classification requires large amounts of labeled data, which is expensive and time-consuming to acquire, especially in some special scenarios that domain knowledge is indispensable for labeling graphs. Observing that some key subgraphs can determine the properties of graphs (e.g. the toxicity of drug molecules depend on some toxic functional groups), in this paper we explore to classify graphs using unlabeled graphs plus a small number of key subgraphs for each class, which is called weakly-supervised graph classification. To this end, we develop the WeGraph method, where the graph classifier is trained with subgraph-based self-supervised learning and divergence- minimization based fine-tuning. Moreover, we design a key subgraph extraction algorithm to iteratively extract and update the key subgraphs, which makes the training process a closed loop. We conduct extensive experiments on different types of graph datasets to evaluate the effectiveness of WeGraph. Experimental results show that WeGraph can achieve high performance even when only one key subgraph is provided for each class. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Spatial Modeling and Multi-Scale Attention Aggregation for Semantic Segmentation of Remote Sensing Images 2

Adaptive Spatial Modeling and Multi-Scale Attention Aggregat...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Yang, Wenying Zhang, Yuchuan Jin, Yuxuan Wang, Yupei Chen, Liang Beijing Institute of Technology Chongqing Innovation Center National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Chongqing China Jianghan University School of Artificial Intelligence Wuhan China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Beijing Institute of Technology Chongqing Innovation Center Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

As remote sensing technology advances and high-resolution sensors are deployed, the analysis of high-resolution remote sensing images encounters challenging issues, such as intra-class variability, and inter-class similarity, due to the unobvious appearance and complicated background. The high-resolution remote sensing images pose critical issues for precise semantic segmentation due to these fundamental issues. To this end, we propose an adaptive hierarchical aggregation network. Different from the previous approach of modeling semantic interdependencies solely within a single feature map in the channel dimension, we introduce multi-scale channel-wise feature aggregation to capture global contextual dependencies. Meanwhile, we design an adaptive detail-aware module to model long-range spatial dependencies, adaptively extracting effective details from different levels as compensation. Additionally, this module utilizes depth-wise separable convolution to selectively filter out irrelevant spatial details from lower-level feature maps. The outputs of the two modules are fused layer by layer to achieve refined feature representation, thereby generating precise pixel-level segmentation results. Our experiments are conducted on the Vaihingen dataset and the Potsdam dataset. The experimental results demonstrate that the proposed algorithm surpasses several existing state-of-the-art approaches. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-distilled Dual-Network with Pixel Screening Loss for Blind Image Deblurring 27th

Self-distilled Dual-Network with Pixel Screening Loss for ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Tianyi Tian, Ming Gao, Changxin Sang, Nong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031781247

In the field of image processing, blind image deblurring aims to restore sharp details in images blurred by an unknown convolution kernel. Recent advancements have shown that deep networks can act as effective image generative priors (DIP) for restoring clear images without requiring external datasets. However, the inherent non-uniqueness of solutions in blind image deblurring often leads DIP-based methods to converge on local optima, resulting in over- or under-deblurred images. To overcome this limitation, we propose a novel deblurring framework featuring dual image generators. These generators mutually constrain each other during training, guiding the model towards the optimal solution. Building on our network structure, we employ a self-ensemble and self-distillation strategy to guide network training, further enhancing performance. Additionally, we introduce a novel loss function based on a pixel screening method, which focuses on the important pixels. This loss enables the network to model the blur kernel more accurately and facilitates the restoration of image details. Our experiments demonstrate that our deblurring approach outperforms most existing methods both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Restoration

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：