检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wan, Zhexiong Fan, Bin Hui, Le Dai, Yuchao Lee, Gim Hee School of Electronics and Information Northwestern Polytechnical University Shaanxi Key Laboratory of Information Acquisition and Processing Shaanxi Xi’an710129 China Department of Computer Science National University of Singapore 117417 Singapore National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing100871 China

Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods based on video frames encounter difficulties in distinguishing whether pixel displacements of an object are caused by camera motion or object motion due to the complexities of accurate image-based motion modeling. Recent advances exploit the motion sensitivity of novel event cameras to counter conventional images’ inadequate motion modeling capabilities, but instead lead to challenges in segmenting pixel-level object masks due to the lack of dense texture structures in events. To address these two limitations imposed by unimodal settings, we propose the first instance-level moving object segmentation framework that integrates complementary texture and motion cues. Our model incorporates implicit cross-modal masked attention augmentation, explicit contrastive feature learning, and flow-guided motion enhancement to exploit dense texture information from a single image and rich motion information from events, respectively. By leveraging the augmented texture and motion features, we separate mask segmentation from motion classification to handle varying numbers of independently moving objects. Through extensive evaluations on multiple datasets, as well as ablation experiments with different input settings and real-time efficiency analysis of the proposed framework, we believe that our first attempt to incorporate image and event data for practical deployment can provide new insights for future work in event-based motion related works. The source code with model training and pre-trained weights is released at https://npucvr. ***/EvInsMOS. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Chinese Sentiment Analysis Model Incorporating Knowledge Graph and Deep Learning

A Chinese Sentiment Analysis Model Incorporating Knowledge G...

引用

2023 7th International Conference on Electrical, Mechanical and computer Engineering (ICEMCE)

作者： Shengping Zhao Jinlong Chen Xingguo Qin School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin Guangxi China

With the rapid growth of social media and e-commerce, users are generating large amounts of textual review data on these platforms. Analyzing and mining these comment data is important for governments, enterprises, and consumers to make decisions. Therefore, sentiment analysis, especially for Chinese comments, has become an area of wide interest in industry and academia. Aiming at the characteristics of Chinese online reviews, this paper applies the techniques of knowledge graph and deep learning around sentence-level sentiment analysis and designs a sentiment analysis model that integrates different information such as sentiment knowledge graph and serialized annotation in a deep learning model to improve the accuracy and effectiveness of sentiment analysis of Chinese online reviews. This is important for improving products and services, understanding user needs, and making more informed business and policy decisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GLFAFormer: DeepFake forgery detection with adaptive feature extract and align

引用

Digital Signal processing: A Review Journal 2025年 165卷

作者： Chen, Long Zhao, Huihuang He, Jiaxin Meng, Weiliang College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

With the rapid development of generative models, there is an increasing demand for universal fake image detectors. In this paper, we investigate the problem of fake image detection for the synthesis of generative models to detect fake images from multiple generative methods. Recent research methods explore the benefits of pre-trained models and mainly adopt a fixed paradigm of training additional classifiers separately, but we find that the fixed paradigm hinders the full learning of forgery features, leading to insufficient representation learning in the detector. The main reason is that the fixed paradigm pays too much attention to global features and neglects local features, which limits the ability of the model to perceive image details and leads to some information loss or confusion. In this regard, based on the pre-trained visual language space, our method introduces two core designs. First, we designed a Deep Window Triple Attention (DWTA) module. A similar dense sliding window strategy is adopted to capture multi-scale local abnormal patterns, and the sensitivity to generated artifacts is enhanced through the triple attention mechanism. Secondly, we proposed a Cross-Space Feature Alignment (CSFA) module. A two-way interactive channel between global features and local features is established, and the alignment loss function is used to achieve semantic alignment of cross-modal feature spaces. The aligned features are adaptively fused through a gating mechanism to obtain the final adaptive forged features. Experiments demonstrate that our method, when trained solely on ProGAN data, achieves superior cross-generator generalization: it attains an average accuracy of 94.7% on unseen GANs and generalizes to unseen diffusion models with 94% accuracy, surpassing existing methods by 2.1%. The source code is available at https://***/long2580h/GLFAFormer. © 2025 Elsevier Inc.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

arXiv

引用

arXiv 2024年

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

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multitask learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-boosted Robust Video Activity Anticipation

arXiv

引用

arXiv 2024年

作者： Qi, Zhaobo Wang, Shuhui Zhang, Weigang Huang, Qingming The School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China

Video activity anticipation aims to predict what will happen in the future, embracing a broad application prospect ranging from robot vision and autonomous driving. Despite the recent progress, the data uncertainty issue, reflected as the content evolution process and dynamic correlation in event labels, has been somehow ignored. This reduces the model generalization ability and deep understanding on video content, leading to serious error accumulation and degraded performance. In this paper, we address the uncertainty learning problem and propose an uncertainty-boosted robust video activity anticipation framework, which generates uncertainty values to indicate the credibility of the anticipation results. The uncertainty value is used to derive a temperature parameter in the softmax function to modulate the predicted target activity distribution. To guarantee the distribution adjustment, we construct a reasonable target activity label representation by incorporating the activity evolution from the temporal class correlation and the semantic relationship. Moreover, we quantify the uncertainty into relative values by comparing the uncertainty among sample pairs and their temporal-lengths. This relative strategy provides a more accessible way in uncertainty modeling than quantifying the absolute uncertainty values on the whole dataset. Experiments on multiple backbones and benchmarks show our framework achieves promising performance and better robustness/interpretability. Source codes are available at https://***/qzhb/UbRV2A. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Survey on Image Object Detection Algorithms Based on Deep Learning 7th

Survey on Image Object Detection Algorithms Based on Deep Le...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Fang, Wei Shen, Liang Chen, Yupeng School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

ISBN: (纸本)9783030786083

With the development of image processing technology, computer vision is becoming more and more popular. In recent years, deep learning has flourished, significant progress has been made in object detection. Especially after the R-CNN framework was proposed, the object detection framework based on deep learning has gradually become the mainstream, which can be divided into two categories: region-based and regression-based. Taking these two types of frameworks as the main body, this paper summarizes the research background and then discusses the object detection algorithms based on candidate regions represented by Faster R-CNN and the algorithms based on regression represented by the YOLO series. According to the development history, this paper summarizes the framework proposed in recent years, compares and analyzes the performance of object detection algorithms on public datasets, and introduces the application scenarios of those algorithms. Finally, this paper discusses the current difficulties and challenges in object detection and looks forward to the future development direction. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Prediction of Drug-Target Interactions Using Molecular Graph and GDNet-DTI Model

Prediction of Drug-Target Interactions Using Molecular Graph...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xu, Shuai Lin, Xiaoli Yu, Haiping Hubei Key Laboratory of Intelligent Information Processing and Realtime Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Inf Ormation Processing and Realtime Industrial System School of Computer Science Huanggang Normal University Wuhan China

ISBN: (纸本)9781665401265

The prediction of drug-target interactions (DTIs) is of great significance to the fields of drug design and drug development. However, traditional biological experiments are time-consuming and cost-effective, which has prompted more people to turn their attention to the use of computers to assist in predicting DTIs. This paper proposes an improved prediction model based on multiple graph representation methods, which is GDNet-DTI that combined GCN and DeepWalk. First, a molecular map with atoms as nodes and chemical bonds as edges is generated using the SMILE sequence of drugs, and then GIN is used to extract the features of molecular map for better obtaining the complex interactions between atoms. For target proteins, the protein sequence is first represented by a word vector, and then the one-dimensional convolution is used to extract features for extracting the different levels of features. Then, based on obtained drug features and target features, a DTI-graph is generated, in which drugs and targets are represented as nodes and interactions are represented as edges. Finally, GDNet-DTI are used to obtain node neighborhood information and graph topology information of the DTI-graph. Compared with other advanced models, the results show that GDNet-DTI combined with multiple graph features can predict DTIs more accurately and effectively with DrugBank and four benchmark datasets. In addition, a case study with COVID-19 data is presented, which shows that the proposed method has the potential to predict the actual DTIs and can contribute to the development of drug discovery. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

1000 FPS HDR Video with a Spike-RGB Hybrid Camera

1000 FPS HDR Video with a Spike-RGB Hybrid Camera

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yakun Chang Chu Zhou Yuchen Hong Liwen Hu Chao Xu Tiejun Huang Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University National Key Laboratory of General AI School of Intelligence Science and Technology Peking University

Capturing high frame rate and high dynamic range (HFR&HDR) color videos in high-speed scenes with conventional frame-based cameras is very challenging. The increasing frame rate is usually guaranteed by using shorter exposure time so that the captured video is severely interfered by noise. Alternating exposures can alleviate the noise issue but sacrifice frame rate due to involving long-exposure frames. The neuromorphic spiking camera records high-speed scenes of high dynamic range without colors using a completely different sensing mechanism and visual representation. We introduce a hybrid camera system composed of a spiking and an alternating-exposure RGB camera to capture HFR&HDR scenes with high fidelity. Our insight is to bring each camera's superiority into full play. The spike frames, with accurate fast motion information encoded, are firstly reconstructed for motion representation, from which the spike-based optical flows guide the recovery of missing temporal information for long-exposure RGB images while retaining their reliable color appearances. With the strong temporal constraint estimated from spike trains, both missing and distorted colors cross RGB frames are recovered to generate time-consistent and HFR color frames. We collect a new Spike-RGB dataset that contains 300 sequences of synthetic data and 20 groups of real-world data to demonstrate 1000 FPS HDR videos outperforming HDR video reconstruction methods and commercial high-speed cameras.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Chinese Summary Generation Based on Pointer key information 5

Research on Chinese Summary Generation Based on Pointer Key ...

引用

5th International Conference on computer information Science and Application technology, CISAT 2022

作者： Huang, Wenming Bu, Xianghui Xiao, Yannan Wen, Yayuan Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin China Guangxi Key Laboratory of Image and Graphics Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9781510660076

Sequence-to-sequence models provide a feasible new approach for generative text summarization, but these models are not able to accurately reproduce factual details and subject information. To address the problem of unconstrained and uncontrollable content generation of generative text summarization models, this paper proposes a generative summarization method KGIT that uses Transformer as a skeleton and incorporates both BERT pre-training model and keyword information. The model uses a comprehensive keyword extraction algorithm, uses two results extracted by LSTM and TextRank as vocabularies respectively, and uses pointers keywords are selected and the extracted keywords are used as the guiding information to generate the summary based on the guiding information. KGIT model can associate the source text and keywords to avoid generating a summary of irrelevant topics. The ROUGE value is used as the evaluation criterion for text summaries, and the summaries generated by the KGIT model can contain more key information and are more accurate and readable when compared with the mainstream summary generation models on the NLPCC2017 Chinese news summary dataset. © 2022 SPIE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation

OCTAMamba: A State-Space Model Approach for Precision OCTA V...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shun Zou Zhuo Zhang Guangwei Gao College of Artificial Intelligence Nanjing Agricultural University Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China College of Computer Science and Technology National University of Defense Technology Changsha China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Optical Coherence Tomography Angiography (OCTA) is a crucial imaging technique for visualizing retinal vasculature and diagnosing eye diseases such as diabetic retinopathy and glaucoma. However, precise segmentation of OCTA vasculature remains challenging due to the multi-scale vessel structures and noise from poor image quality and eye lesions. In this study, we proposed OCTAMamba, a novel U-shaped network based on the Mamba architecture, designed to segment vasculature in OCTA accurately. OCTAMamba integrates a Quad Stream Efficient Mining Embedding Module for local feature extraction, a Multi-Scale Dilated Asymmetric Convolution Module to capture multi-scale vasculature, and a Focused Feature Recalibration Module to filter noise and highlight target areas. Our method achieves efficient global modeling and local feature extraction while maintaining linear complexity, making it suitable for low-computation medical applications. Extensive experiments on the OCTA 3M, OCTA 6M, and ROSSA datasets demonstrated that OCTAMamba outperforms state-of-the-art methods, providing a new reference for efficient OCTA segmentation. Code is available at https://***/zs1314/OCTAMamba

关键词： Optical filters Image segmentation Visualization Convolution Noise Streaming media Feature extraction Retina State-space methods Speech processing

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：