检索结果-内蒙古大学图书馆

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yu, Jizhe Liu, Yu Wu, Xiaoshuai Xu, Kaiping Li, Jiangquan DUT School of Software Technology and DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9789819620630

With the development of deep convolutional neural networks (CNNs), salient object detection has become increasingly mature. Existing methods primarily enhance model performance by deepening and widening U-shaped networks. However, these methods typically consider the top-level features of bottom-up processes as global context, which is suboptimal and limited. This limitation arises because existing CNNs do not consider long-range dependencies, focusing more on local convolution operations. Additionally, the implicit interaction between complementary features in the top-down process fails to effectively learn the structural properties and semantic information, and it inevitably introduces significant noise. To address these issues, this paper adopts the idea of attention mechanisms to restore the object integrity in a more explicit manner while avoiding the introduction of irrelevant factors. First, we design a Global Context Enhancement (GCE) module to further enhance object localization and global context modeling by learning the correlations among deep features. Subsequently, an attention-based Pyramid Aggregation Decoder progressively merges multi-level adjacent features by learning their pairwise correspondences, gradually learning local details and global representations. Furthermore, a Noise Filter Block (NF) is integrated into the PAD to suppress background noise interference. Experimental results on five benchmark datasets show that our model performs favorably compared to 15 state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sustainable Teaching and Learning E-learning Model towards Redesigning Transformative Learning Model for Knowledge Sharing & Infrastructure Enhancements Post COVID-19

引用

Recent Patents on engineering 2025年第2期19卷 1-12页

作者： Veeramanickam, M.R.M. Kaur, Gaganpreet Acakpovi, Amevi Vadrevu, Pavan Kumar Ciro, Rodriguez R. Kalpana, A.V. Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Software Engineering Universidad Nacional Mayor de San Marcos Lima Peru Electrical and Electronic Engineering Department Accra Technical University Accra Ghana Andhra Pradesh India Department of Software Engineering Universidad Nacional Mayor de San Marcos UNMSM Lima Peru Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai India

Background: Recently, e-learning has become a very basic, integral part of technology-based learning. Wide trends are increasing day by day because of the demands and its usage based on working remotely due to highly penetrated mobile handheld devices and digital media. The smart campus infrastructure has played a vital role to its full extent towards Z millennium students in the 20th century. The teaching and learning accessibility depends on terms of various cost-based afforda-ble platforms, either with synchronous learning or asynchronous mode of learning. Methods: The current patent research explores the changeling leading to infrastructural reforms as per the need for digital media for e-learning during and after COVID-19 spreads. The perspectives in 2 forms of research study are: 1st working on infrastructural needs and demands for the smart campuses and online learning challenges and 2nd is working on platforms technology utilization for better accessible resources for all learners. This work studied different aspects during and after COVID-19, leading to the importance of uninterrupted internet access, phone, hardware and relia-bility, etc. In this work, the importance of gamification study and flipped classrooms for enhancing learner performance to highly engage them in learning environments focused research model on learner engagement on Gamified perceiving study with Smart PLS-SEM was investigated. Promoting sustainability in its entirety through knowledge transfer and contributions to address various challenges in the redesign of learners' syllabi to meet educational needs, emphasizing online learning to integrate various modes of learner platforms, personalized teaching and learn-ing, peer-to-peer communication for learner enhancement, and student engagement through gami-fication are studied. Results: Learners who are enrolled at the school, college, and university levels of education increased exponentially post-COVID-19. More than 90% responded to sch

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study 31

Do Current Video LLMs Have Strong OCR Abilities? A Prelimina...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Fei, Yulin Gao, Yuhui Xian, Xingyuan Zhang, Xiaojin Wu, Tao Chen, Wei School of Software Engineering Huazhong University of Science and Technology China Information Hub Hongkong University of Science and Technology Guangzhou China

ISBN: (纸本)9798891761964

With the rise of multi-modal large language models, accurately extracting and understanding textual information from video content-referred to as video-based optical character recognition (Video OCR)-has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct sub-tasks: (1) Recognition of text content itself and its basic visual attributes, (2) Semantic and Spatial Comprehension of OCR objects in videos (3) Dynamic Motion detection and Temporal Localization. We developed this benchmark using a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement, balancing efficiency, cost, and data quality. Our resource aims to help advance research in video LLMs and underscores the need for improving OCR ability for video LLMs. The benchmark will be released on https://***/YuHuiGao/***. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Utilizing Ontologies for Combinatorial Testing 18

Utilizing Ontologies for Combinatorial Testing

引用

18th IEEE International Conference on software Testing, Verification and Validation Workshops, ICSTW 2025

作者： Wotawa, Franz Graz University of Technology Institute of Software Engineering and Artificial Intelligence Graz Austria

ISBN: (纸本)9798331534677

Test case generation using combinatorial testing requires an input model comprising parameters and their ranges of possible values, i.e., their domains, which might be appropriate for ordinary applications but not for more sophisticated application domains like autonomous systems. Therefore, we discuss the use of ontologies for modeling and its utilization for combinatorial testing. We focus on ontologies describing the interface between the system under test and its environment, discuss the rationale behind such an approach, and introduce the basic algorithm for mapping ontologies to input models. We further consider modeling challenges and provide some initial modeling principles. © 2025 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Evolution Analysis of Network Attack and Defense Situation Based on Game Theory

引用

Computers, Materials & Continua 2025年第4期83卷 1475-1494页

作者： Haiyan Sun Chenglong Shao Jianwei Zhang Kun Wang Wanwei Huang College of Software Engineering Zhengzhou University of Light IndustryZhengzhou450007China Intelligent Computing Power Research Department Zhengzhou Xinda Advanced Technology Research InstituteZhengzhou450007China

To address the problem that existing studies lack analysis of the relationship between attack-defense game behaviors and situation evolution from the game perspective after constructing an attack-defense model,this paper proposes a network attack-defense game model(ADGM).Firstly,based on the assumption of incomplete information between the two sides of the game,the ADGM model is established,and methods of payoff quantification,equilibrium solution,and determination of strategy confrontation results are ***,drawing on infectious disease dynamics,the network attack-defense situation is defined based on the density of nodes in various security states,and the transition paths of network node security states are ***,the network zero-day virus attack-defense behaviors are analyzed,and comparative experiments on the attack-defense evolution trends under the scenarios of different strategy combinations,interference methods,and initial numbers are conducted using the NetLogo simulation *** experimental results indicate that this model can effectively analyze the evolution of the macro-level network attack-defense situation from the micro-level attack-defense *** instance,in the strategy selection experiment,when the attack success rate decreases from 0.49 to 0.29,the network destruction rate drops by 11.3%,in the active defense experiment,when the interference coefficient is reduced from 1 to 0.7,the network destruction rate decreases by 7%,and in the initial node number experiment,when the number of initially infected nodes increases from 10 to 30,the network destruction rate rises by 3%.

关键词： Network attack-defense situation evolution zero-day virus NetLogo

来源：评论

学校读者我要写书评

暂无评论

Research On Fatigue Driving Detection Based On Deep Learning

引用

engineering Letters 2025年第2期33卷 348-356页

作者： Zhou, Huinan Dai, Hong University of Science and Technology Liaoning Liaoning AnshanCO 114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning AnshanCO 114051 China

Fatigue driving is one of the main causes of traffic accidents. Effective fatigue driving detection technology can reduce traffic accidents caused by fatigue driving. Traditional fatigue driving detection methods usually use a two-stage detection method, which has the problems of low efficiency and poor accuracy. To solve these problems, this paper designs a single-stage fatigue driving detection model based on separable convolution Road Safety Net (RSNet), which extracts the features in the driver's image or video and classifies these features to determine whether the driver is in an abnormal driving state. RSNet borrows the structure of Swin Transformer and adopts a hierarchical design, which makes the model better able to extract features and classify. Each level is composed of a GDS Layer and multiple RS Blocks. To solve the problem of low efficiency of traditional methods, we use separable convolution in RS Block to replace the traditional convolutional neural network, which reduces the complexity of the model and effectively improves the computational efficiency of the model. Experimental results show that the Top-1 and Top-5 Accuracy of RSNet on the HMDB51 dataset reaches 85 % and 97.35 %, respectively, and the delay is 5.97 ms. Compared with ResNet, EfficientNet, and Swin Transformer, RSNet has higher accuracy and efficiency. In addition, this paper takes the YOLACT algorithm as an example, selects different backbone networks for object detection, and compares the indicators of mean Average Precision (mAP) and Frames Per Second (FPS). Experiments show that RSNet performs better when used as the backbone network for object detection, with mAP reaching 32.4 % and FPS of 39.6 ms. It indicates that RSNet performs well in action recognition tasks. © 2025, International Association of Engineers. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Emotion Classification Based on Bilingual Feature Fusion 27th

Improving Chinese Emotion Classification Based on Bilingual...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lan, Haocheng Ou, Jie Wang, Zhaokun Tian, Wenhong School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781186

The growing popularity of Chinese social media platforms such as Sina Weibo has created a large number of user generated text content, which is of great value for understanding public emotions. However, the existence of mixed languages in these texts, especially Chinese and English, and mixed expressions pose a major challenge to current emotion classification methods. To address these issues, we propose a Bilingual Feature Fusion Network (BFFN) that leverages the multilingual capabilities of pre-trained language models to enhance the semantic feature extraction of Chinese text. Additionally, we introduce a Bilingual Cross Attention Mechanism (BCAM) that utilizes emotional features as the primary factor to capture cross-lingual emotional information effectively. Furthermore, we employ a lightweight fine-tuning approach that combines Low-Rank Adaptation (LoRA) and Embedding Fine-tuning (LEF) to reduce the complexity of fine-tuning model weights for downstream tasks. Extensive experiments on various datasets demonstrate the superiority of our proposed method, outperforming state-of-the-art models like ERNIE by 1.43% in accuracy. Our work contributes to the advancement of emotion classification in the context of mixed-language communication culture and provides a practical solution for real-world applications. Our code has been published on the open source community Github (https://***/oujieww/BFFN). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resolution Guidance for Facial Expression Recognition 27th

Dynamic Resolution Guidance for Facial Expression Recogniti...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Songpan Li, Xu School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781247

Facial expression recognition (FER) plays a crucial role in human-computer interaction and emotion analysis. However, recognizing expressions in low-resolution images remains a significant challenge. This paper introduces a practical method called Dynamic Resolution Guidance for Facial Expression Recognition (DRGFER) to effectively recognize facial expressions in images with varying resolutions without compromising the accuracy of the FER model. Our framework comprises two main components: the Resolution Recognition Network (RRN) and the Multi-Resolution Adaptation Facial Expression Recognition Network (MRAFER). The RRN determines the resolution of the input image, and the MRAFER assigns the image to the most suitable facial expression recognition network according to its resolution. We evaluated the performance of DRGFER on two widely used datasets, RAF-DB and FERPlus. The results demonstrate that our method maintains optimal model performance at each resolution and outperforms alternative resolution-handling approaches. The proposed framework exhibits robustness against variations in both resolution and facial expressions, offering a promising solution for real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

EventLens: Enhancing Visual Commonsense Reasoning by Leveraging Event-Aware Pretraining and Cross-modal Linking

EventLens: Enhancing Visual Commonsense Reasoning by Leverag...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Mingjie Yu, Zhihuan Ma, Yichao Li, Guohui Yang, Zhong School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Software Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350368741

Visual Commonsense Reasoning (VCR) is a cognitive task, challenging models to answer visual questions, and to explain the rationale behind their answers. While Large Language Models (LLMs) offer potential for this task, VCR's complex scenes require specialized approaches to activate their commonsense reasoning abilities, as existing Multimodal LLMs struggle with VCR's visual events and unique reference tags. To address these challenges, we propose EventLens, which enhances VCR through Event-Aware Pretraining and Cross-modal Linking in Supervised Fine-tuning. First, we introduce a new pretraining stage that emulates human cognitive processes to improve LLM comprehension of complex scenarios. Second, during supervised fine-tuning, we leverage reference tags to explicitly bridge RoI features with text, maintaining semantic integrity across modalities. Additionally, instruct prompts and task-specific adapters help integrate LLMs' knowledge with new commonsense reasoning. Experimental results demonstrate competitive performance with state-of-the-art methods and ablation studies verify the effectiveness of proposed EventLens. © 2025 IEEE.

关键词： Multimedia Understanding Pretrained Language Models Visual Commonsense Reasoning

来源：评论

学校读者我要写书评

暂无评论

SparseTrack: Multi-Object Tracking by Performing Scene Decomposition Based on Pseudo-Depth

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 4870-4882页

作者： Liu, Zelin Wang, Xinggang Wang, Cheng Liu, Wenyu Bai, Xiang Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430074 China Huazhong University of Science and Technology Institute of Artificial Intelligence Wuhan430074 China Huazhong University of Science and Technology School of Software Engineering Wuhan430074 China

Exploring robust and efficient association methods has always been an important issue in multi-object tracking (MOT). Although existing tracking methods have achieved impressive performance, congestion and frequent occlusions still pose challenging problems in multi-object tracking. We reveal that performing sparse decomposition on dense scenes is a crucial step to enhance the performance of associating occluded targets. To this end, we propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets and perform data association on these sparse target subsets in order from near to far. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack. SparseTrack provides a new perspective for solving the challenging crowded scene MOT problem. Only using IoU matching, SparseTrack achieves comparable performance with the state-of-the-art (SOTA) methods on the MOT17 and MOT20 benchmarks. © 1991-2012 IEEE.

关键词： Object detection

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：