检索结果-内蒙古大学图书馆

Enhancing action discrimination via category-specific frame clustering for weakly-supervised temporal action localization

引用

Frontiers of Information Technology & Electronic engineering 2024年第6期25卷 809-823页

作者： Huifen XIA Yongzhao ZHAN Honglin LIU Xiaopeng REN School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications Zhenjiang 212013China Changzhou Vocational Institute of Mechatronic Technology Changzhou 213164China

Temporal action localization (TAL) is a task of detecting the start and end timestamps of action instances and classifying them in an untrimmed video. As the number of action categories per video increases, existing weakly-supervised TAL (W-TAL) methods with only video-level labels cannot provide sufficient supervision. Single-frame supervision has attracted the interest of researchers. Existing paradigms model single-frame annotations from the perspective of video snippet sequences, neglect action discrimination of annotated frames, and do not pay sufficient attention to their correlations in the same category. Considering a category, the annotated frames exhibit distinctive appearance characteristics or clear action ***, a novel method to enhance action discrimination via category-specific frame clustering for W-TAL is proposed. Specifically,the K-means clustering algorithm is employed to aggregate the annotated discriminative frames of the same category, which are regarded as exemplars to exhibit the characteristics of the action category. Then, the class activation scores are obtained by calculating the similarities between a frame and exemplars of various categories. Category-specific representation modeling can provide complimentary guidance to snippet sequence modeling in the mainline. As a result, a convex combination fusion mechanism is presented for annotated frames and snippet sequences to enhance the consistency properties of action discrimination,which can generate a robust class activation sequence for precise action classification and localization. Due to the supplementary guidance of action discriminative enhancement for video snippet sequences, our method outperforms existing single-frame annotation based methods. Experiments conducted on three datasets (THUMOS14, GTEA, and BEOID) show that our method achieves high localization performance compared with state-of-the-art methods.

关键词： Weakly supervised Temporal action localization Single-frame annotation Category-specific Action discrimination

来源：评论

学校读者我要写书评

暂无评论

SciMRC: Multi-perspective Scientific Machine Reading Comprehension 30

SciMRC: Multi-perspective Scientific Machine Reading Compreh...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Xiao Zheng, Heqi Nie, Yuxiang Huang, Heyan Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China State Grid Smart Grid Research Institute Co. Ltd. China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9782493814104

Scientific Machine Reading Comprehension (SMRC) aims to facilitate the understanding of scientific texts through human-machine interactions. While existing dataset has significantly contributed to this field, it predominantly focus on single-perspective question-answer pairs, thereby overlooking the inherent variation in comprehension levels among different readers. To address this limitation, we introduce a novel multi-perspective scientific machine reading comprehension dataset, SciMRC, which incorporates perspectives from beginners, students, and experts. Our dataset comprises 741 scientific papers and 6,057 question-answer pairs, with 3,306, 1,800, and 951 pairs corresponding to beginners, students, and experts respectively. Extensive experiments conducted on SciMRC using pre-trained models underscore the importance of considering diverse perspectives in SMRC and highlight the challenging nature of our scientific machine comprehension tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Strategic Foresight: Anticipating Future Trends and Modelling Business Strategies

AI-Driven Strategic Foresight: Anticipating Future Trends an...

引用

2024 International Conference on Decision Aid sciences and applications, DASA 2024

作者： Qader Ismail Alnajem, Ahmed Abdel Ibrahim, Amer Abdulrahman, Mayasa M. Abdulrazak Al-Kubaisi, Abdulrazak A. Tawfeq, Jamal Fadhil Khishe, Mohammad Saeed, Ali Baghdad College of Economic Sciences Business Administration Department Iraq College of Information Technology Department of Computer Science and Software Engineering United Arab Emirates College of Engineering Computer Engineering Department University of Baghdad Baghdad Iraq Medical Technical College Department of Medical Instrumentation Technical Engineering Al-Farahidi University Baghdad00965 Iraq Yuan Ze University Innovation Center for Artificial Intelligence Applications Taiwan Jadara University Jadara Research Center Jordan Northern Technical University Computer Center Ninevah Iraq

ISBN: (纸本)9798350369106

In a generation characterized with the aid of speedy technological advancements, socio-monetary shifts, and environmental challenges, groups need to undertake proactive strategies to stay aggressive and resilient. Strategic foresight, which entails expecting destiny tendencies and modeling enterprise techniques, accordingly, emerges as a vital device in navigating this uncertainty. The trouble this have a look at addresses is the growing trouble groups face in predicting and making ready for destiny disruptions the use of conventional forecasting techniques. The number one goals of this have a look at are to discover the important thing methodologies and gear of strategic foresight, display how those techniques may be implemented to assume destiny tendencies, and offer insights on integrating foresight into enterprise approach formulation. This has a look at contributes to the present frame of information with the aid of using providing a complete evaluation of strategic foresight techniques, which includes environmental scanning, situation planning, the Delphi method, fashion evaluation, SWOT and PESTLE evaluation, and era street mapping. Research findings show that forward-looking strategies provide an organization with the ability to identify potential risks and opportunities, develop adaptive strategies, and achieve long-term growth Specifically, strategic organizations using anticipation reports a 30% increase in the ability to anticipate market fluctuations, a 25% improvement in strategic haste and a 20% reduction in unexpected disruptions, of consumer goods etc. Case studies of various industries demonstrate the practical application and usefulness of forecasting in real-world situations The study concludes that incorporating forward-looking strategies into business planning does not that it not only prepares organizations for future challenges but empowers them to shape their future and ensure sustainable competitive advantage. © 2024 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional SPH simulations of transient viscoelastic fluid flows with a level-set based pre-processing algorithm: Towards industrial applications

引用

engineering Analysis with Boundary Elements 2025年 179卷

作者： Xu, Xiaoyang Wang, Xiaoyue Tian, Lingyun Yu, Peng School of Computer Science and Technology School of Safety Science and Engineering Xi'an University of Science and Technology Xi'an710054 China Guangdong Provincial Key Laboratory of Turbulence Research and Applications Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China

This article introduces an enhanced smoothed particle hydrodynamics (SPH) approach for simulating three-dimensional (3D) transient flows of viscoelastic fluids governed by the Phan Thien Tanner (PTT) model, marking an important step towards practical industrial applications. Specifically, a mixed symmetric correction algorithm is applied to improve the kernel gradient's accuracy, enhancing the computational precision of the SPH method. Additionally, an advanced boundary treatment method is developed, utilizing both the wall and dummy particles, enabling efficient modeling of irregular boundaries. A level-set based pre-processing technique ensures a consistent particle distribution at arbitrary complex boundaries. The developed SPH approach is first tested on 3D Hagen-Poiseuille flow for a PTT fluid, with accuracy verified through comparison with OpenFOAM results and analysis of the l2 norm error between SPH and OpenFOAM solutions. The method is then applied to simulate the behavior of a 3D PTT droplet colliding with a rigid surface. The study explores droplet spreading and bouncing dynamics by varying the Reynolds number. Further analysis investigates the influence of the Reynolds number, Weissenberg number, solvent viscosity ratio, and PTT elongational parameter on droplet behavior. Finally, the method's industrial relevance is demonstrated in the context of 3D injection molding for turbine rotors. The results highlight the potential of the proposed SPH method as a robust tool for simulating 3D PTT viscoelastic fluid flows, offering significant promise for solving complex industrial challenges. © 2025 Elsevier Ltd

关键词： Transition flow

来源：评论

学校读者我要写书评

暂无评论

A General Chessboard Image Inpainting Method

A General Chessboard Image Inpainting Method

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Xinghui Zhang Yajie Wang Song Liu Yanyan Wu School of Computer Science Shenyang Aerospace University Shenyang China Engineering Training Center Shenyang Aerospace University Shenyang China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

With the continuous advancement of artificial intelligence technology, image inpainting, as an important branch of computer vision, has received widespread attention. The issue that lighting conditions significantly affect the identification and positioning of chess pieces in existing chess-playing robots is addressed in this paper, which proposes a general chessboard image inpainting method—Adversarial Masked Autoencoder (AMAE). This method, which combines Generative Adversarial Networks and Masked Auto-Encoders for joint training, is designed to enhance the quality of chessboard images. First, the masked autoencoder is pre-trained using chessboard images. Then, the pre-trained masked autoencoder is jointly trained with generator and discriminator. The adversarial principle of Generative Adversarial Networks is used to guide the training of the masked Autoencoder. A chessboard image with both clear texture details and global structural information is obtained. Finally, a dataset is created by collecting a large number of Go and Chinese chessboard images under different lighting conditions to validate the effectiveness of the proposed method.

关键词： Training computer vision Autoencoders Lighting Generative adversarial networks Generators Image restoration Data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Precision Harvesting in Cluttered Environments: Integrating End Effector Design with Dual Camera Perception

arXiv

引用

arXiv 2025年

作者： Koe, Kendall Shah, Poojan Kalpeshbhai Walt, Benjamin Westphal, Jordan Marri, Samhita Kamtikar, Shivani Nam, James Seungbum Uppalapati, Naveen Kumar Krishnan, Girish Chowdhary, Girish Computer Science UIUC United States Mechanical Science and Engineering UIUC United States Electrical and Computer Engineering UIUC United States National Center for Supercomputing Applications UIUC United States

Due to labor shortages in specialty crop industries, a need for robotic automation to increase agricultural efficiency and productivity has arisen. Previous manipulation systems perform well in harvesting in uncluttered and structured environments. High tunnel environments are more compact and cluttered in nature, requiring a rethinking of the large form factor systems and grippers. We propose a novel codesigned framework incorporating a global detection camera and a local eye-in-hand camera that demonstrates precise localization of small fruits via closed-loop visual feedback and reliable error handling. Field experiments in high tunnels show our system can reach an average of 85.0% of cherry tomato fruit in 10.98s on average. © 2025, CC BY-NC-ND.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

AgriLLM:Harnessing Transformers for Framer Queries 3

AgriLLM:Harnessing Transformers for Framer Queries

引用

3rd Workshop on NLP for Positive Impact, NLP4PI 2024, held in conjunction with the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Didwania, Krish Seth, Pratinav Kasliwal, Aditya Agarwal, Amit Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Academy of Higher Education Manipal India Department of Data Science & Computer Applications Manipal Academy of Higher Education Manipal India Enterprise Analytics & Data Science Artificial Intelligence - Center of Excellence Wells Fargo International Solutions Private Limited Bangalore India

ISBN: (纸本)9798891761759

Agriculture, vital for global sustenance, necessitates innovative solutions due to a lack of organized domain experts, particularly in developing countries where many farmers are impoverished and cannot afford expert consulting. Initiatives like Farmers Helpline play a crucial role in such countries, yet challenges such as high operational costs persist. Automating query resolution can alleviate the burden on traditional call centers, providing farmers with immediate and contextually relevant information. The integration of Agriculture and Artificial Intelligence (AI) offers a transformative opportunity to empower farmers and bridge information gaps. Language models like transformers, the rising stars of AI, possess remarkable language understanding capabilities, making them ideal for addressing information gaps in agriculture. This work 1 explores and demonstrates the transformative potential of Large Language Models (LLMs) in automating query resolution for agricultural farmers, leveraging their expertise in deciphering natural language and understanding context. Using a subset of a vast dataset of real-world farmer queries collected in India, our study focuses on approximately 4 million queries from the state of Tamil Nadu, spanning various sectors, seasonal crops, and query types. © 2024 Association for Computational Linguistics.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

On Learning Frequency-Instance Correlations by Model-Agnostic Training for Synthetic Speech Detection 16

On Learning Frequency-Instance Correlations by Model-Agnosti...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Wang, Zining Gao, Lijian Zhang, Jialin Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Zhenjiang China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

The goal of Synthetic Speech Detection (SSD) is to detect spoofing speech synthesized by text-to-speech and voice conversion. Most existing SSD methods focus only on mining frequency-wise dependency by customizing frequency-aggregation modules in SSD models. However, the instance-wise dependency is usually under-explored, which is critical for identifying the synthetic speech from a global view. In this paper, we propose a novel model-agnostic training strategy for SSD that exploits both local (frequency-wise) and global (instance-wise) contexts, which do not rely on a customized architecture and can be flexibly integrated into previous SSD models. Specifically, we propose an inter-frequency correlation module to capture the local context by reconstructing the masked frequency information from the unmasked frequency context. Meanwhile, an inter-instance correlation module is performed to explore the global context among different instances by promoting intra-class compactness and inter-class dispersion in the latent space. These two complementary modules operate from distinct contextual perspectives, leading to improvements in SSD performance. Extensive experiments show that our method significantly improves the performance of two state-of-the-art models on the 2019 dataset and 2021 dataset of ASVspoof. © 2024 Z. Wang, L. Gao, J. Zhang & Q. Mao.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Broad Federated Meta-Learning of Damaged Objects in Aerial Videos

引用

computer Modeling in engineering & sciences 2023年第12期137卷 2881-2899页

作者： Zekai Li Wenfeng Wang School of Aerospace Engineering Xi’an Jiaotong UniversityXi’an710049China Research Institute of Intelligent Engineering and Data Applications Shanghai Institute of TechnologyShanghai201418China Research Center for Ecology and Environment of Central Asia Chinese Academy of SciencesUrumqi830011China Applied Nonlinear Science Lab Anand International College of EngineeringJaipur391320India Department of Visual Engineering International Academy of Visual Art and EngineeringLondonCR26EQUK Institute of Intelligent Management and Technology Sino-Indian Joint Research Center of AI and RoboticsBhubaneswar752054India

We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial ***-learning system was integrated with the fuzzy broad learning system to further develop the theory of federated *** the mixed picture set of aerial video segmentation and the 3D-reconstructed mixed-reality data were employed in the performance of the broad federated meta-learning *** study results indicated that the object classification accuracy is up to 90%and the average time cost in damage detection is only 0.277 ***,the broad federated meta-learning system is efficient and effective in detecting damaged objects in aerial videos.

关键词： Fuzzy learning system mixed-reality 3D-reconstructed oblique photography

来源：评论

学校读者我要写书评

暂无评论

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5445-5460页

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China China Meteorological Administration National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite Beijing100081 China Tsinghua University State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Beijing100084 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China New York University Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates University of Science and Technology of China School of Cyber Science and Technology Anhui Hefei230052 China

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data

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：