检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hao, Luoying Hu, Yan Yue, Yang Wu, Li Fu, Huazhu Duan, Jinming Liu, Jiang Research Institute of Trustworthy Autonomous Systems Dept. of Computer Science and Engineering Southern University of Science and Technology China School of Computer Science University of Birmingham United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences University of Manchester United Kingdom MGI Tech Co. Ltd. China Singapore

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical surgical scene understanding. In this work, we propose to represent the tasks set [phase recognition → step recognition → action and instrument detection] as multi-level semantic scene understanding (MSSU). For this target, we propose a novel hierarchical context transformer (HCT) network and thoroughly explore the relations across the different level tasks. Specifically, a hierarchical relation aggregation module (HRAM) is designed to concurrently relate entries inside multi-level interaction information and then augment task-specific features. To further boost the representation learning of the different tasks, inter-task contrastive learning (ICL) is presented to guide the model to learn task-wise features via absorbing complementary information from other tasks. Furthermore, considering the computational costs of the transformer, we propose HCT+ to integrate the spatial and temporal adapter to access competitive performance on substantially fewer tunable parameters. Extensive experiments on our cataract dataset and a publicly available endoscopic PSI-AVA dataset demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin. The code is available at https://***/Aurorahao/HCT. Copyright © 2025, The Authors. All rights reserved.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

Closer through commonality: Enhancing hypergraph contrastive learning with shared groups

Closer through commonality: Enhancing hypergraph contrastive...

引用

IEEE International Conference on Big data

作者： Daeyoung Roh Donghee Han Daehee Kim Keejun Han Mun Yi Graduate School of Data Science KAIST Republic of Korea School of Computer Engineering Hansung University Republic of Korea Department of Industrial and Systems Engineering KAIST Republic of Korea

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Hypergraphs provide a superior modeling frame-work for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, overcoming the limitations of traditional homogeneous graphs. However, there have been few studies on hypergraph-based contrastive learning, and existing graph-based contrastive learning methods have not been able to fully exploit the high-order correlation information in hypergraphs. Here, we propose a Hypergraph Fine-grained contrastive learning (HyFi) method designed to exploit the complex high-dimensional information inherent in hypergraphs. While avoiding traditional graph augmentation methods that corrupt the hypergraph topology, the proposed method provides a simple and efficient learning augmentation function by adding noise to node features. Furthermore, we expands beyond the traditional dichotomous relationship between positive and negative samples in contrastive learning by introducing a new relationship of weak positives. It demonstrates the importance of fine-graining positive samples in contrastive learning. Therefore, HyFi is able to produce high-quality embeddings, and outperforms both supervised and unsupervised baselines in average rank on node classification across 10 datasets. Our approach effectively exploits high-dimensional hypergraph information, shows significant improvement over existing graph-based contrastive learning methods, and is efficient in terms of training speed and GPU memory cost. The source code is available at https://***/Noverse0/***.

关键词： Training Costs Correlation Source coding Noise Memory management Graphics processing units Contrastive learning data models Topology

来源：评论

学校读者我要写书评

暂无评论

Literature Review: Analysis of Essential Metadata Attributes of Digital Goods for Transaction in The Virtual World

Literature Review: Analysis of Essential Metadata Attributes...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Gede Indra Raditya Martha Harjanto Prabowo Ford Lumban Gaol Richard Wiputra Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

In online-based virtual worlds such as Metaverse, Online Games, and other online digital spaces, the virtual/digital goods (digital items / digital assets) are fundamental things that must be available to be able to do business & create an economy in the virtual world through monetization & transactions from these digital goods. This research focuses on summarizing and exploring the attributes used in digital goods in the virtual world by extracting attributes in digital goods from other related studies using the Systematic Literature Review methodology & PRISMA Framework comprehensively so that it can be a reference for developers in designing the properties and functions of digital goods in the virtual world that are being developed, which in this case will be in the form of an NFT in the future. Based on research that has been carried out, 3 essential metadata attributes have the most influence on transactions, number 1 Visual Design / Aesthetic (Representative), number 2 Effect (Utilities), and number 3 Statistics / Performance (Utilities) which must be considered in developing/making digital goods in the form of NFTs in the virtual world so that the value of digital goods can attract users to buy or transact them in the virtual world.

关键词： Visualization Metaverse Buildings Games Metadata Information management Business

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations

arXiv

引用

arXiv 2023年

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong China School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Activity in Untrimmed Videos Using Dense Optical Flow and Deep Neural Network 5

Early Detection of Activity in Untrimmed Videos Using Dense ...

引用

5th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2021

作者： Poonkodi, M. Vadivu, G. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India Big Data Analytics School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9781665435246

computer Vision is playing aremarkable role right from essentials to entertainment and thus trying to turn computer as a 'seeing' machine. Having widespread applications in most of the real world domain like healthcare, surveillance., space and social media, yet it is still challenging to match human intelligence in understanding the underlying context. Recognition of a task performed by human is important to learn the happenings, but predicting it, from the activities' initial subset becomes an aid to overcome adversities in near future. Numerous algorithms and techniques are present, yet a gap exists due to the environment in which it is recorded, illumination condition,overlapping of men and materials on captured scenes *** lead to the requirement of high power computing devices for recognition, which is considerably *** this work, Dense OPnet (Dense optical flow and Convolution neural Net) is proposed which takes in the RGB input video, converted to dense optical flow frames and then fed to three layered CNN for recognition and early detection of an activity using N/2 frames of the total input video. This method is evaluated on two benchmark datasetlike J-HMDB21 and UCF50 giving an accuracy of 93.4% and 74.3% on recognition, 68.2% and 50.24% on early action detection respectively. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Imaging Detection and Classification for Near-space Dim Targets 7

Imaging Detection and Classification for Near-space Dim Targ...

引用

7th International Conference on Vision, Image and Signal Processing, ICVISP 2023

作者： Yuan, Yupu Xi, Runping Chen, Qian School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Province Key Laboratory of Speech & Image Processing Xi'an China National Engineering Laboratory of Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China

ISBN: (纸本)9781839539848

The motion mode of near-space targets is complex due to their high threat level. The target imaging faces low SNR and susceptibility to background noise. The existing detection and classification algorithms struggle to meet the demands of performance and speed on such targets. To address these issues, a YOLOv5-based target detection algorithm utilizes CARAFE upsampling and the small detection head to extract internal features and edge information of dim target. The algorithm adeptly captures dim target features, enhancing real-time performance and detection accuracy while overcoming subtle feature granularity and extraction difficulties. Aiming at the problem that there is no existing trajectory classification algorithm in the near-space field, we propose an infrared dim target trajectory classification algorithm. The improved attention module is used to enhance the extraction of motion features, and the target category is accurately identified by the prediction module, improving the capacity to extract dependencies between trajectory fragments. We execute comparative experiments on common infrared dim target dataset, near-space infrared dim target dataset and real dataset to confirm the viability of our methods. The outcomes indicate that our proposed method can be applied to the above three types of dim targets and significantly outperforms state-of-the-art methods. © The Institution of Engineering & Technology 2023.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

FACTORIAL USER MODELING WITH HIERARCHICAL GRAPH NEURAL NETWORK FOR ENHANCED SEQUENTIAL RECOMMENDATION

arXiv

引用

arXiv 2022年

作者： Xue, Lyuxin Yang, Deqing Xiao, Yanghua School of Data Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China

Most sequential recommendation (SR) systems employing graph neural networks (GNNs) only model a user’s interaction sequence as a flat graph without hierarchy, overlooking diverse factors in the user’s preference. Moreover, the timespan between interacted items is not sufficiently utilized by previous models, restricting SR performance gains. To address these problems, we propose a novel SR system employing a hierarchical graph neural network (HGNN) to model factorial user preferences. Specifically, a timespan-aware sequence graph (TSG) for the target user is first constructed with the timespan among interacted items. Next, all original nodes in TSG are softly clustered into factor nodes, each of which represents a certain factor of the user’s preference. At last, all factor nodes’ representations are used together to predict SR results. Our extensive experiments upon two datasets justify that our HGNN-based factorial user modeling obtains better SR performance than the state-of-the-art SR models. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A multip-level additive distortion method for security improvement in palette image steganography

引用

Journal of Visual Communication and Image Representation 2025年 110卷

作者： Chen, Yi Wang, Hongxia Cui, Yunhe Shen, Guowei Guo, Chun Liu, Yong Wu, Hanzhou State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guizhou University Guiyang550025 China School of Cyber Science and Engineering Sichuan University Chengdu610065 China School of Artificial Intelligence Hubei University of Automotive Technology Shiyan442002 China School of Big Data and Computer Science Guizhou Normal University Guiyang550025 China School of Communication and Information Engineering Shanghai University Shanghai200444 China

With the rapid development of the Internet and communication technology, palette images have become a preferred media for steganography. However, the security of palette image steganography faces a big problem. To address this, we propose a multiple-level additive distortion method for security improvement in palette image steganography. The proposed multiple-level additive distortion method comprises an index-level cost method and a pixel-level cost method. The index-level and the pixel-level costs by the two methods can respectively reflect the relationship changes of adjacent indices and the pixels corresponding to the adjacent indices. Meanwhile, the index-level and the pixel-level costs can also reflect the modification impact of steganography. Therefore, the proposed method can improve the security of palette image steganography. We conducted extensive experiments on three datasets to verify the security improvement. Experiment results have shown our proposed multiple-level distortion method indeed has an advantage in security when compared with four state-of-the-art methods. © 2025 Elsevier Inc.

关键词： Additive costs Color table Index matrix Multiple-level distortions Palette images Security Steganography

来源：评论

学校读者我要写书评

暂无评论

Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Deng, Songhe Zhuo, Wei Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model’s ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt Engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: https://***/CVI-SZU/QA-CLIMS Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge

arXiv

引用

arXiv 2024年

作者： Li, Hanzhe Zhou, Jiaran Li, Yuezun Wu, Baoyuan Li, Bin Dong, Junyu School of Computer Science and Technology Ocean University of China China School of Data Science The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces FreqBlender, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Fake 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：