检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Shenghao Fu Junkai Yan Qize Yang Xihan Wei Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China and Tongyi Lab Alibaba Group and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Tongyi Lab Alibaba Group School of Computer Science and Engineering Sun Yat-sen University China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Province Key Laboratory of Information Security Technology China School of Computer Science and Engineering Sun Yat-sen University China and Peng Cheng Laboratory Shenzhen China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Pazhou Laboratory (Huangpu) Guangzhou Guangdong China

ISBN: (纸本)9798331314385

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector's performance while preventing the problems caused by the architecture discrepancy between the detector's backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector's backbone.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Community Detection Algorithm based on Density Peaks 9

An Adaptive Community Detection Algorithm based on Density P...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Fan, Xiang Shi, Lei-Lei Liu, Lu Han, Zi-Xuan Jiang, Liang Yuan, Bo Jiangsu University School of Computer Science and Telecommunication Engineering China Jiangsu University Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace China University of Leicester School of Computing and Mathematical Sciences United Kingdom Jiangsu University of Science and Technology School of Ocean China

ISBN: (纸本)9798350319804

Community detection is an important task for analyzing the topological function and structure of a network, as well as for various application scenarios such as advertising, marketing, and influence maximization. Label propagation is a widely used community detection algorithm for complex networks due to its simplicity and fast computation. However, this algorithm has several limitations in terms of stability and the quality of discovered communities. To address these shortcomings, we propose a novel community detection algorithm based on density peaks (ACDDP) in this paper. Firstly, we improve the local density and minimum distance of nodes by using an adaptive selection of community center nodes. Secondly, we specify the node update order to enhance the robustness and performance of the algorithm. The experimental results on real networks demonstrate that our proposed algorithm achieves higher accuracy in community division while ensuring robustness compared to other popular algorithms. © 2023 IEEE.

关键词： Adaptive Selection Community detection Density Peaks

来源：评论

学校读者我要写书评

暂无评论

SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints 39

SUMI-IFL: An Information-Theoretic Framework for Image Forge...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sheng, Ziqi Lu, Wei Luo, Xiangyang Zhou, Jiantao Cao, Xiaochun School of Computer Science and Engineering MoE Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University China State Key Laboratory of Mathematical Engineering and Advanced Computing China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China

ISBN: (纸本)157735897X

Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety. However, due to the rapid development of image tampering technologies, extracting more comprehensive and accurate forgery clues remains an urgent challenge. To address these challenges, we introduce a novel information-theoretic IFL framework named SUMI-IFL that imposes sufficiency-view and minimality-view constraints on forgery feature representation. First, grounded in the theoretical analysis of mutual information, the sufficiency-view constraint is enforced on the feature extraction network to ensure that the latent forgery feature contains comprehensive forgery clues. Considering that forgery clues obtained from a single aspect alone may be incomplete, we construct the latent forgery feature by integrating several individual forgery features from multiple perspectives. Second, based on the information bottleneck, the minimality-view constraint is imposed on the feature reasoning network to achieve an accurate and concise forgery feature representation that counters the interference of task-unrelated features. Extensive experiments show the superior performance of SUMI-IFL to existing state-of-the-art methods, not only on in-dataset comparisons but also on cross-dataset comparisons. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Correlation theory

来源：评论

学校读者我要写书评

暂无评论

Analysis of Instantaneous Angular Speed Accuracy Considering Encoder Errors

Analysis of Instantaneous Angular Speed Accuracy Considering...

引用

International Conference on Automation and computing (ICAC)

作者： Yuanhao Liu Fengshou Gu Qiang Zeng State Key Laboratory of Mechanical Transmissions for Advanced Equipment Chongqing University Chongqing China School of Computing and Engineering University of Huddersfield Huddersfield UK

ISBN: (数字)9798350360882

ISBN: (纸本)9798350360899

Instantaneous Angular Speed (IAS) is closely related to the dynamic behavior of rotating machinery and plays a crucial role in diagnosing faults. However, the measurement of the IAS is subject to various errors inevitably, which directly affect the accuracy of IAS estimation and diminish the precision of fault diagnosis in rotating machinery. Currently, the estimation of IAS primarily relies on time counting methods, and there has been limited research conducted on the application of Frequency Domain Demodulation (FDD) as an IAS estimation method, despite its potential for providing lower noise levels. The study of IAS errors based on the FFD method has received even less attention. This study undertakes pertinent research and investigates the issue identified. Firstly, it develops a model for IAS estimation using FDD, considering the specific characteristics of the encoder disk signal. Secondly, it establishes IAS models for eccentric and inclined encoder disks, considering the spatial geometric characteristics associated with different types of encoder disk errors. In conclusion, the experimental results successfully validate the accuracy and validity of the proposed theoretical models. This study lays a theoretical foundation for the precise measurement of IAS, thereby enhancing the reliability of using IAS for condition monitoring in rotating machinery.

关键词： Fault diagnosis Accuracy Frequency-domain analysis Measurement uncertainty Estimation Machining Reliability theory Machinery Rotation measurement Noise level

来源：评论

学校读者我要写书评

暂无评论

Development of an interpretable QSPR model to predict the octanol-water partition coefficient based on three artificial intelligence algorithms

引用

Green Chemical engineering 2025年第2期6卷 193-199页

作者： Ao Yang Shirui Sun Lu Qi Zong Yang Kong Jaka Sunarso Weifeng Shen College of Safety Science and Engineering Chongqing University of Science and TechnologyChongqing401331China Beijing Institute of Technology Chongqing Innovation Center Chongqing401135China School of Chemistry and Chemical Engineering Chongqing UniversityChongqing400044China School of Chemistry and Chemical Engineering Yangtze Normal UniversityChongqing408100China Jiangsu Key Laboratory of Advanced Catalytic Materials and Technology School of Petrochemical EngineeringChangzhou UniversityChangzhou213164China School of Engineering and Technology Sunway UniversityNo.5Jalan UniversitiBandar SunwaySelangor Darul Ehsan47500Malaysia Research Centre for Sustainable Technologies Faculty of EngineeringComputing and ScienceSwinburne University of TechnologyJalan Simpang TigaKuching93350SarawakMalaysia

This study aims to significantly improve existing quantitative structure-property relationship(QSPR)models for predicting the octanol-water partition coefficient(KOW).This is because accurate predictions of KOW are crucial for assessing the environmental behavior and bioaccumulation potential of *** models have reported determination coefficient(R^(2))values between 0.9451 and 0.9681,and this research seeks to exceed these *** machine learning(ML)models are explored,i.e.,feed-forward neural networks(FNN),extreme gradient boosting(XGBoost),and random forest(RF).Using a dataset of 14,610 solvents(14,580 after data cleaning)and 21 molecular descriptors derived from SMILES representations,we rigorously evaluate these models based on R^(2),mean absolute error(MAE),root mean squared error(RMSE),and mean relative error(MRE).Notably,the best model developed,the XGBoost-based QSPR,demonstrated exceptional performance,exhibiting an impressive R^(2)value of 0.9772,surpassing benchmarks set by prior research ***,shapley additive explanation(SHAP)analysis is also employed for model interpretation,and it is revealed that the top five influential input features include SMR_VSA8,SMR_VSA3,Kappa2,HeavyAtomCount,and fr_*** study not only sets a new benchmark for KOW prediction accuracy but also enhances the interpretability of QSPR models.

关键词： Octanol-water partition coefficient Environmental property QSPR Interpretable model Machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Verification of State Feedback H∞ State Molecular Controller Via Chemical Reaction Networks 5

Performance Verification of State Feedback H∞ State Molecul...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Yao, Jingwang Wang, Xing'An Lv, Hui Li, Yang Zhang, Wujie Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China Dalian University College of Environmental and Chemical Engineering Dalian116622 China Dalian Chivy Biotechnology Co. Ltd Dalian116023 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China

ISBN: (纸本)9798350325294

An important goal in synthetic biology is in the design and implementation of control strategies embedded in biochemical reaction systems to enable control of the process at the molecular level. The problem of set-point tracking and perturbation disturbances in the biochemical reaction process can be solved by a state feedback control strategy and a more stable and better dynamic performance of synthetic controllers. First, it is shown how a set of CRNs can provide state feedback to the biomolecular implementation of the H∞ controller. Then, to facilitate the modularity of biochemical process design, CRNs of trigonometric functions and repetitive sequence step signals are defined for the first time as input signals to the controller. Finally, numerical simulation experiments are designed to verify the effectiveness of the whole scheme from several perspectives, such as setpoint tracking and external perturbations. The results show that the state feedback H∞ molecular controller outperforms the conventional linear controller because it has a faster tracking response and better perturbation rejection performance. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

GLCF: A Global-Local Multimodal Coherence Analysis Framework for Talking Face Generation Detection 39

GLCF: A Global-Local Multimodal Coherence Analysis Framework...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Xiaocan Yin, Qilin Liu, Jiarui Lu, Wei Luo, Xiangyang Zhou, Jiantao School of Computer Science and Engineering MoE Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China Alibaba Group Hangzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China

ISBN: (纸本)157735897X

Talking face generation (TFG) allows for producing lifelike talking videos of any character using only facial images and accompanying text. Abuse of this technology could pose significant risks to society, creating the urgent need for research into corresponding detection methods. However, research in this field has been hindered by the lack of public datasets. In this paper, we construct the first large-scale multi-scenario talking face dataset (MSTF), which contains 22 audio and video forgery techniques, filling the gap of datasets in this field. The dataset covers 11 generation scenarios and more than 20 semantic scenarios, closer to the practical application scenario of TFG. Besides, we also propose a TFG detection framework, which leverages the analysis of both global and local coherence in the multimodal content of TFG videos. Therefore, a region-focused smoothness detection module (RSFDM) and a discrepancy capture-time frame aggregation module (DCTAM) are introduced to evaluate the global temporal coherence of TFG videos, aggregating multi-grained spatial information. Additionally, a visual-audio fusion module (V-AFM) is designed to evaluate audiovisual coherence within a localized temporal perspective. Comprehensive experiments demonstrate the reasonableness and challenges of our datasets, while also indicating the superiority of our proposed method compared to the state-of-the-art deepfake detection approaches. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Public risks

来源：评论

学校读者我要写书评

暂无评论

Dexterous Grasp Transformer

Dexterous Grasp Transformer

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Guo-Hao Xu Yi-Lin Wei Dian Zheng Xiao-Ming Wu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this work, we propose a novel discriminative frame-work for dexterous grasp generation, named Dexterous Grasp TRansformer (DGTR), capable of predicting a di-verse set of feasible grasp poses by processing the object point cloud with only one forward pass. We formulate dex-terous grasp generation as a set prediction task and design a transformer-based grasping model for it. However, we identify that this set prediction paradigm encounters sev-eral optimization challenges in the field of dexterous grasping and results in restricted performance. To address these issues, we propose progressive strategies for both the training and testing phases. First, the dynamic-static matching training (DSMT) strategy is presented to enhance the opti-mization stability during the training phase. Second, we in-troduce the adversarial-balanced test-time adaptation (AB-TTA) with a pair of adversarial losses to improve grasping quality during the testing phase. Experimental results on the DexGraspNet dataset demonstrate the capability of DGTR to predict dexterous grasp poses with both high quality and diversity. Notably, while keeping high qual-ity, the diversity of grasp poses predicted by DGTR sig-nificantly outperforms previous works in multiple metrics without any data pre-processing. Codes are available at https://***/iSEE-laboratory/DGTR.

关键词： Training Point cloud compression Measurement Grasping Predictive models Transformers Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Real-to-Sim Grasp: Rethinking the Gap between Simulation and Real World in Grasp Detection

arXiv

引用

arXiv 2024年

作者： Cai, Jia-Feng Chen, Zibo Wu, Xiao-Ming Jiang, Jian-Jian Wei, Yi-Lin Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

For 6-DoF grasp detection, simulated data is expandable to train more powerful model, but it faces the challenge of the large gap between simulation and real world. Previous works bridge this gap with a sim-to-real way1. However, this way explicitly or implicitly forces the simulated data to adapt to the noisy real data when training grasp detectors, where the positional drift and structural distortion within the camera noise will harm the grasp learning. In this work, we propose a Real-to-Sim framework for 6-DoF Grasp detection, named R2SGrasp, with the key insight of bridging this gap in a real-to-sim way2, which directly bypasses the camera noise in grasp detector training through an inference-time real-to-sim adaption. To achieve this real-to-sim adaptation, our R2SGrasp designs the Real-to-Sim Data Repairer (R2SRepairer) to mitigate the camera noise of real depth maps in data-level, and the Real-to-Sim Feature Enhancer (R2SEnhancer) to enhance real features with precise simulated geometric primitives in feature-level. To endow our framework with the generalization ability, we construct a large-scale simulated dataset cost-efficiently to train our grasp detector, which includes 64,000 RGB-D images with 14.4 million grasp annotations. Sufficient experiments show that R2SGrasp is powerful and our real-to-sim perspective is effective. The real-world experiments further show great generalization ability of R2SGrasp. Project page is available on https://***/R2SGrasp. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Compact Transformer for Adaptive Style Transfer

A Compact Transformer for Adaptive Style Transfer

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yi Li Xin Xie Haiyan Fu Xiangyang Luo Yanqing Guo School of Artificial Intelligence Dalian University of Technology Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

Due to the limitation of spatial receptive field, it is challenging for CNN-based style transfer methods to capture rich and long-range semantic concepts in artworks. Though the transformer provides a fresh solution by considering long-range dependencies, it suffers from the heavy burdens of parameter scale and computation cost especially in vision tasks. In this paper, we design a compact transformer architecture AdaFormer to address the problem. The model scale shrinks about 20% compared to state-of-the-art transformer for style transfer. Furthermore, we explore the adaptive style transfer by letting the content to select the detailed style element automatically and adaptively, which encourages the output to be both appealing and reasonable. We evaluate AdaFormer comprehensively in the experiments and the results have shown the effectiveness and superiority of our approach compared to existing artistic methods. Diverse plausible stylized images are obtained with better content preservation, more convincing style sfumato and lower computation complexity.

关键词：

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：