检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Qi, Zehao Zhang, Ruixu Hu, Xinyi Liu, Wenxuan Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400706868

Our paper introduces a novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments. Traditional Temporal Action Localization (TAL) frameworks, focusing on overt actions within constrained temporal intervals, often miss subtle pre-abnormal actions that unfold over extended periods. Our dataset comprises 228 videos with 5790 clips, each annotated to capture fine-grained actions within ambiguous temporal boundaries using the Joint-Linear-Assignment methodology. This approach enables detailed analysis of the evolution of abnormal intention over time. To detect subtle, hidden intention, we developed the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention. This enhancement has led to performance improvements of up to 139% in specific scenarios, dramatically boosting the model's sensitivity and interpretability, crucial for advancing proactive surveillance systems. By pushing the boundaries of technology, our dataset and methodologies foster proactive surveillance systems capable of preemptively identifying potential threats from nuanced behavioral patterns, encouraging further exploration into the complexities of intention beyond observable actions. The dataset is available at https://***/Zzz99999/Hidden-Abnormal-Intention. © 2024 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1825-1839页

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

Image Tampering Detection With Frequency-Aware Attention and Multiview Fusion

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年第3期6卷 614-625页

作者： Xu, Xu Chen, Junxin Lv, Wenrui Wang, Wei Zhang, Yushu Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Nanchang330013 China

Manipulated images are flooding our daily lives, which poses a threat to social security. Recently, many studies have focused on image tampering detection. However, they have poor performance on independent validation due to differences in image scenes and tampering methods. The key question is how to design a network that is able to adaptively enhance the tampering information and suppress the generalization features during training. To this end, we propose a dual-branch network with a frequency adaptation paradigm and a feature fusion module for robust tampering image detection. First, this paradigm is designed to adaptively highlight tampering features through frequency conversion and learnable weight. Second, a feature fusion module is developed to filter redundant features and dynamically fuse two-branch features. Experiments on eight typical datasets demonstrate that our model has advantages over state-of-the-art algorithms, and our paradigm can well empower semantic segmentation networks for tampering detection. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution Supplementary Material

引用

IEEE Transactions on Image Processing 2025年 34卷 3013-3024页

作者： Yuan, Jiang Ma, Ji Wang, Bo Hu, Weiming North China Electric Power University School of Control and Computer Engineering Beijing102206 China CASIA State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, we propose a detail-aware implicit degradation adapting module that can better adapt degradation representations to specific LR features by enhancing the basic adaptation unit's perception of image details, significantly reducing the overall SR model complexity. Extensive experiments on synthetic and real data show that our method achieves highly competitive quantitative and qualitative results in various degradation settings while obviously reducing parameters and computational costs, validating the feasibility of designing practical and lightweight blind SR tools. Codes and models will be available at https://***/Fieldhunter/CdCL. © 1992-2012 IEEE.

关键词： Depression Anxiety disorders Face recognition Schizophrenia Visualization Training Data collection Uncertainty Facial features Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A Pre-Diagnosis Model for Indoor Radon Potential Assessment 11

A Pre-Diagnosis Model for Indoor Radon Potential Assessment

引用

11th International Symposium on Digital Forensics and Security, ISDFS 2023

作者： Meneses, Paulo Lopes, Nuno Leite, Patricia Teixeira, Paulo Goncalves, Joaquim Silva, Joauim P. 2Ai-School of Technology Ipca Barcelos Portugal Lasi-Associate Laboratory of Intelligent Systems Guimarães Portugal Ipca School of Technology Barcelos Portugal LIACC-Artificial Intelligence and Computer Science Laboratory Porto Portugal

ISBN: (纸本)9798350336986

Indoor radon is a well-known public health threat. WHO estimates radon causes between 3-14% of all lung cancers and has issued many recommendations to encourage countries to act against the exposure to radon and associated cancer risks. However, many people continue to be unaware about radon health risk. In previous works we developed a prediagnosis approach to evaluate the radon potential in indoor environments and motivate the citizens to act when the estimated radon potential is higher. In this work, we have developed an automatic classification model for the evaluation of the radon potential level in indoor environments by considering a set of relevant features selected to characterize occupants' risk exposure. Radon data measurements from previous works have been merged and provide enough data for the start of this project. The evaluation metrics of the obtained classification model are compelling and represent a good starting point for the development of a platform that will help to raise awareness of the radon risk and promote radon measurements to the wider population. These measurements will be used as new data for the generation of more robust classification models. © 2023 IEEE.

关键词： Radon

来源：评论

学校读者我要写书评

暂无评论

Adaptive Learning via a Negative Selection Strategy for Few-Shot Bioacoustic Event Detection

Adaptive Learning via a Negative Selection Strategy for Few-...

引用

2024 IEEE International Conference on Multimedia and Expo, ICME 2024

作者： Chen, Yaxiong Zhang, Xueping Zi, Yunfei Xiong, Shengwu Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Wuhan University of Technology Sanya Science and Education Innovation Park Sanya572000 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China

ISBN: (纸本)9798350390155

Although the Prototypical Network (ProtoNet) has demonstrated effectiveness in few-shot biological event detection, two persistent issues remain. Firstly, there is difficulty in constructing a representative negative prototype due to the absence of explicitly annotated negative samples. Secondly, the durations of the target biological vocalisations vary across tasks, making it challenging for the model to consistently yield optimal results across all tasks. To address these issues, we propose a novel adaptive learning framework with an adaptive learning loss to guide classifier updates. Additionally, we propose a negative selection strategy to construct a more representative negative prototype for ProtoNet. All experiments ware performed on the DCASE 2023 TASK5 few-shot bioacoustic event detection dataset. The results show that our proposed method achieves an F-measure of 0.703, an improvement of 12.84%. © 2024 IEEE.

关键词： adaptive learning bioacoustic event detection few-shot learning negative selection teacher model

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Object Localization with Background Suppression Erasing for Art Authentication and Copyright Protection

引用

Machine intelligence Research 2024年第1期21卷 89-103页

作者： Chaojie Wu Mingyang Li Ying Gao Xinyan Xie Wing W.Y.Ng Ahmad Musyafa School of Computer Science and Engineering South China University of TechnologyGuangzhou 511442China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's HospitalGuangzhou 510180China

The problem of art forgery and infringement is becoming increasingly prominent,since diverse self-media contents with all kinds of art pieces are released on the Internet every *** art paintings,object detection and localization provide an efficient and ef-fective means of art authentication and copyright ***,the acquisition of a precise detector requires large amounts of ex-pensive pixel-level *** alleviate this,we propose a novel weakly supervised object localization(WSOL)with background su-perposition erasing(BSE),which recognizes objects with inexpensive image-level ***,integrated adversarial erasing(IAE)for vanilla convolutional neural network(CNN)dropouts the most discriminative region by leveraging high-level semantic ***,a background suppression module(BSM)limits the activation area of the IAE to the object region through a self-guidance ***,in the inference phase,we utilize the refined importance map(RIM)of middle features to obtain class-agnostic loc-alization *** experiments are conducted on paintings,CUB-200-2011 and ILSVRC to validate the effectiveness of our BSE.

关键词： Weakly supervised object localization erasing method deep learning computer vision art authentication and copyright protection

来源：评论

学校读者我要写书评

暂无评论

ONE FORWARD IS ENOUGH FOR NEURAL NETWORK TRAINING VIA LIKELIHOOD RATIO METHOD 12

ONE FORWARD IS ENOUGH FOR NEURAL NETWORK TRAINING VIA LIKELI...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Jiang, Jinyang Zhang, Zeliang Xu, Chenliang Yu, Zhaofei Peng, Yijie Wuhan Institute for Artificial Intelligence Guanghua School of Management Peking University China Xiangjiang Laboratory China Department of Computer Science University of Rochester United States Institute for Artificial Intelligence Peking University China

While backpropagation (BP) is the mainstream approach for gradient computation in neural network training, its heavy reliance on the chain rule of differentiation constrains the designing flexibility of network architecture and training pipelines. We avoid the recursive computation in BP and develop a unified likelihood ratio (ULR) method for gradient estimation with only one forward propagation. Not only can ULR be extended to train a wide variety of neural network architectures, but the computation flow in BP can also be rearranged by ULR for better device adaptation. Moreover, we propose several variance reduction techniques to further accelerate the training process. Our experiments offer numerical results across diverse aspects, including various neural network training scenarios, computation flow rearrangement, and fine-tuning of pre-trained models. All findings demonstrate that ULR effectively enhances the flexibility of neural network training by permitting localized module training without compromising the global objective and significantly boosts the network robustness. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

OPENCHAT: ADVANCING OPEN-SOURCE LANGUAGE MODELS WITH MIXED-QUALITY DATA 12

OPENCHAT: ADVANCING OPEN-SOURCE LANGUAGE MODELS WITH MIXED-Q...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Guan Cheng, Sijie Zhan, Xianyuan Li, Xiangang Song, Sen Liu, Yang Department of Computer Science and Technology Tsinghua University China Laboratory of Brain and Intelligence Tsinghua University China Tsinghua University China Shanghai Artificial Intelligence Laboratory China 01.AI

Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://***/imoneoi/openchat and https://***/openchat. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

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：