检索结果-内蒙古大学图书馆

9th International Conference on Computer and Communications, ICCC 2023

作者： Zhu, Xiaoke Zhao, Bo Dong, Zhiwei Dong, Lingyun Li, Danyang School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9798350317251

This paper introduces the Temporal Transform Network based on Scale Sequences (TTS) for cloth-changing person re-identification in video datasets. The TTS network is designed to capture multi-scale temporal cues within video sequences. It accomplishes this by initially modeling short-term temporal cues between adjacent frames, followed by capturing long-term relationships between non-consecutive frames. In more detail, short-term temporal cues are modeled through parallel inflated convolutions with different time dilation rates, enabling the representation of pedestrian movement and appearance dynamics. Long-term relationships are effectively captured using a temporal self-attention model, mitigating challenges such as occlusion and noise within the video sequence. The TTS network outperforms existing methods across cloth-changing video ReID datasets such as CCVID. For instance, under general settings, our approach exhibits a 1.1% improvement in top-1 accuracy and a corresponding 1.1% increase in mAP compared to the baseline. In cloth-changing settings, we observe a 0.2% enhancement in top-1 accuracy and a notable 1.3% increase in mAP relative to the baseline. © 2023 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

A graph-based model for joint chinese word segmentation and dependency parsing

arXiv

引用

arXiv 2019年

作者： Yan, Hang Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Fudan University

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on wordlevel. Therefore word segmentation is the precondition of dependency parsing, which makes dependency parsing suffer from error propagation and unable to directly make use of the character-level pre-trained language model (such as BERT). In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. Different from previous transition-based joint models, our proposed model is more concise, which results in fewer efforts of feature engineering. Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. Besides, when BERT is combined, our model can substantially reduce the performance gap of dependency parsing between joint models and gold-segmented word-based models. Our code is publicly available at https://github. com/fastnlp/JointCwsParser. Copyright © 2019, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

GAN-based Symmetric Embedding Costs Adjustment for Enhancing Image Steganographic Security 24

GAN-based Symmetric Embedding Costs Adjustment for Enhancing...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ye, Miaoxin Zhou, Saixing Luo, Weiqi Tan, Shunquan Huang, Jiwu Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-Sen University Guangzhou China Shenzhen Key Laboratory of Media Security College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen MSU-BIT University Shenzhen China

ISBN: (纸本)9798400706868

Designing embedding costs is pivotal in modern image steganography. Many studies have shown adjusting symmetric embedding costs to asymmetric ones can enhance steganographic security. However, most existing methods heavily depend on manually defined parameters or rules, limiting security performance improvements. To overcome this limitation, we introduce an advanced GAN-based framework that transitions symmetric costs to asymmetric ones without the need for the manual intervention seen in existing approaches, such as the detailed specification of cost modulation directions and magnitudes. In our framework, we firstly achieve symmetric costs for a cover image, which is randomly split into two sub-images, with part of the secret information embedded into one. Subsequently, we design a GAN model to adjust the embedding costs of the second sub-image to asymmetric, facilitating the secure embedding of the remaining secret information. To support our phased embedding approach, our GAN's discriminator incorporates two steganalyers with different tasks: distinguishing the generator's final output, i.e., the stego image, from both the input cover image and the partially embedded stego image, providing diverse guidance to the generator. In addition, we introduce a simple yet effective update strategy to ensure a stable training process. Comprehensive experiments demonstrate that our method significantly enhances security over existing symmetric steganography techniques, achieving state-of-the-art levels compared to other methods focused on embedding costs adjustments. Additionally, detailed ablation studies validate our approach's effectiveness. © 2024 ACM.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Point-Level and Set-Level Deep Representation Learning for Cross-Modal Person Re-identification 8

Point-Level and Set-Level Deep Representation Learning for C...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Hu, Jihui Ye, Pengfei Li, Danyang Dong, Lingyun Chen, Xiaopan Zhu, Xiaoke School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application China

ISBN: (纸本)9781665450515

In practice, significant modality differences usually exist between visible and infrared images, which makes visible-infrared Person Re-Identification (VI-ReID) a challenging research task. Due to the existing influence of pose variation, background changes, and occlusion, there are often outlier samples within the set of images from the same person. These outlier samples can adversely affect the process of learning the cross-modal matching model. The existing VI-ReID methods mainly focus on learning cross-modal feature representation by using image-level discriminant constraints, i.e., the distance between the truly-matching cross-modal images should be smaller than that between wrong-matching cross-modal images. However, most of these methods ignore the adverse influence caused by outliers. To solve the above problems, we proposed a Point-level and Set-level Deep Representation Learning (PSDRL) approach for VI-ReID in this paper. By using the set-level constraint in the process of deep representation learning, the discrepancy between visible and infrared modalities can be decreased, and the adverse effect of outliers can be weakened. By employing the image-level constraint, the discriminability of the obtained deep feature representations can be improved. Extensive experiments are conducted on the publicly available cross-modal Person Re-Identification datasets, including SYSU-MM01 and RegDB. Experimental results demonstrate the effectiveness of the proposed approach. © 2022 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Toward diverse text generation with inverse reinforcement learning

arXiv

引用

arXiv 2018年

作者： Shi, Zhan Chen, Xinchi Qiu, Xipeng Huang, Xuanjing Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan University

Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, in this paper, we employ inverse reinforcement learning (IRL) for text generation. Specifically, the IRL framework learns a reward function on training data, and then an optimal policy to maximum the expected total reward. Similar to the adversarial models, the reward and policy function in IRL are optimized alternately. Our method has two advantages: (1) the reward function can produce more dense reward signals. (2) the generation policy, trained by "entropy regularized" policy gradient, encourages to generate more diversified texts. Experiment results demonstrate that our proposed method can generate higher quality texts than the previous methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

An Improved K-means Algorithm Based on the Bayesian Inference 7th

An Improved K-means Algorithm Based on the Bayesian Inferenc...

引用

7th China National Conference on Big Data and Social computing, BDSC 2022

作者： Chen, Rumeng Wang, Feng Hu, Feng Computer College of Qinghai Normal University Qinghai Xining810008 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China Academy of Plateau Science and Sustainability Qinghai Xining810016 China

ISBN: (纸本)9789811975318

As one of the most widely used algorithms in machine learning, the fs algorithm is known for its simplicity and efficiency. However, it also has certain limitations, including pre-selecting the K value, which leads to issues such as different cluster shapes and outlier effects. In addition, this clustering algorithm needs to select the initial cluster centers, which produces the phenomenon of local optimum. To alleviate these two types of problems, this paper propose a K-means variant combined with Bayesian inference, dubbed the Bayes-K-means. Firstly, use Bayesian parameter inference to identify parameters for initial cluster centers. According to the probability function of the prior distribution, recalculate the distance from the sample points to the cluster centers. Therefore, the algorithm realizes the global search in the iterative process, which helps to improve the global optimum ability of the algorithm and avoids the phenomenon of local search caused by the K-means algorithm. We verify the Bayes-K-means and theoretically analyze its convergence from the aspect of the posterior distribution and the expression of the clustering center, respectively. Finally, applying the collected and processed real datasets, experimental tests based on artificial datasets and UCI datasets, then comparing Bayes-K-means with K-means, K-means++ and Bisecting K-means experiments, aggregated the class results are consistent with the actual situation. The results show that the proposed algorithm can effectively improve the clustering accuracy, efficiency and generalization performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Facial StO2: A New Promising Biometric Identity

Facial StO2: A New Promising Biometric Identity

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Dairong Peng Sirui Sun Xinyu Liu Ju Zhou Tong Chen Institute of Legal Psychology and Intelligent Computing Southwest University Chongqing China Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing Chongqing China School of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

In this paper, we introduce a new biometric identity, facial tissue oxygen saturation (StO2). StO2 is an index of blood oxygen content in tissues and is related to blood vessel distribution pattern and metabolic rate. Experimental results show that classification accuracy can reach 83.33% in 42 participants with different stress states by using StO2 as the only input to the ResNet-50 model. We also proposed a module called StO2Net to eliminate the effects of stress on classification. The highest accuracy can reach up to 90.48% when the module is used. This pilot study shows that facial StO2 can be a promising biometric feature for identity recognition.

关键词： Databases Face recognition Biological system modeling Aging Security Bioinformatics Stress

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Centroid Representation Learning for Cross-domain Few-shot Classification from Remote Sensing Imagery

Pseudo-Centroid Representation Learning for Cross-domain Few...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Can Li Jianlin Xie He Chen Yin Zhuang Jiahao Li Liang Chen National Key Laboratory of Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Cross-domain few-shot classification is gaining significant attention due to its potential to address challenges in remote sensing applications, such as large domain gaps and limited labeled data. Recent approaches have explored leveraging unlabeled target domain data for semi-supervised learning, in addition to source labeled data, to improve cross-domain training. However, these techniques often struggle with getting discriminative representation for distinguishing categories in novel target domains, particularly when facing new categories and limited training examples. To overcome these issues, we propose a novel cross-domain pseudo-centroid representation (CDPCR) framework, designed to generate more discriminative and adaptable class representations for improved cross-domain learning. The framework consists of a semi-supervised cross-domain structure that integrates both source labeled data and a portion of target unlabeled data to establish the relationship between domains. A consistency regularization branch is introduced to stabilize model outputs by aligning predictions on the target unlabeled data under input perturbations. Additionally, a pseudo-centroid contrastive representation learning module is incorporated to enhance intra-category feature consistency while improving the separability of inter-category representations, aiding the model in adapting to classification tasks across diverse domains. The effectiveness of the proposed CDPCR framework is validated through comprehensive experiments conducted across 8 cross-domain scenarios using remote sensing scene classification datasets.

关键词： Training Representation learning Adaptation models Scene classification Perturbation methods Semisupervised learning Predictive models Data processing Data models Remote sensing

来源：评论

学校读者我要写书评

暂无评论

QR Code Detection with Faster-RCNN Based on FPN 6th

QR Code Detection with Faster-RCNN Based on FPN

引用

6th International Conference on Artificial Intelligence and Security, ICAIS 2020

作者： Peng, Jinbo Yuan, Song Yuan, Xin School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9783030578831

Nowadays, the QR code is often used in many popular fields, such as payment and social networking. Therefore, it is particularly important to quickly and accurately detect the position of QR code in real complex scenes. Traditional QR code detection methods mainly use hand-engineered features for detection. However, the QR code photos we take may be blurred due to pixel, distance, and other problems, and may even produce some rotations and deformations because of the complex scenes. Under such circumstances, the traditional QR code detection methods may not be so applicable. Faster-RCNN was originally used for multiple object detection, but we adjusted it slightly and applied it to the detection of QR code. At the same time, we made a small dataset under complex scenes for training Faster-RCNN networks. However, in complex scenes, the size of the QR code vary greatly due to the distance of shooting, so we add an FPN module to the Faster-RCNN to improve the detection performance for small and multi-scale QR code. Experimental results show that our method has achieved good performances in the detection of QR code in complex scenes. © 2020, Springer Nature Switzerland AG.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Thinking clearly, talking fast: Concept-guided non-autoregressive generation for open-domain dialogue systems

arXiv

引用

arXiv 2021年

作者： Zou, Yicheng Liu, Zhihua Hu, Xingwu Zhang, Qi Shanghai Key Laboratory of Intelligent Information Processing Fudan UniversitySchool of Computer Science Fudan UniversityShanghai China

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech processing

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：