检索结果-内蒙古大学图书馆

27th International Conference on pattern recognition, ICPR 2024

作者： Lin, Zi-Hao Xiao, Shun-Xin Chen, Zi-Rong Li, Jian-Min Wang, Da-Han Zhang, Xu-Yao School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031781186

Geometry problem solving (GPS) is an important research direction in artificial intelligence. Previous studies have demonstrated the effectiveness of neural solvers in GPS. However, they are deficiencies in accurately representing spatial relationships of geometric primitives within visually rich geometric diagrams. This paper presents a novel neural solver termed spatial-aware neural solver (SANS) that can perceive spatial relationships between geometric primitives. SANS includes two new modules: multimodal dual-branch spatial awareness pre-trained language module and point-primitive spatial-aware attention module. The pre-training module employs a dual-branch visual-textual point-matching strategy to align visual and textual points, and utilizes semantic structure pre-training to model global relationships. Additionally, the point-primitive spatial awareness attention module enhances the model’s ability to perceive spatial relationships between geometric primitives by accounting for the relative positions of points. Experiments show that SANS achieves 81.5 and 74.1 of accuracy on the Geometry3K and PGPS9K datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable image Registration Approach for Multimodal Histological images

引用

Computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Analysis of Distracted Driving Detection Based on Deep Learning Human Posture 23

Analysis of Distracted Driving Detection Based on Deep Learn...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Li, Yanjun Ling, Xufeng Yang, Jie Shanghai Normal University Tianhua College AI School No. 1661 North Sheng Xin Road China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 800 Dongchuan Road 200240 China

ISBN: (纸本)9781450399029

Distracted driving is a phenomenon that drivers’ attention points to activities unrelated to normal driving, which leads to the decline of driving operation ability. With the popularity of smart phones, traffic accidents caused by distracted driving are on the rise. Traffic accidents caused by driver’s inattention due to vision deviation or distraction are particularly obvious in rear end collisions. The results of the distracted driving questionnaire show that almost all drivers have experienced distracted driving. In order to detect whether drivers are distracted when driving, this paper proposes a distracted driving analysis based on deep learning of human posture. This method uses the MMDetection framework in depth learning to build a target detection network to achieve target detection, then uses the depth neural network to estimate the geometric transformation features, and uses the stacked hourglass network to accurately predict the state features of drivers in the graph. The experimental results show that the measurement method has good accuracy, fast speed, good robustness and consistency, more accurate extraction of human posture related features, strong generalization ability and certain practical value. © 2023 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Automatic Key-points Detection and Style Transfer based Method of Articulatory Animation Generation 23

An Automatic Key-points Detection and Style Transfer based M...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Liu, Wei Ling, Xufeng Liang, Jingxin Wang, Xiaobo Yang, Jie Shanghai Normal University Tianhua College AI School No. 1661 North Sheng Xin Road China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 800 Dongchuan Road 200240 China

ISBN: (纸本)9781450399029

The method of generating articulatory animation based on automatic key point detection and style transfer. This paper proposes a system of key-points detection and registration based on image feature space, and uses the GAN for motion transfer, which is used to automatically generate oral and tongue articulatory animation of English. First, by obtaining the standard articulation image of the International Phonetic Alphabet from the public dataset, we train a deep-learning motion model according to the characteristics of the tongue, upper jaw, lower jaw, small tongue, soft palate and other motion features, according to the characteristics of articulatory organ, and automatically detect the key-points in the image feature space. According to the existing MRI articulatory videos, using different styles of articulatory images, a generative model is used to generate end-to-end animation of different styles automatically. For different combinations of consonants and vowels, generate animation of different syllables, and according to different categories of articulatory, such as stress and light tone, adjust the duration of articulatory to form different animation of stress and light tone of the same syllable. And form the animation of words through syllables, and then form the animation of each sentence. Experiments show that this method can simulate realistic articulatory animation according to input phonetic symbols, and has a very positive effect on English articulatory correction. © 2023 Copyright held by the owner/author(s).

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Learning Explicit Radical Representations for Zero-Shot Chinese Character recognition 27th

Learning Explicit Radical Representations for Zero-Shot Chin...

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Pan, Song-Liang Wang, Da-Han Jiang, Nanfeng Zhang, Xu-Yao Zhu, Shunzhi School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031781186

Zero-shot Chinese character recognition (ZSCCR) aims to recognize unseen Chinese characters by learning the semantic knowledge of seen characters. Radical-based methods treat Chinese characters as combinations of radicals, recognizing characters by predicting the radicals in the images. Existing radical-based methods have a closed radical parsing process that cannot be intervened in mid-course, relying only on semantic labels for constraints. However, semantic embedding vectors are usually manually designed and lack alignment with visual features, making it extremely difficult for the model to learn and locate discriminative radical representations from visual features. This paper proposes a ZSCCR network called Learning Explicit Radical Representations (LERRNet). LERRNet introduces learnable attribute hint vectors to guide the model in locating discriminative radicals and learning explicit representations of images. Specifically, we introduce a Radical Relevance Enhanced Encoder (RREE) to enhance the correlation of local radicals by augmenting the relationships between grid regions in visual features. Guided by attribute hint vectors, LERRNet employs a Radical Representation Decoder (RRD) to locate the most relevant regions of each radical in the given image and learn explicit radical representations. Extensive experiments demonstrate that LERRNet outperforms state-of-the-art radical/stroke-based methods across three ZSCCR benchmarks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Supervised Classification of Plant image Based on Attention Mechanism 7

Supervised Classification of Plant Image Based on Attention ...

引用

7th International Conference on Systems and Informatics, ICSAI 2021

作者： Li, Jie Yang, Jie Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China

ISBN: (纸本)9781665426244

In view of the wide variety of plants on the earth, the plant species identification is particularly necessary to protect and preserve biodiversity. In this work, we propose a plant image classification method based on the encoder-decoder model with additive attention mechanism to extract plant image features and convert them into text descriptions related to plant features. In a well-trained network, it can successfully classify on the species of the generated plant texts. We show that, the proposed method not only equalizes the results of deep convolutional neural network on classification task, but also uses of the prior information of botanists in classification, and thus provide a significant prediction result. © 2021 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Progressive low/high-resolution space attention fusion network for single image super-resolution

Progressive low/high-resolution space attention fusion netwo...

引用

2020 International Symposium on Automation, Information and Computing, ISAIC 2020

作者： Zhong, Chengzu Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

The general single image super-resolution methods mainly extract features from the high-resolution (HR) space by the pre-upscaling step at the beginning of the network or from the low-resolution (LR) space before the post-upscaling step at the end of the network. The former way requires high computation as well as misleading the network by wrong artificial priors. The latter way cannot learn mapping well by only conducting simple operations in HR space. In this paper, we aim to utilize the features from LR and HR space more efficiently and propose the novel network, which applies a frequency-slicing mechanism to divide features into LR and HR space, a direction-aware fusion residual group to extract distinctive features in LR space and an attention fusion module to recalibrate features in HR space. The experimental results demonstrate that our model is superior to the state-of-the-art methods upon quantitative metrics and visual quality. © 2021 institute of Physics Publishing. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation

arXiv

引用

arXiv 2023年

作者： Liu, Jinfeng Kong, Lingtong Yang, Jie Liu, Wei Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China

Depth estimation plays an important role in robotic perception systems. The self-supervised monocular paradigm has gained significant attention since it can free training from the reliance on depth annotations. Despite recent advancements, existing self-supervised methods still underutilize the available training data, limiting their generalization ability. In this paper, we take two data augmentation techniques, namely Resizing-Cropping and Splitting-Permuting, to fully exploit the potential of training datasets. Specifically, the original image and the generated two augmented images are fed into the training pipeline simultaneously and we leverage them to conduct self-distillation. Additionally, we introduce the detail-enhanced DepthNet with an extra full-scale branch in the encoder and a grid decoder to enhance the restoration of fine details in depth maps. Experimental results demonstrate our method can achieve state-of-the-art performance on the KITTI and Cityscapes datasets. Moreover, our KITTI models also show superior generalization performance when transferring to Make3D, NYUv2 and Cityscapes datasets. Our codes are available at https://***/LiuJF1226/BDEdepth. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Robot Debater: Debate-styled Text Auto-generation System Based on Large Foundation Language Models 4

Robot Debater: Debate-styled Text Auto-generation System Bas...

引用

4th IEEE International Conference on pattern recognition and Machine Learning, PRML 2023

作者： Zhu, Yu Ling, Yijun Ling, Xufeng Yang, Jie Shanghai China Shanghai Xiangming High School Shanghai China Shanghai Normal University Tianhua College School of Artificial Intelligence Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9798350324303

We use a large foundation language model, which is fine-tuned with debate corpora, to develop a robot debater application. To address the limitations of requiring immense computational power in large base language models, this study takes advantage of the Low Rank Adaption characteristic prevalent in domain expert knowledge. By applying Low Rank Adaption technology and fine-tuning with a dedicated dataset, the computational load is reduced to just one-thousandth of what is needed for a large language model, greatly expanding the application scenarios of robot debaters using large language models. In view of the characteristics of debate competitions, this model can preset a variety of debate scenarios and supports personalized debate processes. It employs intelligent voice recognition technology combined with a multi-channel voice input method, allowing for precise localization of different human debaters and improving the accuracy of voice input recognition. The system can support multiple large-scale language generation models and utilize various different voice broadcasting systems, including male and female voice styles, as well as a range of voice emotions. This model can be applied to debate competitions held in universities, high schools, and various industries. It can support human-machine debates as well as machine-to-machine debates. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes

arXiv

引用

arXiv 2024年

作者： Yang, Ruikai He, Mingzhen He, Zhenghao Qiu, Youmei Huang, Xiaolin Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University 800 Dongchuan RD Shanghai200240 China

Machine unlearning (MU) is to make a well-trained model behave as if it had never been trained on specific data. In today’s over-parameterized models, dominated by neural networks, a common approach is to manually relabel data and fine-tune the well-trained model. It can approximate the MU model in the output space, but the question remains whether it can achieve exact MU, i.e., in the parameter space. We answer this question by employing random feature techniques to construct an analytical framework. Under the premise of model optimization via stochastic gradient descent, we theoretically demonstrated that over-parameterized linear models can achieve exact MU through relabeling specific data. We also extend this work to real-world nonlinear networks and propose an alternating optimization algorithm that unifies the tasks of unlearning and relabeling. The algorithm’s effectiveness, confirmed through numerical experiments, highlights its superior performance in unlearning across various scenarios compared to current state-of-the-art methods, particularly excelling over similar relabeling-based MU approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

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：