检索结果-内蒙古大学图书馆

Multi-Feature Super-Resolution Network for Cloth Wrinkle Synthesis

Journal of Computer Science & Technology 2021年第3期36卷 478-493页

作者： Lan Chen Juntao Ye Xiaopeng Zhang National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Zhejiang Lab Hangzhou 311121China

Existing physical cloth simulators suffer from expensive computation and difficulties in tuning mechanical parameters to get desired wrinkling ***-driven methods provide an alternative *** typically synthesize cloth animation at a much lower computational cost,and also create wrinkling effects that are similar to the training *** this paper we propose a deep learning based method for synthesizing cloth animation with high resolution *** do this we first create a dataset for training:a pair of low and high resolution meshes are simulated and their motions are *** a result the two meshes exhibit similar large-scale deformation but different small *** simulated mesh pair is then converted into a pair of low-and high-resolution"images"(a 2D array of samples),with each image pixel being interpreted as any of three descriptors:the displacement,the normal and the *** these image pairs,we design a multi-feature super-resolution(MFSR)network that jointly trains an upsampling synthesizer for the three *** MFSR architecture consists of shared and task-specific layers to learn multi-level features when super-resolving three descriptors ***-to-frame consistency is well maintained thanks to the proposed kinematics-based loss *** method achieves realistic results at high frame rates:12-14 times faster than traditional physical *** demonstrate the performance of our method with various experimental scenes,including a dressed character with sophisticated collisions.

关键词： cloth animation deep learning multi-feature super-resolution wrinkle synthesis

来源：评论

学校读者我要写书评

暂无评论

Unpaired Image-Text Matching via Multimodal Aligned Conceptual Knowledge

引用

IEEE Transactions on pattern Analysis and Machine intelligence 2024年第7期47卷 5160-5176页

作者： Yan Huang Yuming Wang Yunan Zeng Junshi Huang Zhenhua Chai Liang Wang New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences (UCAS) Beijing China AI Lab Meituan Beijing China

Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which use millions or billions of paired images and texts for supervised model learning. Different from them, human brains can well match images with texts using their stored multimodal knowledge. Inspired by that, this paper studies a new scenario as unpaired image-text matching, in which paired images and texts are assumed to be unavailable during model learning. To deal with it, we accordingly propose a simple yet effective method namely Multimodal Aligned Conceptual Knowledge (MACK). First, we collect a set of words and their related image regions from publicly available datasets, and compute prototypical region representations to obtain pretrained general knowledge. To make the obtained knowledge better suit for certain datasets, we refine it using unpaired images and texts in a self-supervised learning manner to obtain fine-tuned domain knowledge. Then, to match given images with texts based on the knowledge, we represent parsed words in the texts by prototypical region representations, and compute region-word similarity scores. At last, the scores are aggregated based on bidirectional similarity pooling into an image-text similarity score, which can be directly used for unpaired image-text matching. The proposed MACK is complementary with existing models, which can be easily extended as a re-ranking method to substantially improve their performance of zero-shot and cross-dataset image-text matching.

关键词： Visualization Semantics Task analysis Knowledge graphs Computational modeling Brain modeling Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients

引用

Machine intelligence Research 2023年第5期20卷 666-682页

作者： Cheng-Cheng Ma Bao-Yuan Wu Yan-Bo Fan Yong Zhang Zhi-Feng Li National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China School of Data Science The Chinese University of Hong KongShenzhen 518172China Shenzhen Research Institute of Big Data Shenzhen 518172China AI Lab Tencent Inc.Shenzhen 518057China

Adversarial example has been well known as a serious threat to deep neural networks(DNNs).In this work,we study the detection of adversarial examples based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution(GGD)but with different parameters(i.e.,shape factor,mean,and variance).GGD is a general distribution family that covers many popular distributions(e.g.,Laplacian,Gaussian,or uniform).Therefore,it is more likely to approximate the intrinsic distributions of internal responses than any specific ***,since the shape factor is more robust to different databases rather than the other two parameters,we propose to construct discriminative features via the shape factor for adversarial detection,employing the magnitude of Benford-Fourier(MBF)coefficients,which can be easily estimated using ***,a support vector machine is trained as an adversarial detector leveraging the MBF *** experiments in terms of image classification demonstrate that the proposed detector is much more effective and robust in detecting adversarial examples of different crafting methods and sources compared to state-of-the-art adversarial detection methods.

关键词： Adversarial defense adversarial detection generalized Gaussian distribution Benford-Fourier coefficients image classification

来源：评论

学校读者我要写书评

暂无评论

Antigen-specific antibody design via direct energy-based preference optimization 24

Antigen-specific antibody design via direct energy-based pre...

引用

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

作者： Xiangxin Zhou Dongyu Xue Ruizhe Chen Zaixiang Zheng Liang Wang Quanquan Gu School of Artificial Intelligence University of Chinese Academy of Sciences and New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) and ByteDance Research ByteDance Research College of Computer Science and Electronic Engineering Hunan University and ByteDance Research School of Artificial Intelligence University of Chinese Academy of Sciences and New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA)

ISBN: (纸本)9798331314385

Antibody design, a crucial task with significant implications across various disciplines such as therapeutics and biology, presents considerable challenges due to its intricate nature. In this paper, we tackle antigen-specific antibody sequence-structure co-design as an optimization problem towards specific preferences, considering both rationality and functionality. Leveraging a pre-trained conditional diffusion model that jointly models sequences and structures of antibodies with equivariant neural networks, we propose direct energy-based preference optimization to guide the generation of antibodies with both rational structures and considerable binding affinities to given antigens. Our method involves fine-tuning the pre-trained diffusion model using a residue-level decomposed energy preference. Additionally, we employ gradient surgery to address conflicts between various types of energy, such as attraction and repulsion. Experiments on RAbD benchmark show that our approach effectively optimizes the energy of generated antibodies and achieves state-of-the-art performance in designing high-quality antibodies with low total energy and high binding affinity simultaneously, demonstrating the superiority of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Document-Level Relation Extraction via Pair-Aware and Entity-Enhanced Representation Learning 29

Document-Level Relation Extraction via Pair-Aware and Entity...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Huang, Xiusheng Yang, Hang Chen, Yubo Zhao, Jun Liu, Kang Sun, Weijian Zhao, Zuyu School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation CAS Beijing China Huawei Technologies Co. Ltd Shenzhen China Beijing Academy of Artificial Intelligence Beijing China

Document-level relation extraction aims to recognize relations among multiple entity pairs from a whole piece of article. Recent methods achieve considerable performance but still suffer from two challenges: a) the relational entity pairs are sparse, b) the representation of entity pairs is insufficient. In this paper, we propose Pair-Aware and Entity-Enhanced(PAEE) model to solve the aforementioned two challenges. For the first challenge, we design a Pair-Aware Representation module to predict potential relational entity pairs, which constrains the relation extraction to the predicted entity pairs subset rather than all pairs;For the second, we introduce a Entity-Enhanced Representation module to assemble directional entity pairs and obtain a holistic understanding of the entire document. Experimental results show that our approach can obtain state-of-the-art performance on four benchmark datasets DocRED, DWIE, CDR and GDA. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor 38

Everyday Object Meets Vision-and-Language Navigation Agent v...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Keji Chen, Kehan Bai, Jiawang Huang, Yan Wu, Qi Xia, Shu-Tao Wang, Liang Shandong University China New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Tencent China School of Computer Science University of Adelaide Australia Tsinghua Shenzhen International Graduate School Tsinghua University China

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore environments following natural language. The VLN agent, closely integrated into daily lives, poses a substantial threat to the security of privacy and property upon the occurrence of malicious behavior. However, this serious issue has long been overlooked. In this paper, we pioneer the exploration of an object-aware backdoored VLN, achieved by implanting object-aware backdoors during the training phase. Tailored to the unique VLN nature of cross-modality and continuous decision-making, we propose a novel backdoored VLN paradigm: IPR Backdoor. This enables the agent to act in abnormal behavior once encountering the object triggers during language-guided navigation in unseen environments, thereby executing an attack on the target scene. Experiments demonstrate the effectiveness of our method in both physical and digital spaces across different VLN agents, as well as its robustness to various visual and textual variations. Additionally, our method also well ensures navigation performance in normal scenarios with remarkable stealthiness. The code is available at https://***/Chenkehan21/VLN-ATT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mining High Quality patterns Using Multi-Objective Evolutionary Algorithm (Extended Abstract)

Mining High Quality Patterns Using Multi-Objective Evolution...

引用

International Conference on Data Engineering

作者： Wei Fang Qiang Zhang Jun Sun Xiaojun Wu International Joint Laboratory on Artificial Intelligence of Jiangsu Province Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

Most studies on pattern mining have considered only one pattern, such as frequent pattern or high-utility pattern, which is difficult to meet the increasingly diverse needs of users. In this paper, a novel multi-objective problem model for high quality pattern mining (HQPM) is proposed, where the objectives are support, occupancy, and utility. In order to solve the proposed three-objective problem efficiently, an improved multi-objective evolutionary algorithm for HQPM (MOEA-PM) is proposed with two kinds of population initialization strategies and an auxiliary tool. Experimental results on real-world datasets show that the proposed three-objective problem model with the MOEA-PM algorithm can discover patterns that are both frequently occurring and has a high utility in the transaction datasets, while at the same time being relatively complete. The proposed algorithm outperforms the state-of-the-art in terms of efficiency, quality, and convergence speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EACNet:Ensemble adversarial co-training neural network for handling missing modalities in MRI images for brain tumor segmentation

引用

Journal of Measurement Science and Instrumentation 2025年第1期16卷 11-25页

作者： RAMADHAN Amran Juma CHEN Jing PENG Junlan School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computing Intelligence Jiangnan UniversityWuxi 214122China

Brain tumor segmentation is critical in clinical diagnosis and treatment *** methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical *** methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality ***,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training *** work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing *** proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”***-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing *** model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation *** was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance ***,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing *** analysis suggests that the ensemble appr

关键词： deep learning magnetic resonance imaging(MRI) medical image analysis semantic segmentation segmentation accuracy image synthesis

来源：评论

学校读者我要写书评

暂无评论

Multi-view 3D Human Physique Dataset Construction For Robust Digital Human Modeling of Natural Scenes 8

Multi-view 3D Human Physique Dataset Construction For Robust...

引用

8th International Conference on Communication and Information Processing, ICCIP 2022

作者： Lin, Weitao Zhang, Jiguang Zhang, Zhaohui Xu, Shibiao Xu, Hao Zhang, Xiaopeng School of Artificial Intelligence University of Chinese Academy of Sciences China China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China Co. Ltd China

ISBN: (纸本)9781450397100

A large number of diverse data sets are necessary for networks to predict human body parameters and reconstruct 3D body models from images. Due to the high cost of motion capture and body scanning, high precision pose and body shape parameters are difficult to obtain. Meanwhile, existing datasets cannot meet the requirements in terms of diversity, size, and data accuracy for practical applications. Inspired by the construction schemes of various datasets, we design and construct a large multi-view 3D human body reconstruction dataset (3DMVHumanBP) with more types of supervised data. By recording the different poses of 25 women and 25 men in a green screen laboratory from six perspectives, we constructed a complete large multi-view 3D body posture dataset containing 340, 000 images. It is worth noting that, we innovatively propose a body dimension prior to the constrained human parametric model construction strategy to provide high-precision ground truth parameters of the human body SMPL models. In addition, we also designed a dense UV data generation method based on human body boundary and mask mapping to provide high-quality dense UV data, which more closely fits the features of the human images. It makes up for the defect that few existing data sets can only provide sparse UV data. In the experiment, the effectiveness and advantages of the data set constructed by us in network training are verified. Compared with the training of existing datasets, the mainstream network models trained on our datasets can significantly improve their prediction accuracy and robustness, thanks to the monitoring data of multiple kinds of high-precision human model parameters provided by 3DMVHumanBP. We hope that the human body dataset construction scheme we designed can provide ideas for building large-scale high precision human body datasets in the future. © 2022 Owner/Author.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Detailed Object Description with Controllable Dimensions

arXiv

引用

arXiv 2024年

作者： Wang, Xinran Zhang, Haiwen Li, Baoteng Liang, Kongming Sun, Hao He, Zhongjiang Ma, Zhanyu Guo, Jun Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China China Telecom Artificial Intelligence Technology Co. Ltd Beijing100034 China

Object description plays an important role for visually impaired individuals to understand and compare the differences between objects. Recent multimodal large language models (MLLMs) exhibit powerful perceptual abilities and demonstrate impressive potential for generating object-centric descriptions. However, the descriptions generated by such models may still usually contain a lot of content that is not relevant to the user intent or miss some important object dimension details. Under special scenarios, users may only need the details of certain dimensions of an object. In this paper, we propose a training-free object description refinement pipeline, Dimension Tailor, designed to enhance user-specified details in object descriptions. This pipeline includes three steps: dimension extracting, erasing, and supplementing, which decompose the description into user-specified dimensions. Dimension Tailor can not only improve the quality of object details but also offer flexibility in including or excluding specific dimensions based on user preferences. We conducted extensive experiments to demonstrate the effectiveness of Dimension Tailor on controllable object descriptions. Notably, the proposed pipeline can consistently improve the performance of the recent MLLMs. The code is currently accessible at https://***/xin-ran-w/ControllableObjectDescription. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

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：