检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

Fast Candidate Region Extraction for SAR Ship Target 37

Fast Candidate Region Extraction for SAR Ship Target

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Zhang, Panpan Luo, Haibo Xu, Zheng He, Miao Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China The Key Lab of Image Understanding and Computer Vision Shenyang110016 China

ISBN: (纸本)9781665465366

At present, deep learning technology is widely used in ship target detection in synthetic aperture radar (SAR) images. However, high-resolution remote sensing SAR images cover a larger area and have larger image sizes. To be able to use the deep learning model for training and testing, the image needs to be cropped to the appropriate size. In a high-resolution SAR ship image, the ship target usually takes only a small part of the whole image. As a result, only part of the cropped image contains the target, and most of the rest are background regions. This will cause a lot of computational redundancy in the model inference stage. To solve this problem, a fast candidate region extraction algorithm is proposed in this paper for ship target extraction. The algorithm consists of three parts: firstly, extract the saliency map of the SAR ship image, secondly, perform median filtering on the segmented image, and thirdly, extract candidate regions. The superiority of the algorithm was demonstrated by experiments on the AIR-SARShip-1.0 dataset. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Evading Detection Actively: Toward Anti-Forensics against Forgery Localization

arXiv

引用

arXiv 2023年

作者： Zhuo, Long Luo, Shenghai Tan, Shunquan Chen, Han Li, Bin Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Anti-forensics seeks to eliminate or conceal traces of tampering artifacts. Typically, anti-forensic methods are designed to deceive binary detectors and persuade them to misjudge the authenticity of an image. However, to the best of our knowledge, no attempts have been made to deceive forgery detectors at the pixel level and mis-locate forged regions. Traditional adversarial attack methods cannot be directly used against forgery localization due to the following defects: 1) they tend to just naively induce the target forensic models to flip their pixel-level pristine or forged decisions;2) their anti-forensics performance tends to be severely degraded when faced with the unseen forensic models;3) they lose validity once the target forensic models are retrained with the anti-forensics images generated by them. To tackle the three defects, we propose SEAR (Self-supErvised Anti-foRensics), a novel self-supervised and adversarial training algorithm that effectively trains deep-learning anti-forensic models against forgery localization. SEAR sets a pretext task to reconstruct perturbation for self-supervised learning. In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces. We have conducted large-scale experiments across diverse datasets. The experimental results demonstrate that, through the combination of self-supervised learning and adversarial learning, SEAR successfully deceives the state-of-the-art forgery localization methods, as well as tackle the three defects regarding traditional adversarial attack methods mentioned above. Copyright © 2023, The Authors. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Network Analysis:Classifying and Visualizing Geologic Hazard Reports

引用

Journal of Earth Science 2024年第4期35卷 1289-1303页

作者： Wenjia Li Liang Wu Xinde Xu Zhong Xie Qinjun Qiu Hao Liu Zhen Huang Jianguo Chen School of Geography and Information Engineering China University of GeosciencesWuhan430078China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan430078China School of Computer Science China University of GeosciencesWuhan430078China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen518034China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China Wuhan Geomatics Institute Wuhan430074China Faculty of Earth Resources China University of GeosciencesWuhan430074China

If progress is to be made toward improving geohazard management and emergency decision-making,then lessons need to be learned from past geohazard information.A geologic hazard report provides a useful and reliable source of information about the occurrence of an event,along with detailed information about the condition or factors of the *** such reports,however,can be a challenging process because these texts are often presented in unstructured long text formats,and contain rich specialized and detailed *** text classification is commonly used to mine disaster text data in open domains(e.g.,news and microblogs).But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse *** deficiencies are most obviously exposed in long text ***,this paper uses the bidirectional encoder representations from Transformers(BERT),to model long ***,utilizing a softmax layer to automatically extract text features and classify geohazards without manual *** latent Dirichlet allocation(LDA)model is used to examine the interdependencies that exist between causal variables to visualize *** proposed method is useful in enabling the machine-assisted interpretation of text-based ***,it can help users visualize causes,processes,and other geohazards and assist decision-makers in emergency responses.

关键词： geologic hazard network analysis latent dirichlet allocation text classification deep learning

来源：评论

学校读者我要写书评

暂无评论

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

arXiv

引用

arXiv 2025年

作者： Lai, Song Zhao, Zhe Zhu, Fei Lin, Xi Zhang, Qingfu Meng, Gaofeng Department of Computer Science City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China City University of Hong Kong Shenzhen Research Institute Hong Kong University of Science and Technology of China China

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience replay methods, which store and replay past data alongside new data, have become a widely adopted approach to mitigate catastrophic forgetting. However, these methods neglect the dynamic nature of the stability-plasticity trade-off and aim to find a fixed and unchanging balance, resulting in suboptimal adaptation during training and inference. In this paper, we propose Pareto Continual Learning (ParetoCL), a novel framework that reformulates the stability-plasticity trade-off in continual learning as a multi-objective optimization (MOO) problem. ParetoCL introduces a preference-conditioned model to efficiently learn a set of Pareto optimal solutions representing different trade-offs and enables dynamic adaptation during inference. From a generalization perspective, ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity. Extensive experiments across multiple datasets and settings demonstrate that ParetoCL outperforms state-of-the-art methods and adapts to diverse continual learning scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Which One is Better? Self-supervised Temporal Coherence Learning for Skeleton Based Action Recognition

Which One is Better? Self-supervised Temporal Coherence Lear...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Bizhu Wu Mingyan Wu Haoqin Ji Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

ISBN: (纸本)9781665463959

Recently, researchers have achieved significant results in the skeleton based action recognition task. To better model the skeleton sequences, existing methods learned the feature representations in the self-supervised setting by solving pretext tasks, such as predicting the order of a shuffled skeleton sequence or verifying whether a given skeleton sequence is shuffled or not. However, these pretext tasks are either too challenging or too easy for the encoder to obtain a proper skeleton representation for action recognition. Therefore, we propose a novel self-pretraining pretext task, Which One Is Better (WOIB), to identify which one is more temporally coherent, given two shuffled skeleton sequences. Experiments on the NTU RGB+D, NTU RGB+D 120, and Kinetics-Skeleton datasets with different network architectures show significant improvements in recognition accuracy, demonstrating that such a well-designed pretext task is general and able to drive the encoder to learn more discriminative representations.

关键词： Biometrics (access control) Coherence Predictive models Network architecture Drives Benchmark testing Skeleton

来源：评论

学校读者我要写书评

暂无评论

Translate the facial regions you like using region-wise normalization

arXiv

引用

arXiv 2020年

作者： Liu, Wenshuang Chen, Wenting Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

Though GAN (Generative Adversarial Networks) based technique has greatly advanced the performance of image synthesis and face translation, only few works available in literature provide region based style encoding and translation. We propose in this paper a region-wise normalization framework, for region level face translation. While per-region style is encoded using available approach, we build a so called RIN (region-wise normalization) block to individually inject the styles into per-region feature maps and then fuse them for following convolution and upsampling. Both shape and texture of different regions can thus be translated to various target styles. A region matching loss has also been proposed to significantly reduce the inference between regions during the translation process. Extensive experiments on three publicly available datasets, i.e. Morph, RaFD and CelebAMask-HQ, suggest that our approach demonstrate a large improvement over state-of-the-art methods like StarGAN, SEAN and FUNIT. Our approach has further advantages in precise control of the regions to be translated. As a result, region level expression changes and step by step make up can be achieved. The video demo is available at https://***/ceRqsbzXAfk. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Face Attributes Recognition Using Spatial Transformer Network

Deep Face Attributes Recognition Using Spatial Transformer N...

引用

IEEE International Conference on Information and Automation

作者： Lianzhi Tan Zhifeng Li Qiao Yu Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9781509041039

-Face alignment is very crucial to the task of face attributes recognition. The performance of face attributes recognition would notably degrade if the fiducial points of the original face images are not precisely detected due to large lighting, pose and occlusion variations. In order to alleviate this problem, we propose a spatial transform based deep CNNs to improve the performance of face attributes recognition. In this approach, we first learn appropriate transformation parameters by a carefully designed spatial transformer network called LoNet to align the original face images, and then recognize the face attributes based on the aligned face images using a deep network called CINet. To the best of our knowledge, this is the first attempt to use spatial transformer network in face attributes recognition task. Extensive experiments on two large and challenging databases (CelebA and LFWA) clearly demonstrate the effectiveness of the proposed approach over the current state-of-the-art.

关键词： Face Attribute Recognition Spatial Transformer Network Face Alignment

来源：评论

学校读者我要写书评

暂无评论

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAS-YNU multi-modal cross-view human action dataset

CAS-YNU multi-modal cross-view human action dataset

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Zhao, Qingsong Cheng, Jun Tao, Dapeng Ji, Xiaopeng Wang, Lei Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences China Chinese University of Hong Kong Hong Kong School of Information Science and Engineering Yunnan University China

ISBN: (纸本)9781538680698

Human action recognition is a hot research topic in computer vision, which has extensive applications including human-computer interaction, robot and surveillance. Some outstanding human action datasets have been published. However, they still have some defects, such as the limited modality types, camera views, complexity of scene and action categories. Furthermore, most of them are devised for a subset of the action recognition, such as single-modal recognition and single-view recognition. In this paper, we propose a multi-modal cross-view human action dataset (named CAS-YNU MCHAD). It consists of five synchronous data modalities, including RGB image, depth maps, human segment maps, skeleton data and inertial data. Our dataset contains 14782 action samples from 50 subjects and 10 actions in two perspectives. Extensive benchmark experiments on this dataset are conducted with the state-of-the-art recognition approaches. Experimental results illustrate that it is challenging on cross-view action recognition. We also provide the baseline for the assessment of existing recognition methods. © 2018 IEEE.

关键词： Human computer interaction

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：