检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Luo, Cheng Song, Siyang Xie, Weicheng Spitale, Micol Ge, Zongyuan Shen, Linlin Gunes, Hatice Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Science University of Nottingham Ningbo China Ningbo315100 China Computer Sciences University of Exeter ExeterEX4 4PY United Kingdom Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Airdoc-Monash Research Centre Monash University Faculty of IT Monash University Melbourne Australia

In dyadic interaction, predicting the listener’s facial reactions is challenging as different reactions could be appropriate in response to the same speaker’s behaviour. Previous approaches predominantly treated this task as an interpolation or fitting problem, emphasizing deterministic outcomes but ignoring the diversity and uncertainty of human facial reactions. Furthermore, these methods often failed to model short-range and long-range dependencies within the interaction context, leading to issues in the synchrony and appropriateness of the generated facial reactions. To address these limitations, this paper reformulates the task as an extrapolation or prediction problem, and proposes an novel framework (called ReactFace) to generate multiple different but appropriate facial reactions from a speaker behaviour rather than merely replicating the corresponding listener facial behaviours. Our ReactFace generates multiple different but appropriate photo-realistic human facial reactions by: (i) learning an appropriate facial reaction distribution representing multiple different but appropriate facial reactions;and (ii) synchronizing the generated facial reactions with the speaker verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker’s behaviour. The quality of the generated facial reactions is intimately tied to the speaker’s speech and facial expressions, achieved through our novel speaker-listener interaction modules. Our code is made publicly available at https://***/lingjivoo/ReactFace. Copyright © 2023, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

MixSignGraph: A Sign Sequence is Worth Mixed Graphs of Nodes

arXiv

引用

arXiv 2025年

作者： Gan, Shiwei Yin, Yafeng Jiang, Zhiwei Wen, Hongkai Xie, Lei Lu, Sanglu State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Department of Computer Science University of Warwick CoventryCV4 7AL United Kingdom

—Recent advances in sign language research have benefited from CNN-based backbones, which are primarily transferred from traditional computer vision tasks (e.g., object identification, image recognition). However, these CNN-based backbones usually excel at extracting features like contours and texture, but may struggle with capturing sign-related features. In fact, sign language tasks require focusing on sign-related regions, including the collaboration between different regions (e.g., left hand region and right hand region) and the effective content in a single region. To capture such region-related features, we introduce MixSignGraph, which represents sign sequences as a group of mixed graphs and designs the following three graph modules for feature extraction, i.e., Local Sign Graph (LSG) module, Temporal Sign Graph (TSG) module and Hierarchical Sign Graph (HSG) module. Specifically, the LSG module learns the correlation of intra-frame cross-region features within one frame, i.e., focusing on spatial features. The TSG module tracks the interaction of inter-frame cross-region features among adjacent frames, i.e., focusing on temporal features. The HSG module aggregates the same-region features from different-granularity feature maps of a frame, i.e., focusing on hierarchical features. In addition, to further improve the performance of sign language tasks without gloss annotations, we propose a simple yet counter-intuitive Text-driven CTC Pre-training (TCP) method, which generates pseudo gloss labels from text labels for model pretraining. Extensive experiments conducted on current five public sign language datasets demonstrate the superior performance of the proposed model. Notably, our model surpasses the SOTA models on multiple sign language tasks across several datasets, without relying on any additional cues. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Customized Transformer Adapter with Frequency Masking for Deepfake Detection

引用

IEEE Transactions on Information Forensics and Security 2025年

作者： Shi, Zenan Chen, Haipeng Jia, Yixin Zhang, Dong Lu, Wei Yang, Xun Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Jilin University College of Software Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Sun Yat-sen University School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China

The evolution of advanced artificial intelligence generated content approaches has heightened concerns about deepfake, due to the sophisticated forgeries and concealed appearances they produce. To this end, the pre-trained Vision Transformer (ViT) model has become a de facto choice for deepfake detection, thanks to its powerful learning capability. Despite favorable results achieved by existing ViT-based methods, they have inherent limitations that could result in suboptimal performance in scenarios with continuously evolving forgery techniques, such as overfitting to single forgery patterns or placing excessive emphasis on dominant forgery regions. In this paper, we propose CUTA, a simple yet effective deepfake detection paradigm that utilizes ViT adapters as the medium and fully exploits the spatial- and frequency-domain features of given images to overcome the limitations of existing methods. Specifically, CUTA focuses on frequency domain masking within the input space, which obscures parts of the high-frequency image to intensify the training challenge while preserving subtle forgery cues in the frequency domain to facilitate comprehensive forgery representations. Furthermore, we propose two task-customized modules within the ViT model, i.e., the texture enhancement module and the multi-scale perceptron module, to seamlessly integrate local texture and rich contextual features. These two modules ensure an organic interaction between the task-specific forgery patterns and general semantic features within the pre-trained ViT framework. The experimental results on several publicly available benchmark datasets demonstrate CUTA’s superiority in performance, particularly showcasing its significant advantages in both cross-dataset and cross-manipulation scenarios. 2005-2012 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Quantum circuit architecture search on a superconducting processor

arXiv

引用

arXiv 2022年

作者： Linghu, Kehuan Qian, Yang Wang, Ruixia Hu, Meng-Jun Li, Zhiyuan Li, Xuegang Xu, Huikai Zhang, Jingning Ma, Teng Zhao, Peng Liu, Dong E. Hsieh, Min-Hsiu Wu, Xingyao Du, Yuxuan Tao, Dacheng Jin, Yirong Yu, Haifeng Beijing Academy of Quantum Information Sciences Beijing100193 China School of Computer Science Faculty of Engineering University of Sydney Australia JD Explore Academy State Key Laboratory of Low Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney Australia

Variational quantum algorithms (VQAs) have shown strong evidences to gain provable computational advantages for diverse fields such as finance, machine learning, and chemistry. However, the heuristic ansatz exploited in modern VQAs is incapable of balancing the tradeoff between expressivity and trainability, which may lead to the degraded performance when executed on the noisy intermediate-scale quantum (NISQ) machines. To address this issue, here we demonstrate the first proof-of-principle experiment of applying an efficient automatic ansatz design technique, i.e., quantum architecture search (QAS), to enhance VQAs on an 8-qubit superconducting quantum processor. In particular, we apply QAS to tailor the hardware-efficient ansatz towards classification tasks. Compared with the heuristic ansätze, the ansatz designed by QAS improves test accuracy from 31% to 98%. We further explain this superior performance by visualizing the loss landscape and analyzing effective parameters of all ansätze. Our work provides concrete guidance for developing variable ansätze to tackle various large-scale quantum learning problems with advantages. Copyright © 2022, The Authors. All rights reserved.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Face-sketch learning with human sketch-drawing order enforcement

引用

science China(Information sciences) 2020年第11期63卷 298-311页

作者： Liang CHANG Lihua JIN Lifen WENG Wentao CHAO Xuguang WANG Xiaoming DENG Qiulei DONG School of Artificial Intelligence Beijing Normal University Department of Design Art Xiamen University of Technology Department of Automation North China Electric Power University Beijing Key Laboratory of Human Computer Interactions Institute of Software Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

Dear editor,Although face-sketch synthesis generates a sketch from a given face photo automatically [1], it is an open research problem in computer vision [2–4]. Recently, several deep neural network (DNN)methods for... 详细信息

关键词： face sketch synthesis deep neural network order enforcement image synthesis generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Ensuring Privacy and Correlation Awareness in Multi-Dimensional Service Quality Prediction and Recommendation for Iot

SSRN

引用

SSRN 2024年

作者： Zhong, Weiyi Fang, Wei Zhao, Yifan Wang, Sifeng Yan, Chao Jiang, Rong Khan, Maqbool Yang, Xuan Rafique, Wajid Qufu Normal University School of Engineering Rizhao276800 China Qufu Normal University School of Computer Science Rizhao276800 China Weifang University of Science and Technology Weifang262700 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650000 China Software Competence Center Hagenberg Upper Austria 4232 Austria Angeles University Foundation Pampanga2009 Philippines University of Calgary Department of Electrical and Software Engineering CalgaryT2N 1N4 Canada

Edge computing, with its advantages in terms of lightweight data transmission between users and cloud platforms, has become a promising solution for alleviating the heavy burden of timely data processing in many IoT scenarios, such as smart commerce and wise medicine. While several challenges are raised when we fuse the multiple-source IoT data recorded by different edge servers. First of all, data repetition within each edge server can greatly reduce the efficiency of various edge-based smart applications. Besides, IoT data fusion associated with multiple distributed edge servers can compromise user privacy. In addition, the multi-dimensional and interrelated nature of IoT data complicates precise data mining and analysis. To tackle these issues, a novel edge data fusion method (named TLTM) for cross-platform service recommendation is brought forth, which considers data dimensions, data correlation, and data privacy simultaneously. At last, to validate the effectiveness and efficiency of the TLTM method, we have designed massive experiments on the popular WS-DREAM dataset. The reported experimental results show that our TLTM method is superior to other related methods in terms of popular performance metrics including MAE, RMSE, Precision, Recall, F1-Score, and Time cost. © 2024, The Authors. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

MetaGCD: Learning to Continually Learn in Generalized Category Discovery

arXiv

引用

arXiv 2023年

作者： Wu, Yanan Chi, Zhixiang Wang, Yang Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Electrical and Computer Engineering University of Toronto TorontoM5G1V7 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method. Our code is available at https://***/ynanwu/MetaGCD. © 2023, CC0.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Semantic Prior Distillation with Vision Foundation Model for Enhanced Rapid Bone Scintigraphy Image Restoration

arXiv

引用

arXiv 2025年

作者： Liang, Pengchen Shi, Leijun Yao, Huiping Pu, Bin Chen, Jianguo Zhao, Lei Huang, Haishan Chen, Zhuangzhuang Xu, Zhaozhao Xu, Lite Chang, Qing Li, Yiwei Department of Nuclear Medicine Shanghai Children’s Hospital School of Medicine Shanghai Jiao Tong University Shanghai200062 China School of Microelectronics Shanghai University Shanghai201800 China Department of Ophthalmology Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai201800 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology 999077 Hong Kong School of Software Engineering Sun Yat-sen University Guangdong Province Zhuhai519000 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Computer Science and Technology Henan Polytechnic University Henan Jiaozuo454000 China Department Shanghai Key Laboratory of Gastric Neoplasms Department of Surgery Shanghai Institute of Digestive Surgery Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai201800 China

Rapid bone scintigraphy is an essential tool for diagnosing skeletal diseases and tumor metastasis in pediatric patients, as it reduces scan time and minimizes patient discomfort. However, rapid scans often result in poor image quality, potentially affecting diagnosis due to reduced resolution and detail, which make it challenging to identify and evaluate finer anatomical structures. To address this issue, we propose the first application of SAM-based semantic priors for medical image restoration, leveraging the Segment Anything Model (SAM) to enhance rapid bone scintigraphy images in pediatric populations. Our method comprises two cascaded networks, fIR1 and fIR2, augmented by three key modules: a Semantic Prior Integration (SPI) module, a Semantic Knowledge Distillation (SKD) module, and a Semantic Consistency Module (SCM). The SPI and SKD modules incorporate domain-specific semantic information from a fine-tuned SAM, while the SCM maintains consistent semantic feature representation throughout the cascaded networks. In addition, we will release a novel Rapid Bone Scintigraphy dataset called RBS, the first dataset dedicated to rapid bone scintigraphy image restoration in pediatric patients. RBS consists of 137 pediatric patients aged between 0.5 and 16 years who underwent both standard and rapid bone scans. The dataset includes scans performed at 20 cm/min (standard) and 40 cm/min (rapid), representing a 2× acceleration. We conducted extensive experiments on both the publicly available endoscopic dataset and RBS. The results demonstrate that our method outperforms all existing methods across various metrics, including PSNR, SSIM, FID, and LPIPS. Copyright © 2025, The Authors. All rights reserved.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

Mamba4SOD: RGB-T Salient Object Detection Using Mamba-Based Fusion Module

引用

IET computer Vision 2025年第1期19卷

作者： Yi Xu Ruichao Hou Ziheng Qi Tongwei Ren State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Champaign Illinois USA

RGB and thermal salient object detection (RGB-T SOD) aims to accurately locate and segment salient objects in aligned visible and thermal image pairs. However, existing methods often struggle to produce complete masks and sharp boundaries in challenging scenarios due to insufficient exploration of complementary features from the dual modalities. In this paper, we propose a novel mamba-based fusion network for RGB-T SOD task, named Mamba4SOD, which integrates the strengths of Swin Transformer and Mamba to construct robust multi-modal representations, effectively reducing pixel misclassification. Specifically, we leverage Swin Transformer V2 to establish long-range contextual dependencies and thoroughly analyse the impact of features at various levels on detection performance. Additionally, we develop a novel Mamba-based fusion module with linear complexity, boosting multi-modal enhancement and fusion. Experimental results on VT5000, VT1000 and VT821 datasets demonstrate that our method outperforms the state-of-the-art RGB-T SOD methods.

关键词： Mamba RGB and thermal salient object detection state space mode Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Inconsistency-aware uncertainty estimation for semi-supervised medical image segmentation

arXiv

引用

arXiv 2021年

作者： Shi, Yinghuan Zhang, Jian Ling, Tong Lu, Jiwen Zheng, Yefeng Yu, Qian Qi, Lei Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China Department of Automation Tsinghua University China Tencent Jarvis Lab China School of Data and Computer Science Shandong Women’s University China School of Computer Science and Engineering Southeast University Nanjing211189 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210046 China

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel method of estimating uncertainty. We observe that, when assigned different misclassification costs in a certain degree, if the segmentation result of a pixel becomes inconsistent, this pixel shows a relative uncertainty in its segmentation. Therefore, we present a new semi-supervised segmentation model, namely, conservative-radical network (CoraNet in short) based on our uncertainty estimation and separate self-training strategy. In particular, our CoraNet model consists of three major components: a conservative-radical module (CRM), a certain region segmentation network (C-SN), and an uncertain region segmentation network (UC-SN) that could be alternatively trained in an end-to-end manner. We have extensively evaluated our method on various segmentation tasks with publicly available benchmark datasets, including CT pancreas, MR endocardium, and MR multi-structures segmentation on the ACDC dataset. Compared with the current state of the art, our CoraNet has demonstrated superior performance. In addition, we have also analyzed its connection with and difference from conventional methods of uncertainty estimation in semi-supervised medical image segmentation. Copyright © 2021, The Authors. All rights reserved.

关键词： Pixels

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：