检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hardware architecture design of HEVC entropy decoding

Hardware architecture design of HEVC entropy decoding

引用

IEEE International Conference on big data and Cloud computing (BdCloud)

作者： Shiyu Wang Shengbing Zhang Jihe Wang Libo Chang Liangyou Feng Xiaoya Fan Engineering Research Center of Embedded System Integration Ministry of Education School of Computer Science Northwestern Polytechnical University Xian China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xian China

As the latest generation of digital video coding standard, HEVC has technically optimized multiple modules such as related frame prediction, block processing and entropy coding in the frequency coding and decoding framework. However, flexible and efficient coding algorithms make the amount of calculation in the video decoding and reconstruction process increase dramatically. The energy efficiency of traditional processors is limited, and the decoding calculation process is difficult to meet the current needs of ultra-high-definition video playback. For the most important and time-consuming bitstream analysis and entropy decoding part of the HEVC decoding process, a new hardware architecture strategy is provided, which can effectively improve the HEVC decoding performance. In this paper, the designed data access module, bitstream analysis and entropy decoding unit are simulated and verified. Build an FPGA verification platform, and use the main tier standard test sequence to simulate and verify the designed hardware acceleration architecture. The experimental results show that the hardware architecture of bitstream analysis and entropy decoding designed in this paper can reach the functions and performance indicators specified by the HEVC standard Level-4 main tier, and the bitstream analysis acceleration effect is good. This thesis aims at the current HEVC decoding calculation characteristics, and through the design of hardware architecture verification, it provides new solutions and hardware architecture ideas for subsequent HEVC encoding and decoding performance optimization.

关键词： Analytical models Program processors Video sequences Bit rate Syntactics Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion

arXiv

引用

arXiv 2020年

作者： Wang, Dong Bai, Yunpeng Li, Ying School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xian China School of Computing and Information Systems University of Melbourne VIC3010 Australia

Multispectral pan-sharpening aims at producing a high resolution (HR) multispectral (MS) image in both spatial and spectral domains by fusing a panchromatic (PAN) image and a corresponding MS image. In this paper, we propose a novel dual-channel network (DCNet) framework for MS pan-sharpening. In our DCNet, the dual-channel backbone involves a spatial channel to capture spatial information with a 2D CNN, and a spectral channel to extract spectral information with a 3D CNN. This heterogeneous 2D/3D CNN architecture can minimize causing spectral information distortion, which typically happens in conventional 2D CNN models. In order to fully integrate the spatial and spectral features captured from different levels, we introduce a multi-level fusion strategy. Specifically, a spatial-spectral CLSTM (S2-CLSTM) module is proposed for fusing the hierarchical spatial and spectral features, which can effectively capture correlations among multi-level features. The S2-CLSTM module attaches two fusion ways: the intra-level fusion via bi-directional lateral connections and inter-level fusion via the cell state in the S2-CLSTM. Finally, the ideal HR-MS image is recovered by a reconstruction module. Extensive experiments have been conducted at both simulated lower scale and the original scale of real-world datasets. Compared with the state-of-the-art methods, the proposed DCNet achieves superior or competitive performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Regression Network for Dental Implant Position Prediction

arXiv

引用

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

arXiv

引用

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Transformer for Accelerated MR Imaging

arXiv

引用

arXiv 2021年

作者： Feng, Chun-Mei Yan, Yunlu Chen, Geng Xu, Yong Hu, Ying Shao, Ling Fu, Huazhu Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Terminus Group China Institute of High Performance Computing A*STAR Singapore138632 Singapore

Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging. To capture deep multi-modal information, our MTrans utilizes an improved multi-head attention mechanism, named cross attention module, which absorbs features from the auxiliary modality that contribute to the target modality. Our framework provides three appealing benefits: (i) Our MTrans use an improved transformers for multi-modal MR imaging, affording more global information compared with existing CNN-based methods. (ii) A new cross attention module is proposed to exploit the useful information in each modality at different scales. The small patch in the target modality aims to keep more fine details, the large patch in the auxiliary modality aims to obtain high-level context features from the larger region and supplement the target modality effectively. (iii) We evaluate MTrans with various accelerated multi-modal MR imaging tasks, e.g., MR image reconstruction and super-resolution, where MTrans outperforms state-of-the-art methods on fastMRI and real-world clinical datasets. © 2021, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Hiding Scrambling Text Message in Speech Signal Based on Lightwight Hyperchaotic Map and Conditional Lsb Mechanisms

SSRN

引用

SSRN 2023年

作者： Al Sibahee, Mustafa A. Abduljaleel, Iman Qays Luo, Chengwen Zhang, Jin Huang, Yijing Abduljabbar, Zaid Ameen Ma, Junchao National Engineering Laboratory for Big Data System Computing Technology Shenzhen Technology University 518060 China Department of Computer Science College of Computer Science and Information Technology University of Basrah 61004 Iraq College of Computer Science and Software Engineering Shenzhen University 518060 China Department of Computer Science College of Education for Pure Sciences University of Basrah Basrah61004 Iraq Technical Computer Engineering Department Al-kunooze University College Basrah61001 Iraq Huazhong University of Science and Technology Shenzhen Institute Shenzhen518118 China College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China

This study proposed a lightweight and secure audio steganography system for hiding text messages during transmission over the Internet to address the computational cost exaggeration, and Insufficient levels of security in earlier studies. The paper proposes a two-phase functioning mechanism. Text characters are transformed into ASCII code and then stored in a vector, which is then divided into three sub-vectors. The sub-vectors are scrambled using a two low complexity operation, namely a forwardbackward reading technique and an odd-even index. Two scrambling circuits can be performed: the first on tiny sub-vectors and another on the vector as a whole. In the hiding phase, the speech signal samples were divided into 256 blocks using only 200 values per block, and low complexity Quadratic and the Hénon maps to hide the speech signal in a random manner. This method utilizes the conditional LSB as low complexity algorithm to identify hidden bits and a special hyperchaotic map algorithm for randomly choosing locations. The proposed approach provides good security for a scrambled text message with high SNR and PSNR, small MSE error and PESQ, SSIM near one, BER close to zero, and MOS near five as well as the lowest computational hiding cost. © 2023, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Service Decomposition method for multimodal data exchange scenarios

Service Decomposition method for multimodal data exchange sc...

引用

Computer Science and Management technology (ICCSMT), International Conference on

作者： Deyou Jiang Lei Huang Hanyu Tian Yujie Xie Xiaoming Li School of Economics and Management Beijing Jiaotong University Beijing China National Engineering Laboratory of Comprehensive Transportation Big Data Application Technology Beijing Jingwei Information Technologies Limited Company Beijing China China Academy of Railway Sciences Institute of Computing Technologies Beijing China

Influenced by the complexity of multimodal data exchange scenarios and their differences in data flow graph construction, the objective basis of existing service decomposition methods is not sufficient, and the granularity of the results is too large and difficult to be decomposed. To address this problem, this paper presents a service decomposition method for multimodal data exchange scenarios. This method reconstructs the differentially constructed data flow diagram by unified rules at the stage of requirement analysis and design, and then completes the fine-grained division of microservices around documents based on service-decomposed rules. The case study shows that the method is more effective than the existing method in the multimodal data exchange scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generation and manipulation of chiral terahertz waves in the three-dimensional topological insulator Bi2Te3

引用

Advanced Photonics 2020年第6期2卷 14-22页

作者： Haihui Zhao Xinhou Chen Chen Ouyang Hangtian Wang Deyin Kong Peidi Yang Baolong Zhang Chun Wang Gaoshuai Wei Tianxiao Nie Weisheng Zhao Jungang Miao Yutong Li Li Wang Xiaojun Wu Beihang University Fert Beijing InstituteAdvanced Innovation Center for Big Data and Brain ComputingSchool of MicroelectronicsBeijingChina Beihang University School of Electronic and Information EngineeringBeijingChina Chinese Academy of Sciences Institute of PhysicsBeijing National Laboratory for Condensed Matter PhysicsBeijingChina University of Chinese Academy of Sciences School of Physical SciencesBeijingChina Beihang University Beihang-Goertek Joint Microelectronics InstituteQingdao Research InstituteQingdaoChina Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyChina

Arbitrary manipulation of broadband terahertz waves with flexible polarization shaping at the source has great potential in expanding numerous applications,such as imaging,information encryption,and all-optical coherent control of terahertz nonlinear *** insulators featuring unique spinmomentum-locked surface state have already exhibited very promising prospects in terahertz emission,detection,and modulation,which may lay a foundation for future on-chip topological insulator-based terahertz ***,polarization-shaped terahertz emitters based on topological insulators with an arbitrarily manipulated temporal evolution of the amplitude and the electric-field vector direction have not yet been *** systematically investigated the terahertz radiation from topological insulator Bi2Te3 nanofilms driven by femtosecond laser pulses and successfully realized the generation of efficient chiral terahertz waves with controllable chirality,ellipticity,and principal *** convenient engineering of the chiral terahertz waves was interpreted by a photogalvanic effect(PGE)-induced photocurrent,while the linearly polarized terahertz waves originated from linear PGE-induced shift *** work not only provides further understanding of femtosecond coherent control of ultrafast spin currents but also describes an effective way to generate spin-polarized terahertz waves at the source.

关键词： spin-polarized terahertz manipulation topological insulator photogalvanic effect

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training

arXiv

引用

arXiv 2024年

作者： Tao, Ruijie Qian, Xinyuan Das, Rohan Kumar Gao, Xiaoxue Wang, Jiadong Li, Haizhou The Department of Electrical and Computer Engineering National University of Singapore Singapore The Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China Fortemedia Singapore138637 Singapore Institute for Infocomm Research A*STAR Singapore The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The University of Bremen 28359 Germany

Audio-visual active speaker detection (AV-ASD) aims to identify which visible face is speaking in a scene with one or more persons. Most existing AV-ASD methods prioritize capturing speech-lip correspondence. However, there is a noticeable gap in addressing the challenges from real-world AV-ASD scenarios. Due to the presence of low-quality noisy videos in such cases, AV-ASD systems without a selective listening ability are short of effectively filtering out disruptive voice components from mixed audio inputs. In this paper, we propose a Multi-modal Speaker Extraction-to-Detection framework named ‘MuSED’, which is pre-trained with audio-visual target speaker extraction to learn the denoising ability, then it is fine-tuned with the AV-ASD task. Meanwhile, to better capture the multi-modal information and deal with real-world problems such as missing modality, MuSED is modelled on the time domain directly and integrates the multi-modal plus-and-minus augmentation strategy. Our experiments demonstrate that MuSED substantially outperforms the state-of-the-art AV-ASD methods and achieves 95.6% mAP on the AVA-ActiveSpeaker dataset, 98.3% AP on the ASW dataset, and 97.9% F1 on the Columbia AV-ASD dataset, respectively. We will publicly release the code in due course. © 2024, CC BY.

关键词： Extraction

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：