检索结果-内蒙古大学图书馆

Context-aware Multi-level Question Embedding Fusion for visual question answering

information Fusion 2024年 102卷

作者： Li, Shengdong Gong, Chen Zhu, Yuqing Luo, Chuanwen Hong, Yi Lv, Xueqiang School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Zhejiang Lab Zhejiang Hangzhou311121 China Department of Computer Science California State University Los Angeles CA90032 United States School of Information Science and Technology Beijing Forestry University Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration 100083 China Beijing Key Laboratory of Internet Culture and Digital Dissemination Research Beijing Information Science and Technology University 100101 China

Question model has been widely concerned as the cornerstone of constructing Visual Question Answering (VQA) models. Existing question models attempt to exploit word context to extract multi-level concepts for modeling multi-level questions. However, they still have many defects. For example, most question models utilize simple fusion methods to fuse shallow modules and extract parameter-unshared low-level concepts, leading to poor modeling of multi-level questions;although some question models use deep bidirectional Transformer encoder in external knowledge transfer and BERT for multi-level questions, their complexity is still high. To solve these issues, we propose a novel low-complex multi-level contextual question model, termed Context-aware Multi-level Question Embedding Fusion (CMQEF). We formalize its concepts and theories, deduce its modeling process, optimization process and feature extraction process, analyze its low complexity and high expressiveness, and prove that it defines a new way to solve parameter non-sharing for extracting parameter-shared multi-level concepts and optimize the tradeoff between expressiveness and complexity in question models. Extensive experiments on VQAv2 and VQA-CPv2 validate that comparing with the state-of-the-art, our CMQEF outperforms it on SANs and UpDn, reduces the language priors of SANs and UpDn, and has preferable interpretability and applicability. Our code is available at https://***/lsdruc/CMQEF-for-VQA. © 2023 The Author(s)

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Self-Mutual Distillation Learning for Continuous Sign Language Recognition

Self-Mutual Distillation Learning for Continuous Sign Langua...

引用

International Conference on Computer Vision (ICCV)

作者： Aiming Hao Yuecong Min Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665428132

In recent years, deep learning moves video-based Continuous Sign Language Recognition (CSLR) significantly forward. Currently, a typical network combination for CSLR includes a visual module, which focuses on spatial and short-temporal information, followed by a contextual module, which focuses on long-temporal information, and the Connectionist Temporal Classification (CTC) loss is adopted to train the network. However, due to the limitation of chain rules in back-propagation, the visual module is hard to adjust for seeking optimized visual features. As a result, it enforces that the contextual module focuses on contextual information optimization only rather than balancing efficient visual and contextual information. In this paper, we propose a Self-Mutual Knowledge Distillation (SMKD) method, which enforces the visual and contextual modules to focus on short-term and long-term information and enhances the discriminative power of both modules simultaneously. Specifically, the visual and contextual modules share the weights of their corresponding classifiers, and train with CTC loss simultaneously. Moreover, the spike phenomenon widely exists with CTC loss. Although it can help us choose a few of the key frames of a gloss, it does drop other frames in a gloss and makes the visual feature saturation in the early stage. A gloss segmentation is developed to relieve the spike phenomenon and decrease saturation in the visual module. We conduct experiments on two CSLR bench-marks: PHOENIX14 and PHOENIX14-T. Experimental results demonstrate the effectiveness of the SMKD.

关键词： Training Deep learning Visualization Computer vision Gesture recognition Assistive technologies Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

A Dual-band Monopole Antenna with EBG for Wearable Wireless Body Area Networks

引用

Applied Computational Electromagnetics Society Journal 2021年第1期36卷 48-54页

作者： Wang, Chao Zhang, Liang Wu, Shenbing Huang, Shijie Liu, Changqing Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing & Signal Processing Anhui University Hefei City China AnHui Province Key Laboratory of Simulation and Design Electronic Information System Hefei Normal University Hefei City China

This paper proposes a dual-band wearable monopole antenna adopting an electromagnetic band-gap (EBG) structure, which operates at 2.45 and 5.8 GHz ISM bands and is suitable for wearable applications. Both the monopole antenna and the EBG structure are fabricated on an F4B semi-flexible substrate having a dielectric constant of 2.2. The EBG structure effectively isolates the human body from the radiation of the antenna and reduces the specific absorption rate (SAR) of it by more than 97.5%. This improves the antenna gain and the peak gain reaches 9.1 dBi at 5.8 GHz. The wearable performance of the antenna showed that it can sustain good performance even under realistic human body loading. Besides, the antenna has a small size, which makes it ideal for wearable applications. © ACES

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

arXiv

引用

arXiv 2021年

作者： Wang, Rui Wu, Zuxuan Weng, Zejia Chen, Jingjing Qi, Guo-Jun Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Seattle Cloud Lab Futurewei Technologies BellevueWA98004 United States

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, for image classification tasks, and demonstrate that CDCL achieves state-of-the-art performance on both datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Low-Noise Microwave Signal Generation by Heterodyning Two Narrow-Linewidth Self-Injection Locked Lasers

Low-Noise Microwave Signal Generation by Heterodyning Two Na...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Yihao Fan Siyu E Yuyao Guo Xinhang Li Liangjun Lu Shuxiao Wang Yan Cai Jianping Chen Linjie Zhou Department of Electronic Engineering State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Jiao Tong University Shanghai China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China Shanghai Industrial μ Technology Research Institute Shanghai China

We realize a hybrid integrated self-injection locking laser (SIL) with an ultra-narrow intrinsic linewidth of 5 Hz. With heterodyne synthesis using a pair of SILs, a microwave signal with a 4-kHz linewidth is achieved.

ISBN: (纸本)9798350369311

关键词： Wireless communication Masers Microwave communication Microwave theory and techniques Hybrid power systems Microwave generation Microwave photonics Laser applications Electro-optical waveguides

来源：评论

学校读者我要写书评

暂无评论

A Novel Magnetoelastic Biosensor Based on Pdms/Fesib/Qds Composite Film for African Swine Fever Virus Detections

SSRN

引用

SSRN 2024年

作者： Liu, Yuanhang Sang, Shengbo Zhao, Dong Ge, Yang Xue, Juanjuan Duan, Qianqian Guo, Xing Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Electronic Information and Optical Engineering Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System of The Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan030024 China

African swine fever (ASF) is a highly contagious and severe hemorrhagic disease caused by the African swine fever virus (ASFV). The continuous spread of ASFV affects the safety of global meat supply, so the establishment of sensitive and specific detection methods for ASFV has become an important hot spot in food safety. Herein, we developed a flexible magnetoelastic (ME) biosensor based on PDMS/FeSiB/QDs composite films for the detection of ASFV. Based on the high luminescence performance of CsPbBr3 quantum dots and the excellent magnetoelastic effect of FeSiB, flexible ME biosensors convert stress signals generated by antibody-antigen-specific binding into optical and electromagnetic signals. The nanostructures covalently linked by quantum dots and PDMS provide biomodification sites for ASFV antibodies, simplifying the functionalization modification process compared to conventional biosensors. The deformation of the PDMS film is amplified and conversion of surface stress signal to electrical signal is enhanced by exposing the biosensor to a uniform magnetic field. The experimental results proved that the flexible ME biosensor has wide linear range of 10 ng/mL - 100 μg/mL, and the detection limit is as low as 0.7933 ng/mL. Moreover, the flexible ME biosensor have also shown to good stability, sensitivity and specificity. © 2024, The Authors. All rights reserved.

关键词： Biosensors

来源：评论

学校读者我要写书评

暂无评论

Small-Size Zif-8/In2o3 Core-Shell Nanocomposites for Highly Specific Detection of Ppb-Level No2

SSRN

引用

SSRN 2024年

作者： Wang, Hongtao Zhang, Yaodan Xie, Yuanchao Han, Dan Ma, Jianan Sang, Shengbo Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Electronic Information and Optical Engineering Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System the Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanxi Research Institute of 6D Artificiat Intelligence Biomedical Science Taiyuan030024 China

The enhanced sensitivity and selectivity of nitrogen dioxide (NO2) gas sensors are paramount for atmospheric environmental monitoring. In this work, a novel small-size ZIF-8/In2O3 core-shell nanocubes gas sensor was fabricated using a straightforward solvothermal method, complemented by in situ modification. The ZIF-8 film markedly increased the specific surface area of In2O3 nanocubes from 60.64 m²/g to 140.84 m²/g. Concurrently, there was a rise in the content of adsorbed oxygen ions on the surface. The gas-sensing results demonstrated that the ZIF-8/In2O3 composites achieved a response of 56.3 to 1 ppm of NO2, with an exceptionally low detection limit of 1 ppb. Importantly, it exhibited unique selectivity for NO2 over other interfering gases. The outstanding NO2 gas-sensing performance of the ZIF-8/In2O3 composites can be attributed to the grain model effect inherent in the In2O3 (with side lengths of approximately 40-50 nm), along with the sensitization influence and filtering efficacy of ZIF-8. This advancement in gas sensor technology has significant potential for applications in the rapid detection of low-concentration NO2 gas. © 2024, The Authors. All rights reserved.

关键词： Indium compounds

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

UAV-Aided Secure Communication With Deployment Optimization and Cooperative Jamming 11

UAV-Aided Secure Communication With Deployment Optimization ...

引用

11th International Conference on intelligent Control and information processing, ICICIP 2021

作者： Li, Hongbing Wu, Juan Luo, Lei Xiong, Jiang Chongqing Three Gorges University Key Lab. of Intelligent Information Processing and Control of Chongqing Municipal Institutions Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Wanzhou China Chongqing Three Gorges University Chongqing Key Laboratory of Geological Environment Monitoring and Disaster Early-Warning Wanzhou China Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China

ISBN: (纸本)9781665425155

This paper investigates the jointly transmit power and unmanned aerial vehicle (UAV)/jammer deployment optimization problem for UAV enabled jammer-assisted secure communication systems, where a jammer is exploited to assist transmitting data from a source node to a legitimate destination node in the presence of multiple eavesdroppers. To increase the secrecy energy efficiency, which is defined as the achievable secrecy rate per energy consumption unit, we formulate a secrecy energy efficiency maximization problem by jointly optimizing the transmit power and UAV/jammer deployment. The resulting optimization problem is shown to be a non-convex and fractional optimization problem, which is challenging to solve. As such, we decompose the original problem into two sub-problems, and then, an efficient iterative algorithm is proposed by leveraging the extensive search method and Dinkelbach method in combination with successive convex approximation (SCA) techniques. Numerical simulation results show that the proposed scheme significantly improves the secrecy energy efficiency of the system. © 2021 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Rapid synthesis of Pd single‐atom/cluster as highly active catalysts for Suzuki coupling reactions

引用

Chinese Journal of Catalysis 2022年第4期43卷 1058-1065页

作者： Hehe Wei Xiaoyang Li Bohan Deng Jialiang Lang Ya Huang Xingyu Hua Yida Qiao Binghui Ge Jun Ge Hui Wu State Key Laboratory of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Key Lab for Industrial Biocatalysis Ministry of EducationDepartment of Chemical EngineeringTsinghua UniversityBeijing 100084China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601AnhuiChina Key Laboratory for Advanced Materials Center for Computational Chemistry and Research Institute of Industrial CatalysisEast China University of Science and TechnologyShanghai 200237China

Palladium(Pd)‐based catalysts are essential to drive high‐performance Suzuki coupling reactions,which are powerful tools for the synthesis of functional organic ***,we developed a solution‐rapid‐annealing process to stabilize nitrogen‐mesoporous carbon supported Pd single‐atom/cluster(Pd/NMC)material,which provided a catalyst with superior performance for Suzuki coupling *** comparison with commercial palladium/carbon(Pd/C)catalysts,the Pd/NMC catalyst exhibited significantly boosted activity(100%selectivity and 95%yield)and excellent stability(almost no decay in activity after 10 reuse cycles)for the Suzuki coupling reactions of chlorobenzenes,together with superior yield and excellent selectivity in the fields of the board scope of the ***,our newly developed rapid annealing process of precursor solutions is applied as a generalized method to stabilize metal clusters(***,Pt,Ru),opening new possibilities in the construction of efficient highly dispersed metal atom and sub‐nanometer cluster catalysts with high performance.

关键词： Pd single‐atom/cluster catalyst Suzuki coupling reactions Solution rapid annealing Energy barrier High yield

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：