检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 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

Few-Shot Object Detection Based on Generalized Features 2

Few-Shot Object Detection Based on Generalized Features

引用

2nd International Conference on Artificial Intelligence and intelligent Information processing, AIIIP 2023

作者： Chen, Qiuqin Ke, Xiao College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou350116 China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou Fuzhou350003 China

ISBN: (纸本)9798350371451

Few-shot object detection aims to rapidly detect novel classes of objects using a minimal number of annotated instances. Compared to methods such as meta-learning, few-shot object detection based on transfer learning can achieve better performance. However, when training on base-class datasets, the model gradually improves its detection performance on base classes but does not enhance its generalization. A base-class model lacking generalization tends to result in lower detection performance for novel classes during fine-tuning. To address the aforementioned issues, this paper tackles the problem from two aspects: firstly, we introduce the Confusion-Dropblock Module (CDM) to perturb the model's features, thus enhancing feature generalization. Secondly, we incorporate Deformable Convolution Modules to mitigate the impact of object shapes and sizes on detection performance, thereby improving overall detection performance. Experimental results on the COCO dataset demonstrate the effectiveness of the proposed algorithm, outperforming the compared methods. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing

arXiv

引用

arXiv 2023年

作者： Yang, Shangshang Yu, Xiaoshan Tian, Ye Yan, Xueming Ma, Haiping Zhang, Xingyi Anhui University China Guangdong University of Foreign Studies China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education China

Transformer has achieved excellent performance in the knowledge tracing (KT) task, but they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students’ forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students’ forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space design, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach. Copyright © 2023, 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

AGCL: Aspect Graph Construction and Learning for Aspect-level Sentiment Classification 31

AGCL: Aspect Graph Construction and Learning for Aspect-leve...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Jian, Zhongquan Wu, Daihang Wang, Shaopan Wang, Yancheng Yao, Junfeng Wang, Meihong Wu, Qingqiang Institute of Artificial Intelligence Xiamen University China School of Informatics Xiamen University China School of Film Xiamen University China College of Management Mahidol University Thailand School of Computing and Data Science Xiamen University Malaysia Malaysia Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University China

ISBN: (纸本)9798891761964

Prior studies on Aspect-level Sentiment Classification (ALSC) emphasize modeling interrelationships among aspects and contexts but overlook the crucial role of aspects themselves as essential domain knowledge. To this end, we propose AGCL, a novel Aspect Graph Construction and Learning method, aimed at furnishing the model with finely tuned aspect information to bolster its task-understanding ability. AGCL's pivotal innovations reside in Aspect Graph Construction (AGC) and Aspect Graph Learning (AGL), where AGC harnesses intrinsic aspect connections to construct the domain aspect graph, and then AGL iteratively updates the introduced aspect graph to enhance its domain expertise, making it more suitable for the ALSC task. Hence, this domain aspect graph can serve as a bridge connecting unseen aspects with seen aspects, thereby enhancing the model's generalization capability. Experiment results on three widely used datasets demonstrate the significance of aspect information for ALSC and highlight AGL's superiority in aspect learning, surpassing state-of-the-art baselines greatly. Code is available at https://***/jian-projects/agcl. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

Viterbi Decoding of Directed Acyclic Transformer for Non-Aut...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. © 2022 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Simple Controllable Left-Right-Hand Circularly Polarized Antenna for GPS L2 Using Arc-like Slots

A Simple Controllable Left-Right-Hand Circularly Polarized A...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Lulu Meng Sixian Qian Zhixiang Huang Yingsong Li Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China

A single-layer, polarization adjustable circular-polarization (CP) antenna with four arc-like slots has been designed for GPS L2 band. The created antenna uses four arc-like slots to tune the phase difference to form a CP antenna, where the arc-like slots with a specific size relationship are etched on the patch. By adjusting the radius of the arc-like slots, Left-handed -circular-polarization (LHCP) and Right-handed-circular-polarization (RHCP) can be realized easily with simple structure. Simulations and optimizations show that the constructed CP-antenna has a good axial-ratio bandwidth of 10 MHz and impedance-bandwidth of 40 MHz and 30 MHz for LHCP and RHCP application.

关键词： Polarization Slot antennas Bandwidth Directive antennas Antenna feeds Optimization Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Automatic piano performance interaction system based on greedy algorithm for dexterous manipulator

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 473-485页

作者： Yufei WANG Junfeng YAO Yalan ZHOU Zefeng WANG Center for Digital Media Computing School of FilmXiamen UniversityXiamen 361005China Institute of Artificial Intelligence Xiamen UniversityXiamen 361005China School of Informatics Xiamen UniversityXiamen 361005China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen 361005China

With continuous advancements in artificial intelligence(AI), automatic piano-playing robots have become subjects of cross-disciplinary interest. However, in most studies, these robots served merely as objects of observation with limited user engagement or interaction. To address this issue, we propose a user-friendly and innovative interaction system based on the principles of greedy algorithms. This system features three modules: score management, performance control, and keyboard interactions. Upon importing a custom score or playing a note via an external device, the system performs on a virtual piano in line with user inputs. This system has been successfully integrated into our dexterous manipulator-based piano-playing device, which significantly enhances user interactions.

关键词： Human-robot interaction Piano-playing robot Greedy algorithm Score parsing

来源：评论

学校读者我要写书评

暂无评论

Independent dual beams generated by array element division in integrated optical phased arrays

引用

Chinese Optics Letters 2024年第7期22卷 35-41页

作者： Guihan Wu Yu Xin Lemeng Leng Xiang Ji Shichong Yang Kaifei Tang Quan Luo Hongsheng Luo Jinshan Su Wei Jiang College of Engineering and Applied Sciences Nanjing UniversityNanjing 210023China National Laboratory of Solid-State Microstructures Nanjing 210093China Key Laboratory of Intelligent Optical Sensing and Manipulation Ministry of EducationNanjing UniversityNanjing 210023China Jiangsu Key Laboratory of Artificial Functional Materials Nanjing UniversityNanjing 210023China Key Laboratory of Vibration Signal Capture and Intelligent Processing Yili Normal UniversityIli 835000China

Optical phased arrays(OPAs)have broad application prospects due to their advanced capability in beamforming and *** this work,we achieve independent dual beams in the far field by dividing the array elements of the OPA,with the maximum scanning range reaching 100°.Based on the working principle of OPAs,theoretical considerations of such multibeam generation are presented.A phase data allocation approach for OPAs in the presence of fabrication-induced random phase variation is *** of large ensembles of OPAs with various levels of random residual phase errors have been conducted to help analyze the *** approach can help OPAs realize multi-beams for light detection and ranging(LiDAR).

关键词： optical phased arrays beamforming phase error calibration array element division

来源：评论

学校读者我要写书评

暂无评论

A Radiation Performance Improvement Method of Extremely Low Frequency Acoustics Promoted Antenna

A Radiation Performance Improvement Method of Extremely Low ...

引用

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Qi, Junwei Zhang, Chenwei Li, Yingsong Huang, Zhixiang Loh, Tian Hong Chung, Kwok L. Harbin Engineering University College of Information and Communications Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China National Physical Laboratory Electromagnetic and Eletrochemical Technologies Department Middlesex United Kingdom Huizhou University School of Computer Science and Engineering 516007 China

ISBN: (纸本)9798350336740

In this paper, Q-value theory of conventional antennas is used to analyze reasons of low radiation performance of acoustics promoted antennas, where we modify the radiating structure of existing acoustics promoting antenna using the simulations to get the required improvement on radiation performance. The simulation experiments are carried out in the finite element simulation software Comsol Multiphysics to analyze the radiating performance. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Eletrostatically Actuated MEMS Micromirror 5

Two-dimensional Eletrostatically Actuated MEMS Micromirror

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Tao, Wei Ren, Xingang He, Shuping Wu, Xianliang Cai, Xueyuan Huang, Zhixiang Key Laboratory of Target Recognition and Feature Extraction of Anhui Province Lu'an China Ministry of Education Anhui University Key Laboratory of Intelligent Computing & Signal Processing Hefei China Anhui University Key Laboratory of Electromagnetic Environmental Sensing of Anhui Province Hefei China School of Electronic Engineering and Intelligent Manufacturing Anqing Normal University Anqing China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

Recently, the development of LiDAR in the field of vehicle has made the core micromirror with essential characteristics of large tilted angle and small size. We proposed a two-dimensional electrostatically actuated MEMS micromirror with a slender torsion bar. With the modified theoretical formula, two different torsional modes and corresponding torsional frequencies of the micromirror are obtained, which are then compared to the results by finite element simulation, and revealed a good agreement. The rotation angle of the micromirror is improved through optimizing the micromirror structure. Meanwhile, it is found that the driving voltage and the moment of inertia introduce the softening behavior of the spring, which will then affect the torsion frequency. To prevent the torsion bar stress is too large, with the sinusoidal driving voltage of 75V and 100V, the corresponding mechanical rotation angles are 14.8° and 15.3° at a driving frequency of 340.5Hz and 1500Hz, respectively. © 2022 IEEE.

关键词： Torsional stress

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：