Query：
学者姓名：叶东毅
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
问题生成是一项具有挑战性的自然语言处理任务,旨在生成具有给定答案和上下文的问题,近年来受到了广泛关注.最近,由于神经网络的发展,问题生成任务取得了较大的进展.然而,现有模型仍然存在未有效利用外部知识以及在利用图神经网络捕获隐藏结构信息未捕获语法信息等问题.针对上述问题本文提出知识增强双图交互网络KE-BGINN(Knowledge-En-hanced Bi-Graph Interaction Neural Network).首先为了有效利用外部知识信息,KE-BGINN通过知识图谱本身的图结构信息构造知识增强图,并利用图卷积网络对文本以及答案上下文语义信息进行扩充.其次,KE-BGINN引入一种双图交互机制,利用两个图卷积网络学习上下文的隐藏结构信息以及语法信息,在图间信息融合时,构造一个虚拟图来充分融合不同图之间的异构信息.最后,KE-BGINN利用指针网络解码机制来解决问题生成时罕见和未知词的问题.在SQuAD数据集上的实验结果证明,与对比模型相比较,KE-BGINN模型的综合性能更加优异.
Keyword ：
双图交互 双图交互 图卷积网络 图卷积网络 知识图谱 知识图谱 虚拟图 虚拟图 问题生成 问题生成
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李亚峰 , 叶东毅 , 陈羽中 . 用于问题生成的知识增强双图交互网络 [J]. | 小型微型计算机系统 , 2024 , 45 (5) : 1032-1038 . |
| MLA | 李亚峰 等. "用于问题生成的知识增强双图交互网络" . | 小型微型计算机系统 45 . 5 (2024) : 1032-1038 . |
| APA | 李亚峰 , 叶东毅 , 陈羽中 . 用于问题生成的知识增强双图交互网络 . | 小型微型计算机系统 , 2024 , 45 (5) , 1032-1038 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-round conversational recommendation (MCR), fulfilling a real-time recommendation task for users through interactively asking attributes and recommending items, can be regarded as a multi-step Markov decision-making process. Thus, in MCR, the key point is how to appropriately guide and characterize the dynamic interactive process in the conversation and to mine the dynamic relationship among the user, items and attributes to determine such policies as when to ask (attributes) and recommend (items), what (attributes) to ask and what (items) to recommend. Recent works mainly use statistical information involved in the conversation process to characterize the conversation without comprehensively considering the dynamic relationship among the user, items and attributes and may consequently have a negative impact on accurate capture of the user's real-time preferences. To address this issue, we propose a multi-round conversational recommendation method based on dynamic heterogeneous encoding called DHGECON. Firstly, a dynamic heterogeneous graph with three types of node (users, items, and attributes) is constructed to characterize the proceeding conversation. Secondly, a heterogeneous graph-based encoder which adaptively updates the attention weight of nodes is designed to mine and represent the dynamic high-order semantic relationship among the user, items and attributes. Finally, the encoded information is fed into the decision-making module to get the action (i.e., recommending items or asking attributes) for guiding the next round conversation. Experimental results show that, compared with the state-of-the-art existing methods, the proposed method has a significant improvement in terms of major evaluation metrics over four real-world datasets.(c) 2023 Elsevier B.V. All rights reserved.
Keyword ：
Dynamic heterogeneous graph Dynamic heterogeneous graph Multi-round conversational recommender system Multi-round conversational recommender system Self-attention mechanism Self-attention mechanism
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yao, Huayong , Yao, Hongyu , Ye, Dongyi . DHGECON: A multi-round conversational recommendation method based on dynamic heterogeneous encoding [J]. | KNOWLEDGE-BASED SYSTEMS , 2023 , 273 . |
| MLA | Yao, Huayong 等. "DHGECON: A multi-round conversational recommendation method based on dynamic heterogeneous encoding" . | KNOWLEDGE-BASED SYSTEMS 273 (2023) . |
| APA | Yao, Huayong , Yao, Hongyu , Ye, Dongyi . DHGECON: A multi-round conversational recommendation method based on dynamic heterogeneous encoding . | KNOWLEDGE-BASED SYSTEMS , 2023 , 273 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
自然场景文本识别是计算机视觉领域的研究热点之一，在无人驾驶、图像检索、机器人导航等领域具有广泛的应用前景.由于自然场景中的文本图像存在背景复杂、透视失真、过度弯曲等现象，给文本识别带来了巨大的挑战.针对上述问题，本文提出了一种基于多路并行的位置关联网络(Multi-Path Parallel Location Association Network, MPLAN)的自然场景文本识别方法.首先，针对不规则文本图像，MPLAN使用文本矫正网络自适应学习图像变换，从而获得线性排列的文本图像.其次，为了捕获字符间的位置信息，MPLAN提出了位置关联模块，利用序列特征的有序性，通过捕获字符位置信息，以提高序列特征与目标字符的对齐准确度.此外，为了增强字符间的语义相关性，MPLAN提出了基于多路传输思想的并行注意力模块，获取全局语义信息，实现序列特征的上下文通信，从而锁定有效字符的位置.在包括规则文本、不规则文本在内的六个数据集上的实验结果表明，MPLAN能够有效利用位置信息与全局语义信息解码字符序列，特别是在识别不规则文本上取得了领先的性能.
Keyword ：
场景文本识别 场景文本识别 注意力机制 注意力机制 深度学习 深度学习 端到端 端到端
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈敏 , 叶东毅 , 陈羽中 . 一种用于自然场景文本识别的多路并行位置关联网络 [J]. | 小型微型计算机系统 , 2023 , 44 (04) : 699-705 . |
| MLA | 陈敏 等. "一种用于自然场景文本识别的多路并行位置关联网络" . | 小型微型计算机系统 44 . 04 (2023) : 699-705 . |
| APA | 陈敏 , 叶东毅 , 陈羽中 . 一种用于自然场景文本识别的多路并行位置关联网络 . | 小型微型计算机系统 , 2023 , 44 (04) , 699-705 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
多轮对话推荐系统(CRS)以交互的方式获取用户的实时信息,相较于基于协同过滤等的传统推荐方法能够取得更好的推荐效果.然而现有的CRS存在用户偏好捕获不够准确、对话轮数要求过多以及推荐时机不恰当等问题.针对这些问题,提出一种基于深度强化学习且考虑用户多粒度反馈信息的对话推荐算法.不同于现有的CRS,所提算法在每轮对话中同时考虑用户对商品本身以及更细粒度的商品属性的反馈,然后根据收集的多粒度反馈对用户、商品和商品属性特征进行在线更新,并借助深度Q学习网络(DQN)算法分析每轮对话后的环境状态,从而帮助系统作出较为恰当合理的决策动作,使它能够在比较少的对话轮次的情况下分析用户购买商品的原因,更全面地挖掘用户的实时偏好.与对话路径推理(SCPR)算法相比,在Last.fm真实数据集上,算法的15轮推荐成功率提升了46.5％,15轮推荐轮次上缩短了0.314轮;在Yelp真实数据集上,算法保持了相同水平的推荐成功率,但在15轮推荐轮次上缩短了0.51轮.
Keyword ：
偏好挖掘 偏好挖掘 反馈信息 反馈信息 多粒度 多粒度 多轮对话推荐系统 多轮对话推荐系统 深度Q学习网络 深度Q学习网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 姚华勇 , 叶东毅 , 陈昭炯 . 考虑多粒度反馈的多轮对话强化学习推荐算法 [J]. | 计算机应用 , 2023 , 43 (1) : 15-21 . |
| MLA | 姚华勇 等. "考虑多粒度反馈的多轮对话强化学习推荐算法" . | 计算机应用 43 . 1 (2023) : 15-21 . |
| APA | 姚华勇 , 叶东毅 , 陈昭炯 . 考虑多粒度反馈的多轮对话强化学习推荐算法 . | 计算机应用 , 2023 , 43 (1) , 15-21 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Some extrapolation methods for Chinese landscape painting based on generative adversarial network is proposed in this paper. Existing image extrapolation methods are mainly designed for natural images with large-scale regions containing same objective in each one and with standardized textures, such as grass and sky. They often suffer from blur and boundary semantic inconsistency in extrapolated regions when they are applied to Chinese landscape painting that have complex details, rich gradations and various strokes. To address those problems, a new bidirectional decoding feature fusion network based on generative adversarial network (BDFF-GAN) is proposed. The generator, named UY-Net, is designed with the architecture of U-Net and a multi-scale decoder, which can achieve the function of bidirectional decoding features fusion. Features from different layers of the encoder are assigned to corresponding layers of the multi-scale decoder, where the first-stage feature fusion is achieved by concatenation operations and therefore the connections between features of different scales are enhanced. On the other hand, decoded features from U-Net part and the multi-scale decoder part at same scales are fused by skipping connections to further improve the performance of the generator. Benefiting from the subtle architecture, UY-Net can perform well at semantic features and stroke transmission as well as learning. Moreover, multi-discriminator strategy is adopted in our method. A global discriminator takes the whole result image as the input to control the global consistency, and a local discriminator takes the patch from the junction of source image part and extrapolated part as the input to improve the coherence and details. Experimental results show that BDFF-GAN performs well at semantic features and textures learning with regards to landscape paintings and outperforms existing methods in terms of the semantic content coherence and the naturalness of texture structure with regards to strokes. In addition, we provide an interface that allows users to control the outline of the extrapolated part by boundary guide lines, which achieves the controllability for the layout of extrapolated part and expands the generation diversity and application interactivity of BDFF-GAN. © 2022, Science Press. All right reserved.
Keyword ：
Bidirectional decoding feature fusion Bidirectional decoding feature fusion Chinese landscape painting extrapolation Chinese landscape painting extrapolation Generative adversarial network(GAN) Generative adversarial network(GAN) Local discriminator Local discriminator U-Net U-Net
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fu, T. , Chen, Z. , Ye, D. . GAN-Based Bidirectional Decoding Feature Fusion Extrapolation Algorithm of Chinese Landscape Painting [基于生成对抗网的中国山水画双向解码特征融合外推算法] [J]. | Computer Research and Development , 2022 , 59 (12) : 2816-2830 . |
| MLA | Fu, T. 等. "GAN-Based Bidirectional Decoding Feature Fusion Extrapolation Algorithm of Chinese Landscape Painting [基于生成对抗网的中国山水画双向解码特征融合外推算法]" . | Computer Research and Development 59 . 12 (2022) : 2816-2830 . |
| APA | Fu, T. , Chen, Z. , Ye, D. . GAN-Based Bidirectional Decoding Feature Fusion Extrapolation Algorithm of Chinese Landscape Painting [基于生成对抗网的中国山水画双向解码特征融合外推算法] . | Computer Research and Development , 2022 , 59 (12) , 2816-2830 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The problem of coloring flower line drawings with meticulous effect based on a reference image is addressed. Existing reference-based coloring algorithms for line drawing are difficult to learn and simulate the unique color gradient effect of meticulous flower paintings. Moreover, the reference image in these algorithms is usually required to have similar geometric layout structure to the line drawing, which limits the applicability of the algorithms. Therefore, it is difficult to directly apply existing algorithms to accomplish coloring of line drawings with meticulous effect. On the basis of conditional generative adversarial network(CGAN) framework, a coloring algorithm for flower line drawings with meticulous effect is proposed by means of semantic matching between the reference image and the line drawing. In terms of network structure design, the proposed algorithm uses U-Net as the basis of the generator and designs two additional sub-modules. One is the semantic positioning sub-module. This module pre-trains a semantic segmentation network to generate a semantic label map of the flower line drawing. The label map is encoded as an adaptive instance normalization affine parameter and then introduced into the coloring model to improve the recognition ability of different semantic regions and the accuracy of color positioning. The other is the color coding sub-module. This module extracts the color features of the reference image, and then splices to the first three decoding layers of the generator, in which way, the color information is injected into the color model. Combining this module with semantic location module, our algorithm enhances the learning and simulation of gradient color pattern. In network training stage, the algorithm does not train the model on 'original meticulous flower work-flower line drawing' data pairs. Instead, a perturbed version of the original work via such perturbation operations as disturbing the original geometric structure is generated and then 'perturbed version-flower line drawing' data pairs are used to train our model, which turns out to reduce the model's dependence on the spatial geometry layout of the original work and to then improve the applicability of the proposed algorithm. The experimental results show that the proposed algorithm has a correct response to the color semantics of the reference image selected by the user. It is also shown that the introduced structure of semantic positioning module and color coding module could improve the simulation effect of gradient colors and realize the colorization of the flower line drawing under the guidance of different reference images, as well as diversified coloring results. © 2022, Science Press. All right reserved.
Keyword ：
Color Color Color image processing Color image processing Color matching Color matching Generative adversarial networks Generative adversarial networks Semantics Semantics Semantic Segmentation Semantic Segmentation Semantic Web Semantic Web
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Yuan , Chen, Zhaojiong , Ye, Dongyi . A Coloring Algorithm for Flower Line Drawings with Meticulous Effect Based on Semantic Matching of Reference Images [J]. | Computer Research and Development , 2022 , 59 (6) : 1271-1285 . |
| MLA | Li, Yuan 等. "A Coloring Algorithm for Flower Line Drawings with Meticulous Effect Based on Semantic Matching of Reference Images" . | Computer Research and Development 59 . 6 (2022) : 1271-1285 . |
| APA | Li, Yuan , Chen, Zhaojiong , Ye, Dongyi . A Coloring Algorithm for Flower Line Drawings with Meticulous Effect Based on Semantic Matching of Reference Images . | Computer Research and Development , 2022 , 59 (6) , 1271-1285 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
研究基于生成对抗网的中国山水画的边界外推问题.现有的图像外推方法主要是针对草地、天空等内容比较单一、纹理比较规范的自然场景进行的,直接将其应用于内容较为复杂、层次丰富、笔触变化多样的中国山水画外推会出现外推内容模糊、与原有图像边界语义不一致等现象.针对上述问题,基于生成对抗网的思想,提出一种新的生成对抗网的双向解码特征融合网络(bidirectional decoding feature fusion generative adversarial network,BDFF-GAN).网络在生成器设计方面,以现有的U型网络(U-Net)为基础,增加一个多尺度解码器,构建一种双向解码特征融合的生成器UY-Net.多尺度解码器抽取编码器不同层级的特征进行交叉互补的组合,增强了不同尺度特征之间的连接交融;同时每一层双向解码的结果还通过条件跳跃连接进一步相互融合.UY-Net设计上的这2个特点有利于网络对山水画不同粒度的语义特征和笔触形态的传递与学习.在鉴别器设计方面,采用全局鉴别器和局部鉴别器相结合的架构,全局鉴别器将整幅山水画作为输入来控制外推结果的全局一致性,局部鉴别器将原有山水画与外推山水画交界处周围的小区域作为输入以提高外推部分与原画作的连贯性和细节生成质量.实验结果表明,与其他方法相比较,所提算法较好地学习到了山水画的语义特征和纹理信息,外推结果在语义内容的连贯性和笔触纹理结构的自然性方面都有更好的表现.此外,还设计了一种新的用户交互方式,该方式通过外推边界引导线的形式控制外推部分的轮廓走向,从而实现了布局可调的山水画外推效果,扩展了上述BDFF-GAN网络的生成多样性和应用互动性.
Keyword ：
U型网络 U型网络 中国山水画外推 中国山水画外推 双向解码特征融合 双向解码特征融合 局部鉴别器 局部鉴别器 生成对抗网 生成对抗网
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 符涛 , 陈昭炯 , 叶东毅 . 基于生成对抗网的中国山水画双向解码特征融合外推算法 [J]. | 计算机研究与发展 , 2022 , 59 (12) : 2816-2830 . |
| MLA | 符涛 等. "基于生成对抗网的中国山水画双向解码特征融合外推算法" . | 计算机研究与发展 59 . 12 (2022) : 2816-2830 . |
| APA | 符涛 , 陈昭炯 , 叶东毅 . 基于生成对抗网的中国山水画双向解码特征融合外推算法 . | 计算机研究与发展 , 2022 , 59 (12) , 2816-2830 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
研究基于参考图像的花卉线稿图的工笔效果上色问题.现有的基于参考图像的线稿图上色算法对工笔花卉画特有的色彩渐变的特点难以学习和模拟；此外通常还要求参考图像与线稿图具有相似的几何布局结构，这也限制了算法的适用性，故而直接采用现有算法难以实现线稿图的工笔效果上色.基于条件生成对抗网(conditional generative adversarial network, CGAN)框架，提出了一种将参考图像与线稿图进行语义匹配的花卉线稿图工笔效果上色算法RBSM-CGAN.该算法在网络结构设计方面，以U型网络(简称U-Net)为生成器基础，设计了2个附加子模块：1)语义定位子模块.该模块预训练了一个语...
Keyword ：
工笔花卉上色 工笔花卉上色 条件生成对抗网络 条件生成对抗网络 自适应实例归一化 自适应实例归一化 语义分割网络 语义分割网络 语义匹配 语义匹配
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李媛 , 陈昭炯 , 叶东毅 . 基于参考图语义匹配的花卉线稿工笔效果上色算法 [J]. | 计算机研究与发展 , 2022 , 59 (06) : 1271-1285 . |
| MLA | 李媛 等. "基于参考图语义匹配的花卉线稿工笔效果上色算法" . | 计算机研究与发展 59 . 06 (2022) : 1271-1285 . |
| APA | 李媛 , 陈昭炯 , 叶东毅 . 基于参考图语义匹配的花卉线稿工笔效果上色算法 . | 计算机研究与发展 , 2022 , 59 (06) , 1271-1285 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view clustering has attracted increasing attention by reason of its ability to leverage the complementarity of multi-view data. Existing multi-view clustering methods have explored nonnegative matrix factorization to decompose a matrix into multiple matrices for feature representations from multi-view data, which are not discriminative enough to deal with the natural data containing complex information. Moreover, most of multi -view clustering methods prioritize the consensus information among multi-view data, leaving a large amount of information redundant and the clustering performance deterio-rated. To address these issues, this paper proposes a multi-view clustering framework that adopts a diversity loss for deep matrix factorization and reduces feature redundancy while obtaining more discriminative features. We then bridge the relation between deep auto -encoder and deep matrix factorization to optimize the objective function. This method avoids the challenges in the optimization process. Extensive experiments demonstrate that the proposed method is superior to state-of-the-art methods. (c) 2022 Elsevier Inc. All rights reserved.
Keyword ：
Deep learning Deep learning Deep matrix factorization Deep matrix factorization Diversity embedding Diversity embedding Multi -view clustering Multi -view clustering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Zexi , Lin, Pengfei , Chen, Zhaoliang et al. Diversity embedding deep matrix factorization for multi-view clustering [J]. | INFORMATION SCIENCES , 2022 , 610 : 114-125 . |
| MLA | Chen, Zexi et al. "Diversity embedding deep matrix factorization for multi-view clustering" . | INFORMATION SCIENCES 610 (2022) : 114-125 . |
| APA | Chen, Zexi , Lin, Pengfei , Chen, Zhaoliang , Ye, Dongyi , Wang, Shiping . Diversity embedding deep matrix factorization for multi-view clustering . | INFORMATION SCIENCES , 2022 , 610 , 114-125 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本文针对布局标签图到仿真中国山水画的转换生成问题进行研究,现有的基于条件生成对抗网络(CGAN)的方法存在色彩和语义失真、网络结构参数量较大的问题.针对这些问题,提出一种局部色彩可控的中国山水画仿真生成方法.方法首先提出并设计了一种面向山水画的多语义标签图作为交互方式,根据内容、技法、颜色3个语义层次归纳出山水画中对象的类别,相应地设计了面向手绘山水画原作的多语义标签图的分层分割生成算法,用于构造"手绘山水画-多语义标签图"数据对以作网络训练之用;其次,提出了轻量化的多尺度颜色类别关注的条件生成对抗网络MS3C-CGAN,引入空间自适应归一化残差块、双线性上采样结构简化并重构原有的UC-Net生成器,将生成器的参数量减少了24.45％.对比实验结果表明,本文方法仿真生成的中国山水画更具色彩艺术真实感、语义内容更为准确,同时通过编辑布局标签图可控制生成山水画中植被的色彩,可应用于艺术教育、设计模拟等领域.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 林锦 , 陈昭炯 , 叶东毅 . 局部色彩可控的中国山水画仿真生成方法 [J]. | 小型微型计算机系统 , 2021 , 42 (9) : 1985-1991 . |
| MLA | 林锦 et al. "局部色彩可控的中国山水画仿真生成方法" . | 小型微型计算机系统 42 . 9 (2021) : 1985-1991 . |
| APA | 林锦 , 陈昭炯 , 叶东毅 . 局部色彩可控的中国山水画仿真生成方法 . | 小型微型计算机系统 , 2021 , 42 (9) , 1985-1991 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
