检索结果-内蒙古大学图书馆

Conference on Empirical Methods in Natural Language processing (EMNLp)

作者： Zhou, Hao Huang, Minlie Liu, Yong Chen, Wei Zhu, Xiaoyan Tsinghua Univ CoAI Grp Beijing Natl Res Ctr Informat Sci & Technol State Key Lab Intelligent Technol & SystDCST Beijing 100084 Peoples R China Tencent Inc WeChat AI Pattern Recognit Ctr Shenzhen Peoples R China Sogou Inc Beijing 100084 Peoples R China

ISBN: (纸本)9781955917094

Generating informative and appropriate responses is challenging but important for building human-like dialogue systems. Although various knowledge-grounded conversation models have been proposed, these models have limitations in utilizing knowledge that infrequently occurs in the training data, not to mention integrating unseen knowledge into conversation generation. In this paper, we propose an Entity-Agnostic Representation Learning (EARL) method to introduce knowledge graphs to informative conversation generation. Unlike traditional approaches that parameterize the specific representation for each entity, EARL utilizes the context of conversations and the relational structure of knowledge graphs to learn the category representation for entities, which is generalized to incorporating unseen entities in knowledge graphs into conversation generation. Automatic and manual evaluations demonstrate that our model can generate more informative, coherent, and natural responses than baseline models.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Addressing Inquiries about History: An Efficient and practical Framework for Evaluating Open-domain Chatbot Consistency

Addressing Inquiries about History</...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on Natural Language processing (IJCNLp) / 6th Workshop on Representation Learning for NLp (RepL4NLp)

作者： Li, Zekang Zhang, Jinchao Fei, Zhengcong Feng, Yang Zhou, Jie Chinese Acad Sci ICT CAS Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Tencent Inc WeChat AI Pattern Recognit Ctr Beijing Peoples R China

ISBN: (纸本)9781954085541

A good open-domain chatbot should avoid presenting contradictory responses about facts or opinions in a conversational session, known as its consistency capacity. However, evaluating the consistency capacity of a chatbot is still challenging. Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias. In this paper, we propose the Addressing Inquiries about History (AIH), an efficient and practical framework for the consistency evaluation. At the conversation stage, AIH attempts to address appropriate inquiries about the dialogue history to induce the chatbot to redeclare the historical facts or opinions. We carry out the conversation between chatbots, which is more efficient than the human-bot interaction and can also alleviate the subjective bias. In this way, we manage to rapidly obtain a dialog session that contains responses with high contradiction possibilities. At the contradiction recognition stage, we can either employ human judges or a natural language inference (NLI) model to recognize whether the answers to the inquiries are contradictory with history. Finally, we are able to rank chatbots according to the contradiction statistics. Experiments on open-domain chatbots show that our approach can efficiently and reliably assess the consistency capacity of chatbots and achieve a high ranking correlation with the human evaluation. We release the framework and hope to help improve the consistency capacity of chatbots.(1)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inter-Attribute awareness for pedestrian attribute recognition

引用

pattern recognitION 2022年 131卷

作者： Wu, Junyi Huang, Yan Gao, Zhipeng Hong, Yating Zhao, Jianqiang Du, Xinsheng Xiamen Meiya P Informat Co Ltd AI Res Ctr Xiamen Peoples R China Chinese Acad Sci CASIA Inst Automat Ctr Res Intelligent Percept & Comp CRIPAC Natl Lab Pattern Recognit NLPR Beijing Peoples R China

The task of pedestrian attribute recognition (pAR) is to distinguish a series of person semantic attributes. Generally, existing methods adopt multi-label classification algorithms to tackle the pAR task by utilizing multiple attribute labels. Despite remarkable progress, this kind of method normally ignores relations between different attributes. In order to be aware of relations between attributes, we propose an inter attribute aware network via vector-neuron capsule for pAR (IAA-Caps). Our IAA-Caps method replaces traditional one-dimensional scalar neurons with two-dimensional vector-neuron capsules by embedding them in IAA-Caps. Specifically, during IAA-Caps training, one dimension in capsules is used to recognize different attributes, and the other dimension is used to strengthen the relations of different attributes. Through considering inter-attribute relations, compared with previous methods that use a heavyweight backbone (e.g., ResNet50 or BN-Inception), a more lightweight backbone (i.e., OSNet) can be adopted in our proposed IAA-Caps to achieve better performance. Experiments are conducted on several pAR benchmark datasets, including pETA, pA-100K, RApv1, and RApv2, demonstrating the effectiveness of the proposed IAA-Caps. In addition, experiments also show that the proposed method can improve the performance of pAR on different backbones, showing its generalization ability.(c) 2022 Elsevier Ltd. All rights reserved.

关键词： pedestrian attribute recognition Inter-Attribute awareness Vector-Neuron capsules

来源：评论

学校读者我要写书评

暂无评论

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

引用

IEEE TRANSACTIONS ON IMAGE pROCESSING 2021年 30卷 6036-6049页

作者： Che, Tongtong Zheng, Yuanjie Yang, Yunshuai Hou, Sujuan Jia, Weikuan Yang, Jie Gong, Chen Shandong Normal Univ Sch Informat Sci & Engn Jinan 250300 Peoples R China Shandong Normal Univ Key Lab Intelligent Comp & Informat Secur Univ Sh Jinan 250300 Peoples R China Shandong Normal Univ Shandong Prov Key Lab Novel Distributed Comp Soft Jinan 250300 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China Nanjing Univ Sci & Technol PCA Lab Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing 210094 Peoples R China

There is a growing consensus in computer vision that symmetric optical flow estimation constitutes a better model than a generic asymmetric one for its independence of the selection of source/target image. Yet, convolutional neural networks (CNNs), that are considered the de facto standard vision model, deal with the asymmetric case only in most cutting-edge CNNs-based optical flow techniques. We bridge this gap by introducing a novel model named SDOF-GAN: symmetric dense optical flow with generative adversarial networks (GANs). SDOF-GAN realizes a consistency between the forward mapping (source-to-target) and the backward one (target-to-source) by ensuring that they are inverse of each other with an inverse network. In addition, SDOF-GAN leverages a GAN model for which the generator estimates symmetric optical flow fields while the discriminator differentiates the "real" ground-truth flow field from a "fake" estimation by assessing the flow warping error. Finally, SDOF-GAN is trained in a semi-supervised fashion to enable both the precious labeled data and large amounts of unlabeled data to be fully-exploited. We demonstrate significant performance benefits of SDOF-GAN on five publicly-available datasets in contrast to several representative state-of-the-art models for optical flow estimation.

关键词： Estimation Optical imaging Adaptive optics Generative adversarial networks Brightness Optical fiber networks Semisupervised learning Symmetric optical flow estimation generative adversarial networks forward-backward consistency semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-disease X-ray Image Classification of the Chest Based on Global and Local Fusion Adaptive Networks

引用

CURRENT MEDICAL IMAGING 2024年 20卷 e15734056291283页

作者： Gu, Yu Shi, Ru Yang, Shuaikang Yang, Lidong Zhang, Baohua Wang, Jing Lu, Xiaoqi Li, Jianjun Liu, Xin Zhao, Ying Yu, Dahua Tang, Siyuan He, Qun Inner Mongolia Univ Sci & Technol Sch Digital & Intelligent Ind Inner Mongolia Key Lab Pattern Recognit & Intellig Baotou 014010 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Inner Mongolia Univ Technol Coll Informat Engn Hohhot 010051 Peoples R China Inner Mongolia Univ Sci & Technol Baotou Med Coll Sch Comp Sci & Technol Baotou 014040 Peoples R China

Background: Chest X-ray image classification for multiple diseases is an important research direction in the field of computer vision and medical image processing. It aims to utilize advanced image processing techniques and deep learning algorithms to automatically analyze and identify X-ray images, determining whether specific pathologies or structural abnormalities exist in the ***: We present the MMpDenseNet network designed specifically for chest multi-label disease ***: Initially, the network employs the adaptive activation function Meta-ACON to enhance feature representation. Subsequently, the network incorporates a multi-head self-attention mechanism, merging the conventional convolutional neural network with the Transformer, thereby bolstering the ability to extract both local and global features. Ultimately, the network integrates a pyramid squeeze attention module to capture spatial information and enrich the feature ***: The concluding experiment yielded an average AUC of 0.898, marking an average accuracy improvement of 0.6% over the baseline model. When compared with the original network, the experimental results highlight that MMpDenseNet considerably elevates the classification accuracy of various chest ***: It can be concluded that the network, thus, holds substantial value for clinical applications.

关键词： Medical image processing Multiple diseases of the chest Multi-headed self-attention Adaptive activation function Attention mechanism Chest X-ray image classification

来源：评论

学校读者我要写书评

暂无评论

Shift pooling pSpNet: Rethinking pSpNet for Building Extraction in Remote Sensing Images from Entire Local Feature pooling

引用

REMOTE SENSING 2022年第19期14卷 4889-4889页

作者： Yuan, Wei Wang, Jin Xu, Wenbo Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610106 Peoples R China Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China

Building extraction by deep learning from remote sensing images is currently a research hotspot. pSpNet is one of the classic semantic segmentation models and is currently adopted by many applications. Moreover, pSpNet can use not only CNN-based networks but also transformer-based networks as backbones;therefore, pSpNet also has high value in the transformer era. The core of pSpNet is the pyramid pooling module, which gives pSpNet the ability to capture the local features of different scales. However, the pyramid pooling module also has obvious shortcomings. The grid is fixed, and the pixels close to the edge of the grid cannot obtain the entire local features. To address this issue, an improved pSpNet network architecture named shift pooling pSpNet is proposed, which uses a module called shift pyramid pooling to replace the original pyramid pooling module, so that the pixels at the edge of the grid can also obtain the entire local features. Shift pooling is not only useful for pSpNet but also in any network that uses a fixed grid for downsampling to increase the receptive field and save computing, such as ResNet. A dense connection was adopted in decoding, and upsampling was gradually carried out. With two open datasets, the improved pSpNet, pSpNet, and some classic image segmentation models were used for comparative experiments. The results show that our method is the best according to the evaluation metrics, and the predicted image is closer to the label.

关键词： building extraction deep learning improved pSpNet shift pooling remote sensing image

来源：评论

学校读者我要写书评

暂无评论

New Exact Solutions to the Lakshmanan-porsezian-Daniel Equation with Kerr Law of Nonlinearity

引用

MATHEMATICAL pROBLEMS IN ENGINEERING 2022年第1期2022卷

作者： peng, Chen Li, Zhao Zhao, Hongwei Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610106 Peoples R China China United Network Communicat Grp Co Sichuan Branch Chengdu 610095 Peoples R China

In this study, some new exact travelling wave solutions to the Lakshmanan-porsezian-Daniel (LpD) equation with Kerr law of nonlinearity are retrieved by the complete discrimination system for the polynomial method. Under the travelling wave transformation, the LpD equation is reduced to an ordinary differential equation. The new exact travelling wave solutions including rational solutions, triangle function solutions, solitary wave solutions, and Jacobian elliptic function solutions are obtained and graphically illustrated using three-dimensional and two-dimensional graphs. Comparing with the previous results for LpD equation, some of new solutions in this work such as elliptical solution are not studied, which shows the complete discrimination system method is efficient.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

GapLoss: A Loss Function for Semantic Segmentation of Roads in Remote Sensing Images

引用

REMOTE SENSING 2022年第10期14卷 2422-2422页

作者： Yuan, Wei Xu, Wenbo Chengdu Univ Sch Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610106 Peoples R China Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China

At present, road continuity is a major challenge, and it is difficult to extract the centerline vector of roads, especially when the road view is obstructed by trees or other structures. Most of the existing research has focused on optimizing the available deep-learning networks. However, the segmentation accuracy is also affected by the loss function. Currently, little research has been published on road segmentation loss functions. To resolve this problem, an attention loss function named GapLoss that can be combined with any segmentation network was proposed. Firstly, a deep-learning network was used to obtain a binary prediction mask. Secondly, a vector skeleton was extracted from the prediction mask. Thirdly, for each pixel, eight neighboring pixels with the same value of the pixel were calculated. If the value was 1, then the pixel was identified as the endpoint. Fourth, according to the number of endpoints within a buffered range, each pixel in the prediction image was given a corresponding weight. Finally, the weighted average value of the cross-entropy of all the pixels in the batch was used as the final loss function value. We employed four well-known semantic segmentation networks to conduct comparative experiments on three large datasets. The results showed that, compared to other loss functions, the evaluation metrics after using GapLoss were nearly all improved. From the predicted image, the road prediction by GapLoss was more continuous, especially at intersections and when the road was obscured from view, and the road segmentation accuracy was improved.

关键词： deep learning loss function road extraction remote sensing image sematic segmentation

来源：评论

学校读者我要写书评

暂无评论

New Traveling Wave Solutions for the (2+1)-Dimensional Heisenberg Ferromagnetic Spin Chain Equation

引用

MATHEMATICAL pROBLEMS IN ENGINEERING 2022年第1期2022卷

作者： Han, Tianyong Wen, Jiajin Li, Zhao Yuan, Jun Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China Nanjing Xiaozhuang Univ Sch Informat Engn Nanjing 211171 Jiangsu Peoples R China

The principal objective of this article is to construct new exact soliton solutions of the (2 + 1)-dimensional Heisenberg ferromagnetic spin chain equation which investigates the nonlinear dynamics of magnets. Through using the complete discrimination system method, the traveling wave solutions are obtained. As a result, we get the traveling wave solutions of the Heisenberg ferromagnetic spin chain equation, which include rational function solutions, Jacobian elliptic function solutions, hyperbolic function solutions, trigonometric function solutions, inverse trigonometric function, logarithmic function. Some graphical representations of the problems and that of comparison are also provided.

关键词： Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

Accurate inference of gene regulatory interactions from spatial gene expression with deep contrastive learning

引用

BIOinformatICS 2022年第3期38卷 746-753页

作者： Zheng, Lujing Liu, Zhenhuan Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ SJTU Paris Elite Inst Technol SPEIT Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Key Lab Shanghai Educ Commiss Intelligent Interac Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Key Lab Syst Control & Informat Proc Minist Educ China Shanghai 200240 Peoples R China

Motivation: Reverse engineering of gene regulatory networks (GRNs) has long been an attractive research topic in system biology. Computational prediction of gene regulatory interactions has remained a challenging problem due to the complexity of gene expression and scarce information resources. The high-throughput spatial gene expression data, like in situ hybridization images that exhibit temporal and spatial expression patterns, has provided abundant and reliable information for the inference of GRNs. However, computational tools for analyzing the spatial gene expression data are highly underdeveloped. Results: In this study, we develop a new method for identifying gene regulatory interactions from gene expression images, called ConGRI. The method is featured by a contrastive learning scheme and deep Siamese convolutional neural network architecture, which automatically learns high-level feature embeddings for the expression images and then feeds the embeddings to an artificial neural network to determine whether or not the interaction exists. We apply the method to a Drosophila embryogenesis dataset and identify GRNs of eye development and mesoderm development. Experimental results show that ConGRI outperforms previous traditional and deep learning methods by a large margin, which achieves accuracies of 76.7% and 68.7% for the GRNs of early eye development and mesoderm development, respectively. It also reveals some master regulators for Drosophila eye development.

关键词：

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：