检索结果-内蒙古大学图书馆

Decoupled deep hough voting for point cloud registration

Frontiers of Computer Science 2024年第2期18卷 147-155页

作者： Mingzhi YUAN Kexue FU Zhihao LI Manning WANG Digital Medical Research Center School of Basic Medical SciencesFudan UniversityShanghai 200032China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China

Estimating rigid transformation using noisy correspondences is critical to feature-based point cloud ***,a series of studies have attempted to combine traditional robust model fitting with deep *** them,DHVR proposed a hough voting-based method,achieving new state-of-the-art ***,we find voting on rotation and translation simultaneously hinders achieving better ***,we proposed a new hough voting-based method,which decouples rotation and translation ***,we first utilize hough voting and a neural network to estimate *** based on good initialization on rotation,we can easily obtain accurate rigid *** experiments on 3DMatch and 3DLoMatch datasets show that our method achieves comparable performances over the state-of-the-art *** further demonstrate the generalization of our method by experimenting on KITTI dataset.

关键词： point cloud registration robust model fitting deep learning hough voting

来源：评论

学校读者我要写书评

暂无评论

SS-Pro:a simplified siamese contrastive learning approach for protein surface representation

引用

Frontiers of Computer Science 2024年第5期18卷 243-245页

作者： Ao SHEN Mingzhi YUAN Yingfan MA Manning WANG Digital Medical Research Center School of Basic Medical ScienceFudan UniversityShanghai 200032China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China

Protein surface serves as an important representation of protein structure,revealing how protein interacts with other biomolecules to perform its *** forms the basis for pharmaceutical and fundamental biological research[1].Datadriven deep learning methods in protein surface representation face challenges of label scarcity,since labeled data are typically obtained through wet lab experiments.

关键词： revealing representation simplified

来源：评论

学校读者我要写书评

暂无评论

An Abnormal Audio Generation Method for Fault Diagnosis of Power Transformers

An Abnormal Audio Generation Method for Fault Diagnosis of P...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Niu, Ben Wei, Yangjie Zhang, Ke Yu, Zhuoran Key Laboratory of Intelligent Computing in Medical Image Northeastern University Shenyang China

ISBN: (纸本)9798350368741

Existing deep learning-based models can achieve a prompt diagnosis of operational anomalies by analyzing the audios emitted from power transformers. However, the practical abnormal data are insufficient for model training, resulting in limited diagnostic performance. To address this problem, we propose an abnormal audio generation method based on the improved cycle generative adversarial networks (ImCycleGAN) to augment the limited training dataset. In the ImCycleGAN, the generator and discriminator are redesigned and adversarially trained to generate the realistic-like audios of six abnormal statuses. Moreover, we combine adversarial, cycle consistency and identity mapping losses to optimize the training process of ImCycleGAN and enhance its ability to capture nonlinear features of audios. Finally, the generated data is evaluated in terms of similarity and fault classification. Experimental results show that our method can generate abnormal audios with high similarity to the real ones, and significantly improve the classification accuracy of existing fault diagnosis models. © 2025 IEEE.

关键词： abnormal audio generation fault diagnosis improved cycle generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Effective ensemble learning approach for SST field prediction using attention-based PredRNN

引用

Frontiers of Computer Science 2023年第1期17卷 143-155页

作者： Baiyou QIAO Zhongqiang WU Ling MA Yicheng Zhou Yunjiao SUN School of Computer Science and Engineering Northeastern UniversityShenyang 110169China Key Laboratory of Intelligent Computing in Medical Image Ministry of EducationNortheastern UniversityShenyang 110169China

Accurate prediction of sea surface temperature (SST) is extremely important for forecasting oceanic environmental events and for ocean studies. However, the existing SST prediction methods do not consider the seasonal periodicity and abnormal fluctuation characteristics of SST or the importance of historical SST data from different times;thus, these methods suffer from low prediction accuracy. To solve this problem, we comprehensively consider the effects of seasonal periodicity and abnormal fluctuation characteristics of SST data, as well as the influence of historical data in different periods, on prediction accuracy. We propose a novel ensemble learning approach that combines the Predictive Recurrent Neural Network(PredRNN) network and an attention mechanism for effective SST field prediction. In this approach, the XGBoost model is used to learn the long-period fluctuation law of SST and to extract seasonal periodic features from SST data. The exponential smoothing method is used to mitigate the impact of severely abnormal SST fluctuations and extract the a priori features of SST data. The outputs of the two aforementioned models and the original SST data are stacked and used as inputs for the next model, the PredRNN network. PredRNN is the most recently developed spatiotemporal deep learning network, which simulates both spatial and temporal representations and is capable of transferring memory across layers and time steps. Therefore, we used it to extract the spatiotemporal correlations of SST data and predict future SSTs. Finally, an attention mechanism is added to capture the importance of different historical SST data, weigh the output of each step of the PredRNN network, and improve the prediction accuracy. The experimental results on two ocean datasets confirm that the proposed approach achieves higher training efficiency and prediction accuracy than the existing SST field prediction approaches do.

关键词： SST prediction ensemble learning XGBoost PredRNN attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A learnable self-supervised task for unsupervised domain adaptation on point cloud classification and segmentation

引用

Frontiers of Computer Science 2023年第6期17卷 147-149页

作者： Shaolei LIU Xiaoyuan LUO Kexue FU Manning WANG Zhijian SONG Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China Digital Medical Research Center School of Basic Medical ScienceFudan UniversityShanghai 200032China

1 Introduction Deep neural networks have exhibited excellent performance in supervised tasks on point clouds,such as classification,segmentation[1]and registration[2].In supervised learning schemes,manual labeling of massive point clouds is needed for model ***,point clouds captured from different scenarios exist inevitable distribution discrepancy,and model trained from one domain always generalize badly in another *** reduce the doamin distribution discrepancy,many studies[3–6]have emerged for point cloud unsupervised domain adaptation(UDA)by learning domain-invariant features,where[5]proposed using adaptive nodes to align the local features between the source and the target domains[3,4],and[6]proposed utilizing self-supervised tasks to help capture highly transferable feature representations.

关键词： point cloud utilizing

来源：评论

学校读者我要写书评

暂无评论

Generating empathetic responses through emotion tracking and constraint guidance

引用

Frontiers of Computer Science 2024年第2期18卷 243-245页

作者： Jing LI Donghong HAN Zhishuai GUO Baiyou QIAO Gang WU School of Computer Science and Engineering Northeastern UniversityShenyang 110000China Key Laboratory of Intelligent Computing in Medical Image(Ministry of Education) Northeastern UniversityShenyang 110000China Neusoft Corporation Shenyang 110000China

1 Introduction Empathy is an essential human trait,which reflects the ability of understanding and reflecting on the thoughts and feelings of *** empathetic dialogue system can improve user's experience and establishlong-termhuman-machine *** speaker's emotions and predict response's emotions are necessary steps in empathetic dialogue generation.

关键词： interaction. constraint steps

来源：评论

学校读者我要写书评

暂无评论

RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback 31

RRHF-V: Ranking Responses to Mitigate Hallucinations in Mult...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Guoqing Zhang, Fu Lin, Jinghao Lu, Chenglong Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Multimodal large language models (MLLMs) demonstrate strong capabilities in multimodal understanding, reasoning, and interaction but still face the fundamental limitation of hallucinations, where they generate erroneous or fabricated information. To mitigate hallucinations, existing methods annotate pair-responses (one non-hallucination vs one hallucination) using manual methods or GPT-4V, and train alignment algorithms to improve the correspondence between images and text. More critically, an image description often involve multiple dimensions (e.g., object attributes, posture, and spatial relationships), making it challenging for the model to comprehensively learn multidimensional information from pair-responses. To this end, in this paper, we propose RRHF-V, which is the first using rank-responses (one non-hallucination vs multiple ranking hallucinations) to mitigate multimodal hallucinations. Instead of using pair-responses to train the model, RRHF-V expands the number of hallucinatory responses, so that the responses with different scores in a rank-response enable the model to learn rich semantic information across various dimensions of the image. Further, we propose a scene graph-based approach to automatically construct rank-responses in a cost-effective and automatic manner. We also design a novel training objective based on rank loss and margin loss to balance the differences between hallucinatory responses within a rank-response, thereby improving the model's image comprehension. Experiments on two MLLMs of different sizes and four widely used benchmarks demonstrate that RRHF-V is effective in mitigating hallucinations and outperforms the DPO method based on pair-responses. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction 31

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Re...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Zehan Zhang, Fu Lyu, Kailun Cheng, Jingwei Peng, Tianyue School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Triplet Extraction (ZSRTE) aims to extract triplets from the context where the relation patterns are unseen during training. Due to the inherent challenges of the ZSRTE task, existing extractive ZSRTE methods often decompose it into named entity recognition and relation classification, which overlooks the interdependence of two tasks and may introduce error propagation. Motivated by the intuition that crucial entity attributes might be implicit in the relation labels, we propose a Relation-Centric joint ZSRTE method named Re-Cent. This approach uses minimal information, specifically unseen relation labels, to extract triplets in one go through a unified model. We develop two span-based extractors to identify the subjects and objects corresponding to relation labels, forming span-pairs. Additionally, we introduce a relation-based correction mechanism that further refines the triplets by calculating the relevance between span-pairs and relation labels. Experiments demonstrate that Re-Cent achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

SGMEA: Structure-Guided Multimodal Entity Alignment 31

SGMEA: Structure-Guided Multimodal Entity Alignment

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cheng, Jingwei Guo, Mingxiao Zhang, Fu School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different multimodal knowledge graphs (MMKGs) by integrating structural information, entity attributes, and visual data, thereby promoting knowledge sharing and deep multimodal data integration. However, existing methods often overlook the deeper connections between multimodal data. They primarily focus on the interactions between neighboring entities in the structural modality while neglecting the interactions between entities in the visual and attribute modalities. To address this, we propose a structure-guided multimodal entity alignment method (SGMEA), which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities. By fusing multimodal representations, SGMEA improves the accuracy of entity alignment. Experimental results demonstrate that SGMEA achieves state-of-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Shot Relation Extraction 31

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Sho...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Fu Liu, He Li, Zehan Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Extraction (ZSRE) aims to predict novel relations from sentences with given entity pairs, where the relations have not been encountered during training. Prototype-based methods, which achieve ZSRE by aligning the sentence representation and the relation prototype representation, have shown great potential. However, most existing works focus solely on improving the quality of prototype representations, neglecting sentence representations, and lacking interaction between different types of relation side information. In this paper, we propose a novel ZSRE framework named CE-DA, which includes two modules: Custom Embedding and Dynamic Aggregation. We employ a two-stage approach to obtain customized embeddings of sentences. In the first stage, we train a sentence encoder through unsupervised contrastive learning, and in the second stage, we highlight the potential relations between entities in sentences using carefully designed entity emphasis prompts to further enhance sentence representations. Additionally, our dynamic aggregation method assigns different weights to different types of relation side information through a learnable network to enhance the quality of relation prototype representations. In contrast to traditional methods that treat the importance of all side information equally, our dynamic aggregation method further strengthens the interaction between different types of relation side information. Our method demonstrates competitive performance across various metrics on two ZSRE datasets. © 2025 Association for Computational Linguistics.

关键词： Embeddings

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：