检索结果-内蒙古大学图书馆

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

作者： Zhang, Shuo Huang, Jiaming Tang, Wenbing Tian, Lili Wei, Yuang Liu, Jing Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Huolala Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science and Technology East China Normal University China

ISBN: (纸本)9798350368741

Salient Object Detection (SOD) aims to identify and segment the most striking elements within an image. Salient object detection methods can be differentiated into several types according to the input data, such as RGB-D (Depth) and RGB-T (Thermal). Previous research primarily focused on saliency detection for single data types. However, forcing an RGB-D SOD model to process RGB-T data will degrade its performance significantly. In addition, current methods still face challenges in detecting fine edge details of salient objects and achieving end-to-end training. To address these issues, we introduce diffSOD, which leverages stable diffusion and cross-modal feature rectification and fusion module for saliency detection by transforming salient object detection into a denoising process from a noisy mask to an object mask. It offers a unified solution for salient object detection that seamlessly spans both RGB-D SOD and RGB-T SOD. Extensive experiments validate the effectiveness of the proposed diffSOD, demonstrating its ability to efficiently detect salient objects across both RGB-D and RGB-T data, while achieving superior performance over state-of-the-art methods. © 2025 IEEE.

关键词： attention interaction fusion latent diffusion model multi-modal salient object detection

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction by Disentangled Subgraph Structure

引用

Tsinghua science and Technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts

RoCEL: Advancing Table Entity Linking through Distinctive Ro...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wang, Yuanzheng Fan, Yixing Guo, Jiafeng Zhang, Ruqing Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761643

Table entity linking (TEL) aims to map entity mentions in the table to their corresponding entities in a knowledge base (KB). The core of this task is to leverage structured contexts, specifically row and column contexts, to enhance the semantics of mentions in entity disambiguation. Most entity linking (EL) methods primarily focus on understanding sequential text contexts, making it difficult to adapt to the row and column structure of tables. Additionally, existing methods for TEL indiscriminately mix row and column contexts together, overlooking their semantic differences. In this paper, we explicitly distinguish the modeling of row and column contexts, and propose a method called RoCEL to capture their distinct semantics. Specifically, for row contexts in tables, we take the attention mechanism to learn the implicit relational dependencies between each cell and the mention. For column contexts in tables, we employ a set-wise encoder to learn the categorical information about the group of mentions. At last, we merge both contexts to obtain the final mention embedding for link prediction. Experiments on four benchmarks show that our approach outperforms the state-of-the-art (SOTA) baseline by about 1.5% on the in-domain dataset, and by 3.7% on average across three out-of-domain datasets. © 2024 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

Scattering exceptional point in the visible

引用

Light(science & Applications) 2023年第10期12卷 2228-2235页

作者： Tao He Zhanyi Zhang Jingyuan Zhu Yuzhi Shi Zhipeng Li Heng Wei Zeyong Wei Yong Li Zhanshan Wang Cheng-Wei Qiu Xinbin Cheng MOE Key Laboratory of Advanced Micro-Structured Materials Shanghai 200092China Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China Shanghai Frontiers Science Center of Digital Optics Shanghai 200092China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Shanghai 200092China Department of Electronic Science and Technology Tongji UniversityShanghai 201804China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Acoustics School of Physics Science and EngineeringTongji UniversityShanghai 200092China

Exceptional point (EP) is a special degeneracy of non-Hermitian systems. One-dimensional transmission systems operating at EPs are widely studied and applied to chiral conversion and sensing. Lately, two-dimensional systems at EPs have been exploited for their exotic scattering features, yet so far been limited to only the non-visible waveband. Here, we report a universal paradigm for achieving a high-efficiency EP in the visible by leveraging interlayer loss to accurately control the interplay between the lossy structure and scattering lightwaves. A bilayer framework is demonstrated to reflect back the incident light from the left side ( | r_(−1) | >0.999) and absorb the incident light from the right side ( | r_(+1) | < 10^(–4)). As a proof of concept, a bilayer metasurface is demonstrated to reflect and absorb the incident light with experimental efficiencies of 88% and 85%, respectively, at 532 nm. Our results open the way for a new class of nanoscale devices and power up new opportunities for EP physics.

关键词： visible exceptional incident

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem 30

Benchmarking Hallucination in Large Language Models based on...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Sun, Yuhong Yin, Zhangyue Guo, Qipeng Wu, Jiawen Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai AI Laboratory China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (纸本)9782493814104

Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://***/Yuki-Asuuna/UMWP. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Online multi-label streaming feature selection based on neighborhood rough set with label correlation 24

Online multi-label streaming feature selection based on neig...

引用

3rd International Conference on Artificial Intelligence and Education, ICAIE 2024

作者： Pan, Siping Lin, Yaojin Mao, Yu Lin, Shaojie School of Computer Science Minnan Normal University Fujian Zhangzhou China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Fujian Zhangzhou China

ISBN: (纸本)9798400712692

Online multi-label streaming feature selection has gained significant interest in high-volume data applications. Neighborhood Rough Set (NRS) has emerged as a practical tool for handling multi-label feature selection. However, the majority of existing works have been concentrated on situations where labels are treated as independent and unrelated entities, disregarding the genuine context of interdependence and correlation among labels. To address this issue, this paper introduces a novel approach for online multi-label streaming feature selection, incorporating NRS and Label Correlation (LC). In our approach, we propose the concept of strongly related label subsets based on NRS. As considering label correlation, we compute the similarity between different labels and assign different weights to each label. This integrated method enhances the effectiveness of feature selection by leveraging the interdependencies among labels. he proposed reliability of the algorithm is validated experimentally. © 2024 Copyright held by the owner/author(s).

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DMHFR:Decoder with Multi-Head Feature Receptors for Tract Image Segmentation

引用

computers, Materials & Continua 2025年第3期82卷 4841-4862页

作者： Jianuo Huang Bohan Lai Weiye Qiu Caixu Xu Jie He Department of Endoscopy Center Zhongshan Hospital(Xiamen)Fudan UniversityXiamen361015China School of Computing and Data Science Xiamen University MalaysiaSepang43900Malaysia School of Computer Science and Techonology Tongji UniversityShanghai200092China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou UniversityWuzhou543002China Xiamen Clinical Research Center for Cancer Therapy Xiamen361015China

The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image ***,their ability to learn local,contextual relationships between pixels requires further *** methods face challenges in efficiently managing multi-scale fea-tures of different granularities from the encoder backbone,leaving room for improvement in their global representation and feature extraction *** address these challenges,we propose a novel Decoder with Multi-Head Feature Receptors(DMHFR),which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities:coarse,fine-grained,and full *** groups are subsequently processed by Multi-Head Feature Receptors(MHFRs)after feature capture and modeling *** include two Three-Head Feature Receptors(THFRs)and one Four-Head Feature Receptor(FHFR).Each group of features is passed through these MHFRs and then fed into axial transformers,which help the model capture long-range dependencies within the *** three MHFRs produce three distinct feature *** output from the FHFR serves as auxiliary auxiliary features in the prediction head,and the prediction output and their losses will eventually be *** results show that the Transformer using DMHFR outperforms 15 state of the arts(SOTA)methods on five public ***,it achieved significant improvements in mean DICE scores over the classic Parallel Reverse Attention Network(PraNet)method,with gains of 4.1%,2.2%,1.4%,8.9%,and 16.3%on the CVC-ClinicDB,Kvasir-SEG,CVC-T,CVC-ColonDB,and ETIS-LaribPolypDB datasets,respectively.

关键词： Medical image segmentation feature exploration feature aggregation deep learning multi-head feature receptor

来源：评论

学校读者我要写书评

暂无评论

APIBeh: Learning Behavior Inclination of APIs for Malware Classification 35

APIBeh: Learning Behavior Inclination of APIs for Malware Cl...

引用

35th IEEE International Symposium on Software Reliability Engineering, ISSRE 2024

作者： Cui, Lei Zhu, Yiran Yin, Junnan Hao, Zhiyu Wang, Wei Liu, Peng Yang, Ziqi Yun, Xiaochun Zhongguancun Laboratory China Zhejiang University The State Key Laboratory of Blockchain and Data Security China China Guangxi Normal University School of Computer Science and Engineering China

ISBN: (纸本)9798350353884

Malware classification involves categorizing mal-ware samples based on their characteristics. While deep learning techniques applied to malware execution traces, mainly API calls, have shown potential in this field, they still perform poorly. This is primarily because they treat all APIs equally and train classifiers directly on native APIs, which inadequately capture the under-lying family-related semantics. In this paper, we first investigate the behaviors of multiple malware families and observe that different families exhibit divergent behaviors, with each family consistently favoring certain behaviors over time. Motivated by this, we propose APIBeh, a new embedding method designed to enhance malware classification. APIBeh first utilizes Benignity Degree Algorithm to identify and exclude insignificant, likely benign APIs from sequences. Then, it introduces the concept of Behavior Inclination, which quantifies the association between an API and malicious behaviors, facilitating high-level behavior encoding for each API. This Behavior Inclination embedding is then concatenated with raw embedding to represent an API, and fed into a DL model for classifier training. Experimental results show that APIBeh outperforms existing embedding methods in classification performance, e.g., 3.18% boost in weighted f1-score over a recent study using word2vec. In addition, it offers robustness to concept drift and adversarial attacks. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based pathological analysis of liver cancer:Current advancements and interpretative strategies

引用

iLIVER 2024年第1期3卷 82-89页

作者： Guang-Yu Ding Jie-Yi Shi Xiao-Dong Wang Bo Yan Xi-Yang Liu Qiang Gao Department of Liver Surgery and Transplantation Liver Cancer InstituteZhongshan HospitalShanghai 200032China Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education Fudan UniversityShanghai 200032China School of Computer Science and Technology Xidian UniversityXi'an 710126China School of Computer Science Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghai 200433China Institute of Biomedical Sciences Fudan UniversityShanghai 200030China State Key Laboratory of Genetic Engineering Fudan UniversityShanghai 200433China

In recent years,significant advances have been achieved in liver cancer management with the development of artificial intelligence(AI).AI-based pathological analysis can extract crucial information from whole slide images to assist clinicians in all aspects from diagnosis to prognosis and molecular ***,AI techniques have a“black box”nature,which means that interpretability is of utmost importance because it is key to ensuring the reliability of the methods and building trust among clinicians for actual clinical *** this paper,we provide an overview of current technical advancements in the AI-based pathological analysis of liver cancer,and delve into the strategies used in recent studies to unravel the“black box”of AI's decision-making process.

关键词： Liver cancer Artificial intelligence Pathology Interpretative model

来源：评论

学校读者我要写书评

暂无评论

GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

arXiv

引用

arXiv 2025年

作者： Gu, Zhouhong Chen, Xingzhou Shi, Xiaoran Wang, Tao Zheng, Suhang Li, Tianyu Feng, Hongwei Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Alibaba Group China

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response synthesis or preferential response optimization, they often struggle with constraint understanding and adaptation. This limitation becomes particularly evident when handling fine-grained constraints, leading to either hallucination or brittle performance. We introduce Generative Adversarial Policy Optimization (GAPO), a novel framework that combines GAN-based training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints. GAPO leverages adversarial training to automatically generate training samples of varying difficulty while utilizing the encoder-only architecture to better capture prompt-response relationships. Extensive experiments demonstrate GAPO’s superior performance across multiple benchmarks, particularly in scenarios requiring fine-grained constraint handling, where it significantly outperforms existing methods like PPO, DPO, and KTO. Our results suggest that GAPO’s unique approach to preferential prompt learning offers a more robust and effective solution for controlling LLM outputs. Code is avaliable in https://***/MikeGu721/GAPO. © 2025, CC BY.

关键词： Adversarial machine learning

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：