检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yan, Shilin Xu, Xiaohao Zhang, Renrui Hong, Lingyi Chen, Wenchao Zhang, Wenqiang Zhang, Wei Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China University of Michigan Ann Arbor United States MMLab CUHK Hong Kong

Panoramic videos contain richer spatial information and have attracted tremendous amounts of attention due to their exceptional experience in some fields such as autonomous driving and virtual reality. However, existing datasets for video segmentation only focus on conventional planar images. To address the challenge, in this paper, we present a panoramic video dataset, i.e., PanoVOS. The dataset provides 150 videos with high video resolutions and diverse motions. To quantify the domain gap between 2D planar videos and panoramic videos, we evaluate 15 off-the-shelf video object segmentation (VOS) models on PanoVOS. Through error analysis, we found that all of them fail to tackle pixel-level content discontinues of panoramic videos. Thus, we present a Panoramic Space Consistency Transformer (PSCFormer), which can effectively utilize the semantic boundary information of the previous frame for pixel-level matching with the current frame. Extensive experiments demonstrate that compared with the previous SOTA models, our PSCFormer network exhibits a great advantage in terms of segmentation results under the panoramic setting. Our dataset poses new challenges in panoramic VOS and we hope that our PanoVOS can advance the development of panoramic segmentation/tracking. The dataset, codes, and pre-train models will be published at https://***/shilinyan99/PanoVOS. Copyright © 2023, The Authors. All rights reserved.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation 39

Semi-Supervised Clustering Framework for Fine-grained Scene ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yang, Jiarui Wang, Chuan Zhang, Jun Wu, Shuyi Jinjing, Zhao Liu, Zeming Yang, Liang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Institute of Information Engineering CAS China School of Computer Science and Technology Beijing JiaoTong University China Guangdong Provincial Key Lab of Intell. Info. Processing & Shenzhen Key Lab of Media Security Shenzhen University China Information Research Center of Military Science PLA Academy of Military Science China National Key Laboratory of Science and Technology on Information System Security China School of Computer Science and Engineering Beihang University China School of Artificial Intelligence Hebei University of Technology China

ISBN: (纸本)157735897X

Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise relationships existing in the scene. Considering the substantial human labor costs, existing scene graph annotations are often sparse and biased, which result in confusion training with low-frequency predicates. In this work, we design a Semi-Supervised Clustering framework for Scene Graph Generation (SSC-SGG) that uses the sparse labeled data to guide the generation of effective pseudo-labels from unlabeled object pairs, thus enriching the labeled sample space, especially for low-frequency interaction samples. We approach from the perspective of clustering, reducing the problem of confirmation bias in a self-training manner. Specifically, we first enhance the model’s robustness to feature extraction via prototype-based clustering, aggregating different relationship augmented features onto the same prototype. Secondly, we design a dynamic pseudo-label assignment algorithm based on a mini-batch, which adjusts the detection sensitivity to different frequency samples from the historical assignment. Finally, we conduct joint training on the pseudo-labels and the labeled data. We conduct experiments on various SGG models and achieve substantial overall performance improvements, demonstrating the effectiveness of SSC-SGG. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dissecting the Applicability of HTTP/3 in Content Delivery Networks

Dissecting the Applicability of HTTP/3 in Content Delivery N...

引用

International Conference on Distributed Computing Systems

作者： Mengying Zhou Yang Chen Shihan Lin Xin Wang Bingyang Liu Aaron Yi Ding Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Huawei Technologies Co. Ltd. China Department of Engineering Systems and Services Delft University of Technology The Netherlands

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

HTTP/3 (H3) has experienced significant growth and extensive adoption in various scenarios, especially in Content Delivery Networks (CDNs). Over the past few years, there have been numerous insightful studies on its deployment in industrial CDNs. However, these studies often separately analyze H3 and CDN, overlooking their synergistic integration. In this work, we explore the applicability of H3 in CDN from a holistic perspective. We analyze 325 websites hosted by seven CDN providers and identify three key characteristics where CDN align perfectly with H3's strengths. Firstly, CDN resources dominate the composition of webpages, where enabling H3 can amplify H3's benefits in connection acceleration. Secondly, CDN providers also exhibit a dominant characteristic, with the majority of CDN resources hosted by a few large providers. This phenomenon makes different webpages share the same provider. When browsing consecutively, H3 helps to skip the connection phase by resuming the connections to the same CDN provider across pages. Thirdly, H3 mitigates the congestion problem on webpages serving multiple CDN resources. This work provides a deeper insight into the applicability of H3 in large-scale distributed systems like CDNs, holding promise for informing the development and optimization of industrial H3.

关键词： Content distribution networks Distributed computing Optimization

来源：评论

学校读者我要写书评

暂无评论

Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding

arXiv

引用

arXiv 2022年

作者： Gao, Songyang Dou, Shihan Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models. The current mainstream solution is designing an additional shallow model to pre-identify biased instances. However, such two-stage methods scale up the computational complexity of training process and obstruct valid feature information while mitigating bias. To address this issue, we utilize the representation normalization method which aims at disentangling the correlations between features of encoded sentences. We find it also promising in eliminating the bias problem by providing isotropic data distribution. We further propose KernelWhitening, a Nyström kernel approximation method to achieve more thorough debiasing on nonlinear spurious correlations. Our framework is end-to-end with similar time consumption to fine-tuning. Experiments show that Kernel-Whitening significantly improves the performance of BERT on out-of-distribution datasets while maintaining in-distribution accuracy. © 2022, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A BERT-Based Model for Legal Document Proofreading 13th

A BERT-Based Model for Legal Document Proofreading

引用

13th IFIP TC 12 International Conference on intelligent information processing, IIP 2024

作者： Liu, Jinlong Luo, Xudong School of Computer Science and Engineering Guangxi Normal University Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology of Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin541004 China

ISBN: (纸本)9783031578076

Legal documents require high precision and accuracy in language use, leaving no room for grammatical and spelling errors. To address the issue, this paper proposes a novel application of the BERT pre-trained language model for legal document proofreading. The BERT-based model is trained to detect and correct legal texts’ grammatical and spelling errors. On a dataset of annotated legal documents, we experimentally show that our BERT-based model significantly outperforms state-of-the-art proofreading models in precision, recall, and F1 score, showing its potential as a valuable tool in legal document preparation and revision processes. The application of such advanced deep learning techniques could revolutionise the field of legal document proofreading, enhancing accuracy and efficiency. © IFIP International Federation for information processing 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Selection of Cancer Biomarkers from Microarray Gene Expression Data Utilizing the Bi-Objective Optimization Method

Selection of Cancer Biomarkers from Microarray Gene Expressi...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Jiang, Hanjing Lin, Jianqing Zhu, Huachao Huang, Yabing Huazhong University of Science and Technology Key Lab. of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Wuhan430074 China Wuhan University School of Computer Science Wuhan430064 China Renmin Hospital of Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350337488

Cancer-associated biomarker genes play an indispensable role in the intricate tapestry of cancer development and manifestation. The expression of biomarkers in different types of tumor cells has beneficial implications for shedding light on the development of various cancers, guiding clinical diagnosis, and treatment. Microarray technology enables the expression levels of thousands of genes in samples to be sequenced simultaneously. However, sparse and high-dimensional microarray data present a formidable challenge in identifying biomarker genes. This study presents EREF-NSGA2, a novel method for cancer biomarker selection from microarray data, employing a hybrid gene selection approach. Firstly, the combination of the wrapper and embedded gene selection methods is proposed to filter the microarray data, which efficiently decreases the search space of the algorithm. After that, the improved NSGA-II algorithm is used to search the genes subset obtained from the previous step to reach the optimal subset of cancer biomarker genes. The proposed EREF-NSGA2 is compared with other reported methods on six cancer benchmark gene expression datasets. A detailed biological analysis is performed to analyze the relationship between the selected genes and the cancer data sets they belong to. To summarize, EREF-NSGA2 proves its effectiveness in selecting a feature subset comprising the fewest genes while maintaining the highest classification accuracy. © 2023 IEEE.

关键词： Bi-objective optimization Cancer biomarker Gene selection NSGA-II

来源：评论

学校读者我要写书评

暂无评论

Dynamic Social Recommendation with High-Matching Inhomogeneous Relations

Dynamic Social Recommendation with High-Matching Inhomogeneo...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Li, Shenghan Wang, Jinyan Zeng, Huachang Li, Jun Wei, Yuecen Li, Xianxian Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin China Guangxi Normal University Guangxi Key Lab of Multi-source Information Mining Security Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China School of Computer and Information Technology Anhui Vocational and Technical College Hefei China

ISBN: (纸本)9798350337020

Social recommendation utilizing social relations as auxiliary information can alleviate data sparsity issues of collaborative filtering methods. However, existing social recommendation methods usually focus on the shallow relations of user-item interactions and social networks to mine potential user preferences, which fail to provide a fine-grained consideration of the inhomogeneous influence and the changes in user interest or item attractiveness over time in high-order interactions of multiple relation types. To address these issues, we propose a novel method named Dynamic Social Recommendation with High-matching Inhomogeneous Relations (DSRHIR) to reveal the influence of inhomogeneity in dynamic interactions on social recommendation from multiple perspectives. Specifically, we first model the short-term dynamic and long-term static representations of both users with social relations and similar relations, and items with correlations. Then, we combine their dynamic and static representations during the interaction and the information from the high-order neighbors of these three relations to obtain a graph-augmented representation. Finally, the graph-augmented representation is used to modulate high-matching user interest and item attractiveness. Extensive experiments on two real-world datasets demonstrate the effectiveness of DSRHIR. © 2023 IEEE.

关键词： graph neural network inhomogeneous relations Recommender systems social networks

来源：评论

学校读者我要写书评

暂无评论

Innovative Design of Hybrid Teaching for Data Structure 24

Innovative Design of Hybrid Teaching for Data Structure

引用

7th International Conference on Educational Technology Management, ICETM 2024

作者： Zhang, Dan Zhao, Dong Ma, Xiujuan Wang, Jiawei School of Computer Science Qinghai Normal University Qinghai Xining China State Key Lab of Tibetan Intelligent Informntion Processing and Application Co-Established by Province and Ministry Qinghai Normal University Qinghai Xining China Talent and Personnel Department Qinghai Normal University Qinghai Xining China

ISBN: (纸本)9798400717468

This paper explores the core position of Data Structure in information-related education and the teaching challenges it faces. By adopting the hybrid teaching education concept of"gradual progress, truth-seeking and innovation" and combining it with the modern educational thinking of"Internet +", this paper is committed to building a hybrid teaching model to improve students’ learning efficiency, understanding and practical skills. By analyzing and improving existing teaching methods, this report proposes a series of innovative strategies to cultivate high-quality talents who can adapt to the needs of future technological development. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

RLGNN: Robust Graph Neural Networks with Noisy label Learning 22

RLGNN: Robust Graph Neural Networks with Noisy Label Learnin...

引用

22nd IEEE International Symposium on Parallel and Distributed processing with Applications, ISPA 2024

作者： Qian, Haodong Li, De Li, Qiyu Wang, Jinyan Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Guangxi Normal University School of Computer Science and Engineering Guilin541004 China

ISBN: (纸本)9798331509712

Graph Neural Networks (GNNs) have become a powerful tool for processing graph-structured data. However, real-world data often faces the problem of label noise and sparsity, which will greatly affect the application of graph neural networks in the real world. Hence, we introduce Robust Graph Neural Networks with Noisy label Learning (RLGNN) to tackle the challenges posed by label noise and sparsity in graph-structured data. Its key components include unsupervised contrastive learning for deriving robust node representations, a two-stage clean sample selection mechanism, and a semi-supervised loss function to harness information from unlabeled nodes. RLGNN ingeniously merges contrastive learning with the prediction space, refining the label selection process and boosting the model's robustness and generalizability. Comprehensive experiments indicate that RLGNN significantly surpasses existing models in managing label noise in semi-supervised node classification scenarios. © 2024 IEEE.

关键词： Contrastive 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：