检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial intell.gence, 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 intell.gence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parsing-based view-aware embedding network for vehicle re-identification

arXiv

引用

arXiv 2020年

作者： Meng, Dechao Li, Liang Liu, Xuejing Li, Yadong Yang, Shijie Zha, Zheng-Jun Gao, Xingyu Wang, Shuhui Huang, Qingming Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing China University of Chinese Academy of Sciences China Megvii Inc Beijing China University of Science and Technology of China China Peng Cheng Laboratory Shenzhen China Institute of Microelectronics Chinese Academy of Sciences Beijing China

Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario. The main challenges of this task are the large intra-instance distance caused by different views and the subtle inter-instance discrepancy caused by similar vehicles. In this paper, we propose a parsing-based view-aware embedding network (PVEN) to achieve the view-aware feature alignment and enhancement for vehicle ReID. First, we introduce a parsing network to parse a vehicle into four different views, and then align the features by mask average pooling. Such alignment provides a fine-grained representation of the vehicle. Second, in order to enhance the view-aware features, we design a common-visible attention to focus on the common visible views, which not only shortens the distance among intra-instances, but also enlarges the discrepancy of inter-instances. The PVEN helps capture the stable discriminative information of vehicle under different views. The experiments conducted on three datasets show that our model outperforms state-of-the-art methods by a large margin. Copyright © 2020, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification

Parsing-Based View-Aware Embedding Network for Vehicle Re-Id...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Dechao Meng Liang Li Xuejing Liu Yadong Li Shijie Yang Zheng-Jun Zha Xingyu Gao Shuhui Wang Qingming Huang Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing China University of Chinese Academy of Sciences China Megvii Inc Beijing China University of Science and Technology of China China Institute of Microelectronics Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario. The main challenges of this task are the large intra-instance distance caused by different views and the subtle inter-instance discrepancy caused by similar vehicles. In this paper, we propose a parsing-based view-aware embedding network (PVEN) to achieve the view-aware feature alignment and enhancement for vehicle ReID. First, we introduce a parsing network to parse a vehicle into four different views and then align the features by mask average pooling. Such alignment provides a fine-grained representation of the vehicle. Second, in order to enhance the view-aware features, we design a common-visible attention to focus on the common visible views, which not only shortens the distance among intra-instances, but also enlarges the discrepancy of inter-instances. The PVEN helps capture the stable discriminative information of vehicle under different views. The experiments conducted on three datasets show that our model outperforms state-of-the-art methods by a large margin.

关键词： Feature extraction Task analysis Cameras Gallium nitride Training Image color analysis Fuses

来源：评论

学校读者我要写书评

暂无评论

Exploring outliers in crowdsourced ranking for QoE

arXiv

引用

arXiv 2017年

作者： Xu, Qianqian Yan, Ming Huang, Chendi Xiong, Jiechao Huang, Qingming Yao, Yuan Institute of Information Engineering Cas Beijing100093 Department of Computational Mathematics Michigan State University East LansingMI48824 United States BICMR-LMAM-LMEQF-LMP School of Mathematical Sciences Peking University Beijing100871 Tencent Ai Lab Shenzhen518057 University of Chinese Academy of Sciences Beijing100049 China Key Lab of Intell. Info. Process. Inst. of Comput. Tech. Cas Beijing100190 Key Lab of Big Data Mining and Knowledge Management Cas Beijing100190 Department of Mathematics Hong Kong University of Science and Technology 100871 Hong Kong

Outlier detection is a crucial part of robust evaluation for crowd-sourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years. In this paper, we propose some simple and fast algorithms for outlier detection and robust QoE evaluation based on the nonconvex optimization principle. Several iterative procedures are designed with or without knowing the number of outliers in samples. Theoretical analysis is given to show that such procedures can reach statistically good estimates under mild conditions. Finally, experimental results with simulated and real-world crowdsourcing datasets show that the proposed algorithms could produce similar performance to Huber-LASSO approach in robust ranking, yet with nearly 8 or 90 times speed-up, without or with a prior knowledge on the sparsity size of outliers, respectively. Therefore the proposed methodology provides us a set of helpful tools for robust QoE evaluation with crowdsourcing data. Copyright © 2017, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Research on adaptation criteria generation based on large data mining

Research on adaptation criteria generation based on large da...

引用

IEEE Chinese Guidance, Navigation and Control Conference (CGNCC)

作者： Hong-Quan Yun Li Xu Hao Dou De-Lie Ming National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute China Nat. Key Lab. of Sci. & Technol. on Aerosp. Intell. Control Beijing Aerosp. Autom. Control Inst. China State Key Lab. for Multi-spectral Inf. Process. Technol. Huazhong University of Science and Technology Wuhan Hubei CN

ISBN: (纸本)9781467383196

This paper performs research on adaptation analysis based on large amount of multi-source remote sensing data. In view of different demands from different task background, the research is firstly focused on how to analyze the data in computer language. To achieve this, the feature parameters of target areas are extracted from different target area geographic data. In combination of ORACLE database engine, data mining technology is used to carry out the target area adaptation assessment, and extract corresponding adaptation criteria. We test the trained adaptation criteria on multi-source geographic information data of different target areas. Experimental results show that the resulting criterion has certain coincidence rate and robustness.

关键词： Image edge detection Decision trees Stability criteria Pattern matching Guidelines Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Ranking Sentences in Scientific Literatures

Ranking Sentences in Scientific Literatures

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Jiao Tian Mengyun Cao Jin Liu Xiaoping Sun Zhuge Hai University of Chinese Academy of Sciences Beijing China Knowledge Grid Group CAS Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Wuhan University CAS Key Lab. of Intell. Inf. Process. Institute of Computing Technology Chinese Academy of Sciences Beijing CN

Sentence ranking is one of the most important research issues in text analysis. It can be used in extracted textual summarization and information retrieval. Graph-based methods are a common way of ranking and extracting sentences. In graph based methods, sentences are nodes of graph and edges are built based on the sentence similarities or on sentence co-occurrence relationship. PageRank style algorithms can be applied to get sentence ranks. In this paper, we focus on how to rank sentences in a single scientific paper. A scientific literature has more structural information than general texts and this structural information has not been fully explored yet in graph based ranking models. We investigated several different methods that used structural information such as paragraph and section information to construct a heterogeneous graph for ranking sentences. We conducted experiments on these methods to compare the results on sentence ranking. It shows that structural information can help identify more representative sentences.

关键词： Semantics Algorithm design and analysis Web pages Data mining Iterative methods Current measurement

来源：评论

学校读者我要写书评

暂无评论

Efficiently Finding Top-K Items from Evolving Distributed Data Streams

Efficiently Finding Top-K Items from Evolving Distributed Da...

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Baoyuan Qi Gang Ma Zhongzhi Shi Wei Wang University of Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Cas Beijing China Key Lab. of Intell. Inf. Process. Institute of Computing Technology Chinese Academy of Sciences Beijing CN Beijing Lexo Technologies Co. Ltd. Beijing China

ISBN: (纸本)9781479967162

The problem of efficiently finding top-k frequent items has attracted much attention in recent years. Storage constraints in the process.ng node and intrinsic evolving feature of the data streams are two main challenges. In this paper, we propose a method to tackle these two challenges based on space-saving and gossip-based algorithms respectively. Our method is implemented on SAMOA, a scalable advanced massive online analysis machine learning framework. The experimental results show its effectiveness and scalability.

关键词： Peer-to-peer computing Data mining Distributed databases Protocols Machine learning algorithms Monitoring Radiation detectors

来源：评论

学校读者我要写书评

暂无评论

Localize and segment scene text

Localize and segment scene text

引用

14th Pacific-Rim Conference on Multimedia, PCM 2013

作者： Liu, Xiaoqian Wang, Weiqiang School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Key Lab of Intell. Info. Process. CAS Institute of Computing Technology Beijing China

ISBN: (纸本)9783319037301

In this paper, we present a scene text extraction approach which can realize text localization and segmentation simultaneously. Two popular paradigms (machine learning method and rule-based method) are combined to achieve competitive performance. For a given image, a sliding window is used to detect scene text. The texture feature Local Binary Pattern is extracted to represent the content of each window, and an unbalanced SVM classifier is designed to identify candidate text regions. Then, candidate text windows are further verified using color contrast and binarized by an adaptive local thresholding computation to get candidate text connected components. Further, non-text ones among them are removed utilizing some empirical rules. Finally, text connected components are linked into text lines according to their spatial relationships and appearance similarities. The evaluation results on two challenging and standard datasets ICDAR 2003 and ICDAR 2011 demonstrate that the proposed approach can effectively detect and segment scene text with different sizes, fonts, colors and arrangement directions. © Springer International Publishing Switzerland 2013.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Location-Driven Geographical Topic Discovery

Location-Driven Geographical Topic Discovery

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Li Zhang Xiaoping Sun Hai Zhuge Knowledge Grid Lab. Key Lab. of Intell. Inf. Process. Beijing China University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences China

With the prevalence of geo-position devices GPS and smart phones, textual information, long or short, associated with GPS tags usually denoted by a coordinate with latitude and longitude is widely encountered on the Web. For example, in Twitter, smart phones record the location of every tweet after it is authorized. The spatial objects on Google map are also presented with some textual descriptions. These data provide researchers two-dimension perspectives, fusing both location and textual dimension. In real world, similar concepts, discussions, product sales and geographic objects are often gathered together which people are interest in. This paper studied three methods that combine a density-based clustering method DBSCAN with LDA (Latent Dirichlet Allocation) method in different ways to discover geographical topics. The first method clusters the GPS tagged documents and then for each clustered region, it applies LDA on the document set in that region, The second method first uses DBSCAN to find clusters among documents, merges documents from each cluster region into one document and form one document set on which LDA is applied, The third method applies LDA on the whole document set, and then, extracts topics generated by LDA in a specific region from DBSCAN. Abundant experiments are conducted with varying parameters. It is shown that three methods performed well in discovering topics in clusters, but the first two methods take much less computing time.

关键词： Global Positioning System Sports equipment Space vehicles Computers Educational institutions Data mining Analytical models

来源：评论

学校读者我要写书评

暂无评论

Fine-grained image classification using color exemplar classifiers

Fine-grained image classification using color exemplar class...

引用

14th Pacific-Rim Conference on Multimedia, PCM 2013

作者： Zhang, Chunjie Xiong, Wei Liu, Jing Zhang, Yifan Liang, Chao Huang, Qingming School of Computer and Control Engineering University of Chinese Academy of Sciences 100049 Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences P.O. Box 2728 Beijing China National Engineering Research Center for Multimedia Software Wuhan University 430072 Wuhan China Key Lab of Intell. Info. Process Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783319037301

The use of local features has demonstrated its effectiveness for many visual applications. However, local features are often extracted with gray images. This ignores the useful information within different color channels which eventually hinders the final performance, especially for fine-grained image classification. Besides, the semantic information of local features is too weak to be applied for high-level visual applications. To cope with these problems, in this paper, we propose a novel fine-grained image classification method by using color exemplar classifiers. For each image, we first decompose it into multiple color channels to take advantage of the color information. For each color channel, we represent each image with a response histogram which is generated by exemplar classifiers. Experiments on several public image datasets demonstrate the effectiveness of the proposed color exemplar classifier based image classification method. © Springer International Publishing Switzerland 2013.

关键词： Image classification

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：