检索结果-内蒙古大学图书馆

LORE++: Logical location regression network for table structure recognition with pre-training

Pattern Recognition 2025年 157卷

作者： Long, Rujiao Xing, Hangdi Yang, Zhibo Zheng, Qi Yu, Zhi Huang, Fei Yao, Cong Alibaba Group Zhejiang HangZhou China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Zhejiang Hangzhou China Equal contribution.

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Current approaches address this issue by either predicting the adjacency of detected cells or direct generation of structural sequences. Nonetheless, these approaches either count on additional heuristic rules for post-processing, or involve the generation of extremely long-range sequences that lead to computational intricacy. In this paper, We redefine TSR as a LOgical location REgression paradigm, which effectively captures inherent logical dependencies and constraints among table cells. Correspondingly, we propose LORE, a novel approach for TSR. LORE simultaneously predicts accurate geometric coordinates of table cells and the logical structures of the entire table. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other TSR paradigms. Moreover, to enhance the model's spatial and logical representation capabilities, we propose two pre-training tasks, resulting in an upgraded version named LORE++. The incorporation of pre-training is proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR. © 2024 Elsevier Ltd

关键词： Visual document understanding Table structure recognition OCR

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via joint local learning and group sparse regression

引用

Frontiers of Information Technology & Electronic Engineering 2019年第4期20卷 538-553页

作者： Yue WU Can WANG Yue-qing ZHANG Jia-jun BU Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science and Technology Zhejiang University Alibaba-Zhejiang University Joint Institute of Frontier Technologies

Feature selection has attracted a great deal of interest over the past decades. By selecting meaningful feature subsets, the performance of learning algorithms can be effectively improved. Because label information is expensive to obtain, unsupervised feature selection methods are more widely used than the supervised ones. The key to unsupervised feature selection is to find features that effectively reflect the underlying data distribution. However,due to the inevitable redundancies and noise in a dataset, the intrinsic data distribution is not best revealed when using all features. To address this issue, we propose a novel unsupervised feature selection algorithm via joint local learning and group sparse regression(JLLGSR). JLLGSR incorporates local learning based clustering with group sparsity regularized regression in a single formulation, and seeks features that respect both the manifold structure and group sparse structure in the data space. An iterative optimization method is developed in which the weights finally converge on the important features and the selected features are able to improve the clustering results. Experiments on multiple real-world datasets(images, voices, and web pages) demonstrate the effectiveness of JLLGSR.

关键词： Unsupervised Local learning Group sparse regression Feature selection

来源：评论

学校读者我要写书评

暂无评论

Crowdsourcing-based web accessibility evaluation with golden maximum likelihood inference

引用

Proceedings of the ACM on Human-Computer Interaction 2018年第CSCW期2卷 1-21页

作者： Song, Shuyi Bu, Jiajun Artmeier, Andreas Shi, keyue Wang, Ye Yu, Zhi Wang, Can Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China

Web accessibility evaluation examines how well websites comply with accessibility guidelines which help people with disabilities to perceive, navigate and contribute to the Web. This demanding task usually requires manual assessment by experts with many years of training and experience. However, not enough experts are available to carry out the increasing number of evaluation projects while non-experts often have different opinions about the presence of accessibility barriers. Addressing these issues, we introduce a crowdsourcing system with a novel truth inference algorithm to derive reliable and accurate assessments from conflicting opinions of evaluators. Extensive evaluation on 23,901 complex tasks assessed by 50 people with and without disabilities shows that our approach outperforms state of the art approaches. In addition, we conducted surveys to identify frequent barriers that people with disabilities are facing in their daily lives and the difficulty to access Web pages when they encounter these barriers. The frequencies and severities of barriers correlate with their derived importance in our evaluation project. Copyright © ACM.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Speech Guided Disentangled Visual Representation Learning for Lip Reading 21

Speech Guided Disentangled Visual Representation Learning fo...

引用

23rd ACM International Conference on Multimodal Interaction, ICMI 2021

作者： Zhao, Ya Ma, Cheng Feng, Zunlei Song, Mingli Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Zhejiang Hangzhou China

ISBN: (纸本)9781450384810

Lip reading has achieved unparalleled development in recent years. However, existing methods have two main problems: 1) there is no explicit mechanism to ensure that the extracted visual features are only related to lip movements, resulting in degraded performance when video contains large variations, such as speakers' poses;2) quantities of labeled data are required to achieve good results, which are difficult to obtain in low-resource languages. In this paper, we propose a new visual representation learning method, SVLR, whose purpose is to extract disentangled, lip movements related visual features for lip reading task, by making use of quantities of unlabeled audio-visual data. This is achieved by explicitly disentangling the feature into lip movements related part and speaker identity related part. Then predicting speech from the disentangled features is used as the training objective to optimize model parameters. After this cross-modal training, the video encoder that extracts lip movements features is used as a feature extractor for the lip reading task. Various experiments on several word-level lip reading benchmarks have proved the effectiveness of the proposed method. © 2021 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification of Road Cracks Based on Semantic-Aware Mixup 4

Multi-label Classification of Road Cracks Based on Semantic-...

引用

4th International Conference on Computers, Information Processing and Advanced Education, CIPAE 2023

作者： Xu, Chengyang Zhou, Chunpeng Yu, Zhi Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Hangzhou China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Hangzhou China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Ningbo China

ISBN: (纸本)9798350342710

In the realm of road crack detection scenarios, Mixup, a widely used data augmentation technique, exhibits constrained effectiveness in multi-label classification, unlike its performance on general datasets. This paper investigates the reasons behind this limitation, identifying two main factors: (1) the mutually exclusive nature of road crack labels and (2) the potential generation of incorrect labels during image mixing. To address these issues, we propose an approach called Semantic-Aware Mixup (SA-Mixup), which focuses on enhancing crack samples specifically. Experimental evaluations on three distinct road crack datasets demonstrate the effectiveness and simplicity of our proposed method. The results highlight significant improvements in model performance, offering a promising solution for accurate and efficient multi-label classification in road crack detection tasks. © 2023 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Enabling reliable and efficient network reboot in wireless sensor networks 1

引用

7th China Conference of Wireless Sensor Networks, CWSN 2013

作者： Wu, Wenbin Gao, Yi Zhang, Xuefeng Huang, Chao Dong, Wei Zhejiang Key Laboratory of Service Robot CS College Zhejiang University Hangzhou Zhejiang China

ISBN: (数字)9783642541742

ISBN: (纸本)9783642541735

Wireless sensor networks often encounter unexpected failures due to a variety of reasons. Since detecting the failed nodes is normally a nontrivial work, rebooting all the nodes in the network is an effective mechanism to recover from failures. This paper presents NR, a network reboot mechanism based on TinyOS, which enables reliable and efficient network reboot in WSNs. NR ensures 100 % reliability by incorporating an eventual consistency dissemination protocol. It avoids flash I/Os by storing data items on persistent RAM. Evaluation results show that NR can ensure 100 % reliability and is efficient in I/O operations. © 2014 Springer-Verlag Berlin Heidelberg.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Matching Varying-Length Texts via Topic-Informed and Decoupled Sentence Embeddings

Matching Varying-Length Texts via Topic-Informed and Decoupl...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Zhou, Xixi Gu, Chunbin Jie, Xin Bu, Jiajun Wang, Haishuai Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China

ISBN: (纸本)9798891761193

Measuring semantic similarity between texts is a crucial task in natural language processing. While existing semantic text matching focuses on pairs of similar-length sequences, matching texts with non-comparable lengths has broader applications in specific domains, such as comparing professional document summaries and content. Current approaches struggle with text pairs of non-comparable lengths due to truncation issues. To address this, we split texts into natural sentences and decouple sentence representations using supervised contrastive learning (SCL). Meanwhile, we adopt the embedded topic model (ETM) for specific domain data. Our experiments demonstrate the effectiveness of our model, based on decoupled and topic-informed sentence embeddings, in matching texts of significantly different lengths across three well-studied datasets. © 2024 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

Colorization for gray scale facial image by locality-constrained linear coding

Colorization for gray scale facial image by locality-constra...

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Liang, Yang Song, Mingli Bu, Jiajun Chen, Chun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China

ISBN: (纸本)9783642347771

Colorization for gray scale facial image is an important technique in various practical applications. However, the methods that have been proposed are essentially semi-automatic. In this paper, we present a new probabilistic framework based on Maximum A Posteriori (MAP) estimation to automatically transform the given gray scale facial image to corresponding color one. Firstly, the input image is divided into several patches and non-parametric Markov random field (MRF) is employed to formulate the global energy. Secondly, Locality-constrained Linear Coding (LLC) is employed to learn the color distribution for each patch. At the same time, the simulated annealing algorithm is employed to iteratively update the patches chosen by LLC to optimize the MRF by decreasing global energy cost. The experimental results demonstrate that the proposed framework is effective to colorize the gray scale facial images to corresponding color ones. © 2012 Springer-Verlag.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Pose estimation with motionlet LLC coding

Pose estimation with motionlet LLC coding

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Sun, Li Song, Mingli Bu, Jiajun Chen, Chun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China

ISBN: (纸本)9783642347771

3D human pose estimation is a challenging but important research topic with abundant applications. As for discriminative human pose estimation, the main goal is to learn a nonlinear mapping from image descriptors to 3D human pose configurations, which is difficult due to the high-dimensionality of human pose space and the multimodality of the distribution. To address these problems, we propose a novel motionlet LLC coding on a discriminative framework. A motionlet consists of training examples covering a local area in terms of image space, pose space and time stream. We first group most informative and helpful training examples into motionlets, then perform LLC Coding to learn the nonlinear mapping and get candidate poses, and finally choose the most appropriate pose as the result estimate. To further eliminate ambiguities and improve robustness, we extend our framework to incorporate multiviews. We conduct qualitative evaluation on our Taichi data set and quantitative evaluation on HumanEva data set, which show that our approach has gained the-state-of-the-art performance and significant improvement against previous approaches. © 2012 Springer-Verlag.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Large-scale outdoor scene classification by boosting a set of highly discriminative and low redundant graphlets

Large-scale outdoor scene classification by boosting a set o...

引用

11th IEEE International Conference on Data Mining Workshops, ICDMW 2011

作者： Zhang, Luming Song, Mingli Deng, Xiaoyu Bu, Jiajun Chen, Chun Zhejiang Provincial Key Laboratory of Service Robot Computer Science College Zhejiang University China

ISBN: (纸本)9780769544090

Large-scale outdoor scene classification is an important issue in multimedia information retrieval. In this paper, we propose an efficient scene classification model by integrating outdoor scene image's local features into a set of highly discriminative and less redundant graphlets (i.e., small connected subgraph). Firstly, each outdoor scene image is segmented into a number of regions in terms of its color intensity distribution. And a region adjacency graph (RAG) is defined to encode the geometric property and color intensity distribution of outdoor scene image. Then, the frequent sub-structures are mined statistically from the RAGs corresponding to the training outdoor scene images. And a selecting process is carried out to obtain a set of sub-structures from the frequent ones towards being highly discriminative and low redundant. And these selected substructures are used as templates to extract the corresponding graphlets. Finally, we integrate these extracted graphlets by a multi-class boosting strategy for outdoor scene classification. The experimental results on the challenging SUN [1] data set and the LHI [14] data set validate the effectiveness of our approach. © 2011 IEEE.

关键词： Classification (of information)

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：