检索结果-内蒙古大学图书馆

36th Conference on Neural Information processing Systems (NeurIPS)

作者： Gokul, N. C. Ladi, Manideep Negi, Sumit Selvaraj, Prem Kumar, Pratyush Khapra, Mitesh AI4Bharat Chennai India IIT Madras Chennai India Microsoft Res Redmond WA USA

ISBN: (纸本)9781713871088

There are over 300 sign languages in the world, many of which have very limited or no labelled sign-to-text datasets. To address low-resource data scenarios, selfsupervised pretraining and multilingual finetuning have been shown to be effective in natural language and speech processing. In this work, we apply these ideas to sign language recognition. We make three contributions. first, we release SignCorpus, a large pretraining dataset on sign languages comprising about 4.6K hours of signing data across 10 sign languages. SignCorpus is curated from sign language videos on the internet, filtered for data quality, and converted into sequences of pose keypoints thereby removing all personal identifiable information (PII). Second, we release Sign2Vec, a graph-based model with 5.2M parameters that is pretrained on SignCorpus. We envisage Sign2Vec as a multilingual large-scale pretrained model which can be fine-tuned for various sign recognition tasks across languages. Third, we create MultiSign-ISLR - a multilingual and label-aligned dataset of sequences of pose keypoints from 11 labelled datasets across 7 sign languages, and MultiSign-FS - a new finger-spelling training and test set across 7 languages. On these datasets, we fine-tune Sign2Vec to create multilingual isolated sign recognition models. With experiments on multiple benchmarks, we show that pretraining and multilingual transfer are effective giving significant gains over state-of-the-art results. All datasets, models, and code has been made open-source via the OpenHands toolkit(1).

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Clinical graph Transformer for Ophthalmic Report Generation

Cross-modal Clinical Graph Transformer for Ophthalmic Report...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Mingjie Cai, Wenjia Verspoor, Karin Pan, Shirui Liang, Xiaodan Chang, Xiaojun Monash Univ Dept Data Sci & Artificial Intelligence Clayton Vic Australia Sun Yat Sen Univ Zhongshan Ophthalm Ctr State Key Lab Ophthalmol Guangzhou Peoples R China RMIT Univ Sch Comp Technol Melbourne Vic Australia Sun Yat Sen Univ Sch ISE Peng Cheng Natl Lab Guangzhou Peoples R China Univ Technol Sydney AAII ReLER Sydney NSW Australia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Automatic generation of ophthalmic reports using data-driven neural networks has great potential in clinical practice. When writing a report, ophthalmologists make inferences with prior clinical knowledge. This knowledge has been neglected in prior medical report generation methods. To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure. However, two major common Knowledge Noise (KN) issues may affect models' effectiveness. 1) Existing general biomedical knowledge bases such as the UMLS may not align meaningfully to the specific context and language of the report, limiting their utility for knowledge injection. 2) Incorporating too much knowledge may divert the visual features from their correct meaning. To overcome these limitations, we design an automatic information extraction scheme based on natural language processing to obtain clinical entities and relations directly from in-domain training reports. Given a set of ophthalmic images, our CGT first restores a sub-graph from the clinical graph and injects the restored triples into visual features. Then visible matrix is employed during the encoding procedure to limit the impact of knowledge. Finally, reports are predicted by the encoded cross-modal features via a Transformer decoder. Extensive experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods and achieve state-of-the-art performances.

关键词： Training Visualization Unified modeling language Benchmark testing Writing Transformers Image restoration

来源：评论

学校读者我要写书评

暂无评论

Scene graph disentanglement and composition for generalizable complex image generation 24

Scene graph disentanglement and composition for generalizabl...

引用

proceedings of the 38th International Conference on Neural Information processing Systems

作者： Yunnan Wang Ziqiang Li Wenyao Zhang Zequn Zhang Baao Xie Xihui Liu Wenjun Zeng Xin Jin Shanghai Jiao Tong University Shanghai China and Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo China and University of Science and Technology of China Hefei China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo China The University of Hong Kong Hong Kong China

ISBN: (纸本)9798331314385

There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their relationships. To address this issue, we leverage the scene graph, a powerful structured representation, for complex image generation. Different from the previous works that directly use scene graphs for generation, we employ the generative capabilities of variational autoencoders and diffusion models in a generalizable manner, compositing diverse disentangled visual clues from scene graphs. Specifically, we first propose a Semantics-Layout Variational AutoEncoder (SL-VAE) to jointly derive (layouts, semantics) from the input scene graph, which allows a more diverse and reasonable generation in a one-to-many mapping. We then develop a Compositional Masked Attention (CMA) integrated with a diffusion model, incorporating (layouts, semantics) with fine-grained attributes as generation guidance. To further achieve graph manipulation while keeping the visual content consistent, we introduce a Multi-Layered Sampler (MLS) for an "isolated" image editing effect. Extensive experiments demonstrate that our method outperforms recent competitors based on text, layout, or scene graph, in terms of generation rationality and controllability. Code is available at https://***/wangyunnan/DisCo.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discontinuous Named Entity Recognition as Maximal Clique Discovery 59

Discontinuous Named Entity Recognition as Maximal Clique Dis...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on natural language processing (IJCNLP) / 6th workshop on Representation Learning for NLP (RepL4NLP)

作者： Wang, Yucheng Yu, Bowen Zhu, Hongsong Liu, Tingwen Yu, Nan Sun, Limin Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9781954085527

Named entity recognition (NER) remains challenging when entity mentions can be discontinuous. Existing methods break the recognition process into several sequential steps. In training, they predict conditioned on the golden intermediate results, while at inference relying on the model output of the previous steps, which introduces exposure bias. To solve this problem, we first construct a segment graph for each sentence, in which each node denotes a segment (a continuous entity on its own, or a part of discontinuous entities), and an edge links two nodes that belong to the same entity. The nodes and edges can be generated respectively in one stage with a grid tagging scheme and learned jointly using a novel architecture named Mac. Then discontinuous NER can be reformulated as a non-parametric process of discovering maximal cliques in the graph and concatenating the spans in each clique. Experiments on three benchmarks show that our method outperforms the state-of-the-art (SOTA) results, with up to 3.5 percentage points improvement on F1, and achieves 5x speedup over the SOTA model.(1)

关键词： graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Leveraging language-Aligned Visual Knowledge for Remote Sensing Image Spectral Super-Resolution

Leveraging Language-Aligned Visual Knowledge for Remote Sens...

引用

workshop on Hyperspectral Image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Bowen Chen Keyan Chen Liqin Liu Zhenwei Shi Zhengxia Zou Image Processing Center School of Astronautics Beihang University Beijing China Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing China

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

Spectral super-resolution (SSR) can reconstruct hyperspectral images (HSIs) from images with fewer spectral bands, such as RGB images, to furnish critical spectral information for var-ious downstream applications. However, existing SSR meth-ods for remote sensing images often focus solely on mapping RGB pixels to spectral signatures, neglecting semantic con-tent. This oversight may result in the omission of critical semantic details and inaccurate spatial-spectral textures. To address these issues, we propose language-Aligned Visual Embedding-Driven Spectral Super-Resolution (LAVER), a novel SSR method that leverages the rich vision-language pri-ors in the Contrastive language-Image Pre-training (CLIP) model. Specifically, we first design a denoising diffusion model-based baseline and then propose Local CLIP and language-Enhanced Spectral Fusion Block (LESFB) to un-leash the potential of language-aligned visual embeddings. LAVER can reconstruct HSIs with higher fidelity and better details than the baseline and other advanced methods. Codes can be found at http://***/Mr-Bamboo/LAVER.

关键词： Visualization Codes Conferences Superresolution Semantics Noise reduction Spatial resolution Image reconstruction Signal resolution Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Learning of graph-based question answering rules 1

Learning of graph-based question answering rules

引用

1st workshop on graph-based Algorithms for natural language processing, Textgraphs 2006 at Human language Technologies

作者： Mollá, Diego Department of Computing Macquarie University Sydney2109 Australia

In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences. Question answering rules are automatically learnt from a training corpus of questions and answer sentences with the answer annotated. The method is independent from the graph representation formalism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences. © 2006 Association for Computational Linguistics

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Multi-view Unsupervised Representation Learning via Integration of Fuzzy Rules and graph-based Adaptive Regularization

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Zhu, Yi Li, Dong Xi, Chao Pedrycz, Witold Macau University of Science and Technology School of Computer Science and Engineering China East China University of Technology School of Mechanical and Electronic Engineering Nanchang330013 China Gliwice Department of Measurement and Control Systems Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey

With the rapid advancement of data acquisition technologies, multiview data have been widely applied in fields such as social networks, computer vision, and natural language processing. Multiview data typically contain information arising from different views or sensors, offering more perspectives for observation. The multiview nature also brings challenges, such as high dimensionality, noise, heterogeneity, and redundancy. Particularly, in scenarios with limited labeled data, traditional single-view learning methods often struggle to handle these complex issues. To address this, this article proposes an unsupervised multiview learning framework that integrates Takagi–Sugeno–Kang fuzzy systems and graph-based adaptive regularization (MvTSK-GAR) to handle the heterogeneity and redundancy in multiview data effectively. Specifically, this article first captures the uncertainty in multiview data through fuzzy rules and models the structural relationships between the data using graph-based adaptive regularization. The framework does not rely on a large amount of labeled data. Instead, it integrates complementary information coming from different views to automatically mine latent patterns, thus generating more accurate and stable data representations. Experimental results demonstrate that the proposed framework performs well in various real-world applications, particularly excelling in high-dimensional data processing and noise reduction. Good performance in multiple publicly available datasets validates the effectiveness of our approach. Thecode is available at https://***/r/MvTSK-GAR-E3FB/***. © 1993-2012 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Evaluation of French Research Projects in the Acquisition Process of Research Tax Credit (CIR) 26

Automatic Evaluation of French Research Projects in the Acqu...

引用

26th International Conference on Knowledge-based and Intelligent Information and Engineering Systems, KES 2022

作者： Carvallo, J. Ramezanpanah, Z. Rodriguez, A. MYTEAM 179 rue de la Pompe Paris75116 France

In this work, we evaluated research projects of French companies using natural language processing. To this end, we designed a system able to estimate the probability of obtaining a research tax credit (CIR) for a project based on its technical description. This system is designed around two modules whose outputs are concatenated and fed to a fully-connected neural network that predicts the probability of success for the project. The first module uses the FastText algorithm and a Convolutional Neural Network to extract a Text Embedding vector. The second module uses an unsupervised knowledge graph extraction method and a graph Neural Network to extract a graph Embedding vector. The texts used as data in this study describe the research projects of companies and are written in French. Due to their high confidentiality, no similar examples exist in the literature. This data is provided by a partner consulting firm whose work consists in helping companies raise funds for their research projects. Since the methods in the literature were not effective in extracting the knowledge graphs used in the second module for our data, we present a new Knowledge graph extraction using an unsupervised Named Entities Recognition, NER, as our contribution. © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 26th International Conference on Knowledge-based and Intelligent Information & Engineering Systems (KES 2022)

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

graph-based generalized latent semantic analysis for document representation 1

Graph-based generalized latent semantic analysis for documen...

引用

1st workshop on graph-based Algorithms for natural language processing, Textgraphs 2006 at Human language Technologies

作者： Matveeva, Irina Levow, Gina-Anne Dept. of Computer Science University of Chicago ChicagoIL60637 United States

Document indexing and representation of term-document relations are very important for document clustering and retrieval. In this paper, we combine a graph-based dimensionality reduction method with a corpus-based association measure within the Generalized Latent Semantic Analysis framework. We evaluate the graph-based GLSA on the document clustering task. © 2006 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

Combining Visual and Linguistic Models for a Robust Recipient Line Recognition in Historical Documents 15th

Combining Visual and Linguistic Models for a Robust Recipien...

引用

15th IAPR International workshop on Document Analysis Systems (DAS)

作者： Mayr, Martin Felker, Alex Maier, Andreas Christlein, Vincent Friedrich Alexander Univ Erlangen Nurnberg Pattern Recognit Lab Erlangen Germany

ISBN: (纸本)9783031065552;9783031065545

Automatically extracting targeted information from historical documents is an important task in the field of document analysis and eases the work of historians when dealing with huge corpora. In this work, we investigate the idea of retrieving the recipient transcriptions from the Nuremberg letterbooks of the 15th century. This task can be solved with fundamentally different ways of approaching it. first, detecting recipient lines solely based on visual features and without any explicit linguistic feedback. Here, we use a vanilla U-Net and an attention-based U-Net as representatives. Second, linguistic feedback can be used to classify each line accordingly. This is done on the one hand with handwritten text recognition (HTR) for predicting the transcriptions and on top of it a light-wight natural language processing (NLP) model distinguishing whether the line is a recipient line or not. On the other hand, we adapt a named entity recognition transformer model. The system jointly performs the line transcription and the recipient line recognition. For improving the performance, we investigated all the possible combinations with the different methods. In most cases the combined output probabilities outperformed the single approaches. The best combination achieved on the hard test set an F1 score of 80% and recipient line recognition accuracy of about 96% while the best single approach only reached about 74% and 94%, respectively.

关键词： Recipient recognition natural language processing Semantic image segmentation Handwritten text recognition

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：