检索结果-内蒙古大学图书馆

NOTA: Multimodal Music Notation Understanding for Visual Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Mingni Li, Jiajia Yang, Lu Zhang, Zhiqiang Tian, Jinghao Li, Zuchao Zhang, Lefei Wang, Ping School of Computer Science Wuhan University Wuhan China Key Laboratory of Archival Intelligent Development and Service NAAC China School of Information Management Wuhan University Wuhan China

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3 tasks. Based on the dataset, we trained NotaGPT, a music notation visual large language model. Specifically, we involve a pre-alignment training phase for cross-modal alignment between the musical notes depicted in music score images and their textual representation in ABC notation. Subsequent training phases focus on foundational music information extraction, followed by training on music notation analysis. Experimental results demonstrate that our NotaGPT-7B achieves significant improvement on music understanding, showcasing the effectiveness of NOTA and the training pipeline. Our datasets are open-sourced at https://***/datasets/MYTH-Lab/NOTA-dataset. © 2025, CC BY.

关键词： Visual languages

Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Lu Li, Jiajia Ci, En Zhang, Lefei Li, Zuchao Wang, Ping School of Computer Science Wuhan University Wuhan China School of Information Management Wuhan University Wuhan China Key Laboratory of Archival Intelligent Development and Service NAAC China

Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multimodal, few-shot and zero-shot settings.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Information retrieval

Research and Practice on Network Security Vulnerability Management Methods in the Transportation Industry 23

学校读者我要写书评

暂无评论

Research and Practice on Network Security Vulnerability Mana...

Proceedings of the 2023 International Conference on Artificial Intelligence, Systems and Network Security

作者： Wei Li Kuang Tian Wei Wang Key Laboratory for Comprehensive Traffic Operation Monitoring and Service Beijing Intelligent Transportation Development Center China

ISBN: (纸本)9798400716966

关键词：

ArcMMLU: A Library and Information Science Benchmark for Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Shitou Li, Zuchao Liu, Xingshen Yang, Liming Wang, Ping Key Laboratory of Archival Intelligent Development and Service NAAC United States School of Information Management Wuhan University China School of Computer Science Wuhan University China School of Law Tsinghua University China

In light of the rapidly evolving capabilities of large language models (LLMs), it becomes imperative to develop rigorous domain-specific evaluation benchmarks to accurately assess their capabilities. In response to this need, this paper introduces ArcMMLU, a specialized benchmark tailored for the Library & Information Science (LIS) domain in Chinese. This benchmark aims to measure the knowledge and reasoning capability of LLMs within four key sub-domains: archival Science, Data Science, Library Science, and Information Science. Following the format of MMLU/CMMLU, we collected over 6,000 high-quality questions for the compilation of ArcMMLU. This extensive compilation can reflect the diverse nature of the LIS domain and offer a robust foundation for LLM evaluation. Our comprehensive evaluation reveals that while most mainstream LLMs achieve an average accuracy rate above 50% on ArcMMLU, there remains a notable performance gap, suggesting substantial headroom for refinement in LLM capabilities within the LIS domain. Further analysis explores the effectiveness of few-shot examples on model performance and highlights challenging questions where models consistently underperform, providing valuable insights for targeted improvements. ArcMMLU fills a critical gap in LLM evaluations within the Chinese LIS domain and paves the way for future development of LLMs tailored to this specialized area. © 2023, CC BY-SA.

关键词： Computational linguistics

A Novel Hybrid Makeup Transfer Method Based on Latent Vector Manipulation 2

学校读者我要写书评

暂无评论

A Novel Hybrid Makeup Transfer Method Based on Latent Vector...

2nd International Conference on Artificial Intelligence and Computer Information Technology, AICIT 2023

作者： Li, Yumiao Li, Peng Shen, Ziqi Li, Wenhui Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi'an710119 China School of Computer Science Shaanxi Normal University Xi'an710119 China Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an710062 China Engineering Laboratory of Teaching Information Technology of Shaanxi Province Xi'an710119 China Xi'an Key Laboratory of Cultural Tourism Resources Development and Utilization Xi'an710062 China

ISBN: (纸本)9798350302950

With the development of image processing technology and the improvement of people's living standards, there is a wide demand for makeup services in society. In this paper, we focus on style transfer and its application in automatic makeup generation, and propose a facial feature fusion recovery technique that utilizes an adaptive spatial feature fusion attention mechanism to solve the problem of inconsistent clarity between the reference image and the source image. By using the moving least squares method to calculate similarity on each sample image, the reference image set achieving the optimal makeup transfer effect can be efficiently selected. At the same time, the latent vector can be manipulated to achieve on-demand hybrid makeup generation and de-makeup image generation. By assigning different weights, the proportion of makeup in specific reference image in the final makeup effect can be controlled, and a new mixed makeup style can be obtained. The experiment shows that the proposed model can achieve state-of-the-art makeup transfer effect, and can also generate suitable makeup effects for low resolution input images. © 2023 IEEE.

关键词： Image enhancement

A Sentiment Classification Model Based on Attention TIG-CNN-BiGRU

学校读者我要写书评

暂无评论

A Sentiment Classification Model Based on Attention TIG-CNN-...

2023 International Conference on Culture-Oriented Science and Technology, CoST 2023

作者： Li, Peng Liang, Tianmian An, Ning Zhang, Lichen Wu, Xiaojun Wang, Xiaoming Lu, Junling Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi'an710119 China School of Computer Science Shaanxi Normal University Xi'an710119 China Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an710062 China Engineering Laboratory of Teaching Information Technology of Shaanxi Province Xi'an710119 China Xi'An Key Laboratory of Cultural Tourism Resources Development and Utilization Xi'an710062 China

ISBN: (纸本)9798350357998

The uniqueness of folk song expression forms and complex semantic relationships, and the existing models are not good at recognizing the emotion category of folk song lyrics, so an attention TIG-CNN-BiGRU based emotion classification model is proposed. That is, we first propose a text vector representation based on TF-IDF feature weighted pretrained Glove word embedding to extract important features by assigning different weights, and then combine CNN, BiGRU and attention mechanism to extract local features using multi-scale convolutional kernel CNN, BiGRU to capture semantic dependencies of long sequences and attention mechanism to assign high weights to key features to make the model have better lyrics recognition ability. Experiments comparing the model with various baseline methods on the lyrics dataset show that the model outperforms other lyrics sentiment classification models in terms of sentiment classification accuracy and various other metrics. © 2023 IEEE.

关键词： Deep neural networks

Hypergraph based Understanding for Document Semantic Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Qiwei Li, Zuchao Wang, Ping Ai, Haojun Zhao, Hai School of Computer Science Wuhan University China School of Information Management Wuhan University China School of Cyber Science and Engineering Wuhan University China Key Laboratory of Archival Intelligent Development and Service NAAC China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus on entity categories while ignoring the extraction of entity boundaries. We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. It can conduct a more detailed analysis of the document text representation analyzed by the upstream model and achieves a better performance of semantic information. We apply this method on the basis of GraphLayoutLM to construct a new semantic entity recognition model HGALayoutLM. Our experiment results on FUNSD, CORD, XFUND and SROIE show that our method can effectively improve the performance of semantic entity recognition tasks based on the original model. The results of HGALayoutLM on FUNSD and XFUND reach the new state-of-the-art results. © 2024, CC BY.

关键词： Semantics

The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiajia Yang, Lu Tang, Mingni Chen, Cong Li, Zuchao Wang, Ping Zhao, Hai School of Information Management Wuhan University Wuhan China Key Laboratory of Archival Intelligent Development and Service NAAC China School of Computer Science Wuhan University Wuhan China School of Music Shenyang Conservatory of Music Shenyang China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs' capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-Eval, a comprehensive and large-scale music benchmark specifically designed to evaluate the musicrelated capabilities of LLMs. ZIQI-Eval encompasses a wide range of questions, covering 10 major categories and 56 subcategories, resulting in over 14,000 meticulously curated data entries. By leveraging ZIQI-Eval, we conduct a comprehensive evaluation over 16 LLMs to evaluate and analyze LLMs' performance in the domain of music. Results indicate that all LLMs perform poorly on the ZIQI-Eval benchmark, suggesting significant room for improvement in their musical capabilities. With ZIQIEval, we aim to provide a standardized and robust evaluation framework that facilitates a comprehensive assessment of LLMs' musicrelated abilities. The dataset is available at GitHub1 and HuggingFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Music

The statistical observation localized equivalent-weights particle filter in a simple nonlinear model

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 2022年第2期41卷 80-90页

作者： Yuxin Zhao Shuo Yang Renfeng Jia Di Zhou Xiong Deng Chang Liu Xinrong Wu College of Intelligent Systems Science and Engineering Harbin Engineering UniversityHarbin 150001China Harbin Marine Boiler&Turbine Research Institute Harbin 150078China China Ship Development and Design Center Wuhan 430064China Key Laboratory of Marine Environmental Information Technology National Marine Data and Information ServiceState Oceanic AdministrationTianjin 300171China

This paper presents an improved approach based on the equivalent-weights particle filter(EWPF)that uses the proposal density to effectively improve the traditional particle *** proposed approach uses historical data to calculate statistical observations instead of the future observations used in the EWPF’s proposal density and draws on the localization scheme used in the localized PF(LPF)to construct the localized *** new approach is called the statistical observation localized EWPF(LEWPF-Sobs);it uses statistical observations that are better adapted to the requirements of real-time assimilation and the localization function is used to calculate weights to reduce the effect of missing observations on the *** approach not only retains the advantages of the EWPF,but also improves the assimilation quality when using sparse *** experiments performed with the Lorenz 96 model show that the statistical observation EWPF is better than the EWPF and EAKF when the model uses standard distribution *** of the statistical observation localized EWPF and LPF reveal the advantages of the new method,with fewer particles giving better *** particular,the new improved filter performs better than the traditional algorithms when the observation network contains densely spaced measurements associated with model state nonlinearities.

关键词： data assimilation particle filter equivalent weights particle filter localization methods