检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Network for Joint Multimodal Entity-Relation Extraction

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第1期37卷 1-14页

作者： Yuan, Li Cai, Yi Xu, Jingyu Li, Qing Wang, Tao South China Univ Technol Minist Educ Sch Software Engn Key Lab Big Data & Intelligent Robot Guangzhou 510641 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Kings Coll London Dept Biostat & Hlth Informat London WC2R 2LS England

Joint multimodal entity-relation extraction (JMERE) is a challenging task that involves two joint subtasks, i.e., named entity recognition and relation extraction, from multimodal data such as text sentences with associated images. Previous JMERE methods have primarily employed 1) pipeline models, which apply pre-trained unimodal models separately and ignore the interaction between tasks, or 2) word-pair relation tagging methods, which neglect neighboring word pairs. To address these limitations, we propose a fine-grained network for JMERE. Specifically, we introduce a fine-grained alignment module that utilizes a phrase-patch to establish connections between text phrases and visual objects. This module can learn consistent multimodal representations from multimodal data. Furthermore, we address the task-irrelevant image information issue by proposing a gate fusion module, which mitigates the impact of image noise and ensures a balanced representation between image objects and text representations. Furthermore, we design a multi-word decoder that enables ensemble prediction of tags for each word pair. This approach leverages the predicted results of neighboring word pairs, improving the ability to extract multi-word entities. Evaluation results from a series of experiments demonstrate the superiority of our proposed model over state-of-the-art models in JMERE.

关键词： Visualization data mining Contrastive learning Feature extraction Brain modeling Tagging Semantics Predictive models Pipelines Logic gates entity-relation extraction multimodal pre-trained model

来源：评论

学校读者我要写书评

暂无评论

On RNN-Based k-WTA Models With Time-Dependent Inputs

引用

IEEE/CAA Journal of Automatica Sinica 2022年第11期9卷 2034-2036页

作者： Mei Liu Mingsheng Shang the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714 the Chongqing School University of Chinese Academy of SciencesChongqing 400714China

Dear editor,This letter identifies two weaknesses of state-of-the-art k-winnerstake-all(k-WTA)models based on recurrent neural networks(RNNs)when considering time-dependent inputs,i.e.,the lagging error and the infeas... 详细信息

关键词： letter convergence finite

来源：评论

学校读者我要写书评

暂无评论

HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models

arXiv

引用

arXiv 2024年

作者： Yang, Yifan Liu, Dong Zhang, Shuhai Deng, Zeshuai Huang, Zixiong Tan, Mingkui South China University of Technology China Pazhou Lab Key Laboratory of Big Data and Intelligent Robot Ministry of Education China

Reconstructing 3D clothed human involves creating a detailed geometry of individuals in clothing, with applications ranging from virtual try-on, movies, to games. To enable practical and widespread applications, recent advances propose to generate a clothed human from an RGB image. However, they struggle to reconstruct detailed and robust avatars simultaneously. We empirically find that the high-frequency (HF) and low-frequency (LF) information from a parametric model has the potential to enhance geometry details and improve robustness to noise, respectively. Based on this, we propose HiLo, namely clothed human reconstruction with high- and low-frequency information, which contains two components. 1) To recover detailed geometry using HF information, we propose a progressive HF Signed Distance Function to enhance the detailed 3D geometry of a clothed human. We analyze that our progressive learning manner alleviates large gradients that hinder model convergence. 2) To achieve robust reconstruction against inaccurate estimation of the parametric model by using LF information, we propose a spatial interaction implicit function. This function effectively exploits the complementary spatial information from a low-resolution voxel grid of the parametric model. Experimental results demonstrate that HiLo outperforms the state-of-the-art methods by 10.43% and 9.54% in terms of Chamfer distance on the Thuman2.0 and CAPE datasets, respectively. Additionally, HiLo demonstrates robustness to noise from the parametric model, challenging poses, and various clothing styles. 1 Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Explicitly diverse visual question generation

引用

NEURAL NETWORKS 2025年 184卷 107002页

作者： Xie, Jiayuan Zheng, Jiasheng Fang, Wenhao Cai, Yi Li, Qing Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China South China Univ Technol Sch Software Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China Chinese Acad Sci Inst Software Beijing Peoples R China

Visual question generation involves the generation of meaningful questions about an image. Although we have made significant progress in automatically generating a single high-quality question related to an image, existing methods often ignore the diversity and interpretability of generated questions, which are important for various daily tasks that require clear question sources. In this paper, we propose an explicitly diverse visual question generation model that aims to generate diverse questions based on interpretable question sources. To explicitly perform question generation, our model first extracts the scene graph from the image using the unbiased scene graph generation method, where questions generated based on the scene graphs have interpretable question sources. To ensure the diversity of generated questions, our model selects different subgraphs from the scene graph as question sources. Specifically, we employ a subgraph selector to learn how humans select multiple subgraphs that are suitable for question generation. Finally, our model generates diverse questions based on different selected subgraphs. Extensive experiments on the VQA v2.0 and COCO-QA datasets show that the proposed model outperforms the baselines and is able to interpretably generate diverse questions.

关键词： Multimodal Diverse visual question generation Interpretable text generation Unbiased scene graph generation

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised PolSAR image classification method based on contrastive learning 6

Semi-supervised PolSAR image classification method based on ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Hua, Wenqiang Sun, Nan Liu, Lin The Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an China School of Computer Technology Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9798400707674

Polarimetric synthetic aperture radar (PolSAR) image classification has important application value and a wide range of application scenarios in many fields. Supervised classification methods, which need to use a large amount of labeled data to improve classification accuracy, have achieved satisfactory classification performance. However, it is difficult and expensive to obtain sufficient labeled data for PolSAR images. The problem to be solved is how to obtain high classification accuracy with a limited number of labeled samples. Semi-supervised PolSAR image classification method based on contrastive learning is proposed. Firstly, a supervised PolSAR image classification method based on meta-learning is introduced. Prototypical network based on meta-learning ideas is used as the basic classification model, and a prototypical representation is created for each category. Classification is performed by computing the similarity between the prototypical representation and samples to be classified. Secondly, a method of training feature extractor based on contrastive learning is designed. By maintaining the consistency of features between the same data and distinguishing the differences between different data after data augmentation, the method enables the feature extractor to obtain accurate feature representation. By co-training with meta-learning, so as to improve the classification performance. Finally, experiments on real PolSAR data prove the effectiveness of the proposed method. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

OSFS-Vague: Online streaming feature selection algorithm based on vague set

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1451-1466页

作者： Jie Yang Zhijun Wang Guoyin Wang Yanmin Liu Yi He Di Wu School of Physics and Electronic Science Zunyi Normal UniversityZunyiChina Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Computer Science Old Dominion UniversityNorfolkVirginiaUSA College of Computer and Information Science Southwest UniversityChongqingChina

Online streaming feature selection(OSFS),as an online learning manner to handle streaming features,is critical in addressing high-dimensional *** real big data-related applications,the patterns and distributions of streaming features constantly change over time due to dynamic data generation ***,existing OSFS methods rely on presented and fixed hyperparameters,which undoubtedly lead to poor selection performance when encountering dynamic *** make up for the existing shortcomings,the authors propose a novel OSFS algorithm based on vague set,named *** main idea is to combine uncertainty and three-way decision theories to improve feature selection from the traditional dichotomous method to the trichotomous ***-Vague also improves the calculation method of correlation between features and ***,OSFS-Vague uses the distance correlation coefficient to classify streaming features into relevant features,weakly redundant features,and redundant ***,the relevant features and weakly redundant features are filtered for an optimal feature *** evaluate the proposed OSFS-Vague,extensive empirical experiments have been conducted on 11 *** results demonstrate that OSFS-Vague outperforms six state-of-the-art OSFS algorithms in terms of selection accuracy and computational efficiency.

关键词： feature selection online feature selection three-way decision vague set

来源：评论

学校读者我要写书评

暂无评论

YOLOvis: a yolo style object detection network for drone vision 3

YOLOvis: a yolo style object detection network for drone vis...

引用

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Peng, Yanfei Li, Jincheng Guo, Xinyue School of Electronic and Information Engineering Liaoning University of Technology and Engineering Huludao125105 China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Huludao125105 China

ISBN: (纸本)9781510681880

In recent years, with the rapid development of drone photography technology, drones have emerged as a new method for photography and observation. We have applied object detection technology to drone photography and proposed a YOLO-style 2D object detection network called YOLOvis based on the YOLOv8 architecture. We introduced the PatchFPN structure to improve the network's robustness in detecting small objects and proposed the TranConcat structure to scale features for enhanced usability. YOLOvis utilizes the challenging VisDrone data set as the model's task data set. With a slight increase in computational cost, the model achieves an accuracy of mAP50 33.7%, which is a 3.7% improvement compared to YOLOv8 of the same size and a 17.0% improvement compared to YOLOv5 of the same size. Additionally, to better tailor the model to specific needs, we have proposed YOLOvis models of different sizes. The code and pretrained models are in https://***/BarryGUN/bgyolo_v8_***. © 2024 SPIE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

RGMEF: a lightweight multi-exposure image fusion network based on retinex and gradient guidance

引用

MACHINE VISION AND APPLICATIONS 2025年第3期36卷 1-18页

作者： Feng, Yunfei Zhang, Mei Zhu, Jinhui South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510641 Peoples R China South China Univ Technol Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou 510641 Peoples R China

The goal of the multi-exposure image fusion (MEF) is to create a high dynamic range (HDR) image with balanced exposures and more details by extracting and enhancing valid information from multiple low dynamic range images with varied exposures. In recent years, deep learning has provided many solutions for MEF, and they have achieved remarkable effects. However, because of the high network complexity, these approaches often have low efficiency and limit the potential improvement of the effect. In order to fuse valuable information from different images, we introduce a lightweight but robust MEF network, which focus on the image internal characteristics rather than long-distance information. In this study, we first design a decomposed network inspired by retinex theory to extract the illumination map from an image and obtain the gradient map through Sobel operator. Subsequently, we introduce two lightweight feature extraction modules to extract image features with the guidance of illumination and gradient maps respectively, and then fuse these features to produce an HDR result through three fusion blocks. Furthermore, we design a loss function to obtain a more suitable brightness range for the current scene. Numerous comparative experiments demonstrate the superiority of our method in terms of image texture, pixel intensity, and color retention. Moreover, some ablation studies indicate that our approach has a significant adaptability to source images.

关键词： Multi-exposure fusion Image guidance High dynamic range Retinex theory

来源：评论

学校读者我要写书评

暂无评论

Multimodal Image-Text Representation Learning for Sketch-Less Facial Image Retrieval

Multimodal Image-Text Representation Learning for Sketch-Les...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Dawei Dai Yingge Liu Shiyu Fu Guoyin Wang Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Sketch-less facial image retrieval (SLFIR) framework aims to break the barriers that drawing a high-quality facial sketch requires excellent skills and substantial time, it performs the retrieval using a partial sketch with as few strokes as possible. However, such early-stage sketches often contain only local details, resulting in poor retrieval performance. In this study, we propose learning of the representation by fusing the sketches with prior human semantic knowledge to improve the early retrieval performance. Specifically, (1) based on the LAION-Face dataset, a facial language-image pretraining (FLIP) model is constructed to learn the aligned representations of facial image and text; (2) subsequently, using FLIP as the backbone, multiscale features of sketch and text are extracted and fused to learn the efficient representation for the final retrieval. The proposed method achieves state-of-the-art early retrieval performance on all two public datasets and exhibits a good generalization ability in practical testing.

关键词： Representation learning Semantics Image retrieval Feature extraction Faces Testing

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：