检索结果-内蒙古大学图书馆

6th ieee International conference on multimedia information processing and retrieval, MIPR 2023

ISBN: (纸本)9798350307818

The proceedings contain 27 papers. The topics discussed include: dual-stream multi-modal graph neural network for few-shot learning;improving detection of diabetic retinopathy in low-resolution images via latent diffusion;learning fashion compatibility with color distortion prediction;visual passage score aggregation for image retrieval;the metaverse: AI-powered universe of persistent digital twins;enhancing general face forgery detection via vision transformer with low-rank adaptation;visual sentiment analysis by distillation of instance-based sentiment vectors;transformer based image-text consistency analysis for infographic articles;attacking identity semantics in DeepFakes via deep feature fusion;Bayesian belief network analysis on self-driving cars;a multi-stage bias reduction framework for eye gaze detection;and region-aware photo assurance system for image authentication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proceedings - ieee 1st conference on multimedia information processing and retrieval, MIPR 2018

Proceedings - IEEE 1st Conference on Multimedia Information ...

引用

1st ieee conference on multimedia information processing and retrieval, MIPR 2018

ISBN: (纸本)9781538618578

The proceedings contain 85 papers. The topics discussed include: vehicle detection in UAV traffic video based on convolution neural network;comparing visual, textual, and multimodal features for detecting sign language in video sharing sites;integrating visual and textual affective descriptors for sentiment analysis of social media posts;ontology-driven hierarchical deep learning for fashion recognition;deep learning of path-based tree classifiers for large-scale plant species identification;deep structured prediction: a new formulation for person re-identification;do they all look the same? deciphering Chinese, Japanese and Koreans by fine-grained deep learning;a novel objective quality assessment method for perceptually-coded cloud gaming video;and buffer management for synchronous and low-latency playback of multi-stream user-generated content.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 2024 ieee 7th International conference on multimedia information processing and retrieval, MIPR 2024

Proceedings - 2024 IEEE 7th International Conference on Mult...

引用

7th ieee International conference on multimedia information processing and retrieval, MIPR 2024

ISBN: (纸本)9798350351422

The proceedings contain 106 papers. The topics discussed include: macro-AUC-driven active learning strategy for multi-label classification enhancement;mitigating privacy threats without degrading visual quality of VR applications: using re-identification attack as a case study;attenuation-aware weighted optical flow with medium transmission map for learning-based visual odometry in underwater terrain;GeoVQA: a comprehensive multimodal geometry dataset for secondary education;pulse of the crowd: quantifying crowd energy through audio and video analysis;automated recognition of optic disc and blood vessels in diabetic fundoscopy images using real-time image analysis;GeoSecure-B: a method for secure bearing calculation;and exploiting correlation between facial action units for detecting deepfake videos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2023 ieee 6th International conference on multimedia information processing and retrieval MIPR 2023

2023 IEEE 6th International Conference on Multimedia Informa...

引用

ieee conference on multimedia information processing and retrieval (MIPR)

2023 ieee 6th International conference on multimedia information processing and retrieval MIPR 2023.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring efficient optimization techniques in online retrieval-augmented generation application 24

Exploring efficient optimization techniques in online retrie...

引用

24th ACM/ieee Joint conference on Digital Libraries, JCDL 2024

作者： Zhang, Yining Peng, Yinan Tu, Chengying Zhang, Zherui Yan, Hongfei Chen, Chong Ma, Hao Yang, Jia Zhang, Yan Liao, Rikun School of Computer Science Peking University Beijing China State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University Beijing China Bejing Normal University Beijing China Peking University Beijing China

ISBN: (纸本)9798400710933

Recent advances in large language models (LLM) have brought an explosive growth to chat-bot applications. Among them, retrievalaugmented generation, which provides extra context to make LLM capable of answering out-of-domain questions is becoming a popular method. However, naive implementation of RAG usually cannot reach ideal answer quality in complicated real-world scenarios. Researchers have proposed a number of methods to improve RAG, but many of them involves extra LLM calls which is too time-consuming for online application. In this paper, we explored practical techniques and designs in RAG that improve answers to user-satisfying quality while keeping the response latency at a moderate level in the scenario of a research data QA application in university. Our main findings include introducing a relevance judge with smallscale LLM for retrieved documents can effectively filter out less relevant ones, which can otherwise disrupt the generated answer greatly, and decomposing the generation task into multiple independent sub-Tasks can reduce the chance of hallucination and also accelerates the generation. As for model performance, prompt engineering and fine-Tuning (through learning from strong LLM) are effective yet simple ways to enhance answer quality. Our results and experience provide insights for building future real-world LLM applications. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： retrieval-augmented generation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Hierarchical Dynamic Similarity Hashing for multimedia retrieval

Unsupervised Hierarchical Dynamic Similarity Hashing for Mul...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yunfei Chen Zhan Yang Jun Long Big Data Institute Central South University ChangSha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Unsupervised cross-modal hashing methods have become a core technology for retrieving vast amounts of heterogeneous multimedia information due to their advantages in retrieval speed and storage efficiency. Although these methods have made significant progress in the field of multimedia retrieval, they still face challenges related to inaccurate similarity measurements and incomplete embedding of relational information. To address these issues, we propose Unsupervised Hierarchical Dynamic Similarity Hashing(UHDSH) for multimedia retrieval. First, the Semantic Similarity Measurement Layer extracts common semantic information within multimedia data to construct a dynamic fluctuation similarity hypergraph, which guides the training of the hash function. Second, the Relational Constraint Hashing Layer, based on the dynamic fluctuation similarity hypergraph embedding technique and multimodal feature reconstruction, ensures the precise embedding of both semantic and relational information. Finally, we conducted comprehensive experiments on two widely used datasets, MIR Flickr and NUS-WIDE. Our proposed UHDSH method achieves a maximum improvement of 5.06% over the best baseline methods. The code is publicly available at https://***/YunfeiChenMY/UHDSH.

关键词： Training Hash functions Fluctuations Image databases Semantics Signal processing Feature extraction Web sites multimedia communication Speech processing

来源：评论

学校读者我要写书评

暂无评论

A multimedia Interactive Presentation System Based on AIoT and RAG-Enabled Large Language Models

A Multimedia Interactive Presentation System Based on AIoT a...

引用

ieee International conference on Consumer Electronics (ICCE)

作者： Ming-Shun Wang Ming-Che Chen Department of Electronic Engineering Southern Taiwan University of Science and Technology Tainan Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

This paper proposes a multimedia interactive presentation system, Gen-Presenter, that leverages Artificial Intelligence of Things (AIoT) and retrieval Augmented Generation (RAG)-enabled Large Language Models (LLM). The Gen-Presenter system integrates an edge-AI computing device with peripherals such as a camera, microphone, speakers, and display screen, in combination with a natural language processing (NLP) server. The system detects visitor activity through the camera, infers their age group, and uses this information to select appropriate slides and generate corresponding voice narration for interactive presentations. Experimental results show that Gen-Presenter, when responding to queries from users of different age groups, can select appropriate presentation slides and generating corresponding explanations, with performance closely matching human decisions. In terms of slide selection, the overall precision, recall, and accuracy were 0.87, 0.67, and 0.76, respectively. Additionally, the suitability rates for the generated age-appropriate text content across the three age groups exceeded 0.7. This demonstrates the system's success in delivering human-like slide explanations and interactive Q&A sessions.

关键词： Accuracy Large language models multimedia systems retrieval augmented generation Cameras Natural language processing Internet of Things Time factors Servers Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Cross-Modal retrieval Scheme Based on CLIP and Deep Hashing

A Privacy-Preserving Cross-Modal Retrieval Scheme Based on C...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yuan Cao Hui Zhang Xinzheng Shang Ocean University of China Qingdao China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the massive growth of multimedia data, local devices gradually cannot meet the data processing needs, thus utilizing cloud server resources becomes better choice. To prevent privacy leakage, user data can only be stored in ciphertext. Existing cross-media retrieval schemes are only for plaintext data and cannot protect privacy. Privacy-preserving cross-modal retrieval of cloud data becomes a research priority. In this paper, we propose a CLIP-based privacy-preserving cross-modal retrieval scheme. First, CLIP encoder is utilized to transform images and texts into public space features to enhance retrieval accuracy. Subsequently, the original feature relevance is reduced by feature transformation network and mutual information loss to enhance privacy preservation. Finally, a transformer encoder-based hash learning method is used to embed the transformed features into compact hash codes, which is combined with comparison learning to enhance the discriminative properties. Experimental results on cross-modal datasets verify the efficiency and accuracy of the proposed scheme.

关键词： Learning systems Privacy Data privacy Codes Accuracy Transforms Feature extraction Transformers Mutual information Cross modal retrieval

来源：评论

学校读者我要写书评

暂无评论

Enhancing Slovak Natural Language processing: Fine-Tuning Sentence BERT Models with Translated MS MARCO V2 Data Using MADLAD-400

Enhancing Slovak Natural Language Processing: Fine-Tuning Se...

引用

International conference on Computational Cybernetics (ICCC)

作者： Kristián Sopkovič Eva Kupcová Daniel Hládek Matúš Pleva Maroš Harahus Department of Electronics and Multimedia Telecommunications Faculty of Electrical Engineering and Informatics Technical University of Kosice Kosice Slovakia

ISBN: (数字)9798331502461

ISBN: (纸本)9798331502478

This study explores the enhancement of Slovak Natural Language processing (NLP) by fine-tuning Sentence BERT models using the translated MS MARCO V2 dataset, facilitated by the MADLAD-400 language model. We translated the MS MARCO V2 dataset into Slovak and utilized this translation to train Sentence BERT models, aiming to improve the quality of vector representations for Slovak sentences. Employing a triplet network approach, we derived meaningful sentence vector representations, enabling effective comparison through cosine similarity. The research yields a newly translated database and evaluates the performance of fine-tuned Slovak vector representation models, thereby advancing Slovak search capabilities.

关键词： Translation Databases Computational modeling Computational cybernetics Transformers information retrieval Vectors Data models Machine translation

来源：评论

学校读者我要写书评

暂无评论

Pushing the Boundary of multimedia Big Data: An Overview of ieee MIPR

引用

ieee multimedia 2019年第2期26卷 87-91页

作者： Su, Guan-Ming Zhang, Chengcui Wang, Haohong Chen, Min Kankanhalli, Mohan Lienhart, Rainer Dolby Labs Imaging Appl Res San Francisco CA 94103 USA Univ Alabama Dept Comp Sci Tuscaloosa AL 35487 USA TCL Res Amer San Jose CA USA Univ Washington Bothell Sch STEM Comp & Software Syst Bothell WA USA Natl Univ Sch Comp Singapore Singapore Univ Augsburg Comp Vis Lab Multimedia Comp Augsburg Germany

New forms of multimedia data (such as text, numbers, tags, networking, signals, geo-tagged information, graphs/relationships, three-dimensional/VR/AR and sensor data, etc.) have emerged in many applications in addition to traditional multimedia data (image, video, audio). multimedia has become the biggest of big data as the foundation of today's data-driven discoveries. Almost all disciplines of science and engineering, as well as social sciences, involve multimedia data in some forms, such as recording experiments, driverless cars, unmanned aerial vehicles, smart communities, biomedical instruments, security surveillance. Some recent events demonstrate the power of real-time broadcast of unfolding events on social networks. multimedia data is not just big in volume, but also multi-modal and mostly unstructured. Storing, indexing, searching, integrating, and recognizing from the vast amounts of data create unprecedented challenges. Even though significant progress has been made processing multimedia data, today's solutions are inadequate in handling data from millions of sources simultaneously. The ieee International conference on multimedia information processing and retrieval (ieee-MIPR) aims to provide a forum for original research contributions and practical system design, implementation, and applications of multimedia information processing and retrieval for single modality or multiple modalities. The target audiences are university researchers, scientists, industry practitioners, software engineers, and graduate students who want to become acquainted with technologies for big data analytics, machine intelligence, information fusion in multimedia information processing and retrieval. Following a successful debut in Miami, Florida in 2018, the second MIPR, held in San Jose, California, attracted over 140 submissions and more than 100 attendees-a big growth from its inaugural event and an indication of its growing visibility and popularity in the multimedia resea

关键词： Big Data Data Analysis information retrieval multimedia Computing ieee MIPR Big Data Analytics multimedia Big Data multimedia Data processing multimedia information processing And retrieval Data Handling ieee International conference Machine Intelligence information Fusion Streaming Media multimedia Computing Computer Vision Technological Innovation Big Data information retrieval Data Analysis

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：