arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

多模态信息融合

面向图像、视频、多传感器和跨模态感知的信息融合,包括 Image Fusion、红外可见光、遥感、医学影像、LiDAR/雷达/相机和音视频融合。

共收录 1405 信号源:cs.CV, eess.IV, eess.SP, cs.RO, cs.MM

1. 融合架构与评测 1405 篇

2001.06804 2020-01-22 cs.CV 79%

Learning Compositional Neural Information Fusion for Human Parsing

Wenguan Wang, Zhijie Zhang, Siyuan Qi, Jianbing Shen, Yanwei Pang, Ling Shao

专题命中 融合架构与评测 :information fusion(title,abstract);分类 cs.CV

Comments ICCV2019. Websie: https://github.com/ZzzjzzZ/CompositionalHumanParsing

Journal ref ICCV2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1909.01763 2019-09-05 cs.CV cs.LG 79%

Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context

Jie Zhang, Yin Zhao, Longjun Cai, Chaoping Tu, Wu Wei

专题命中 融合架构与评测 :multi-modal fusion(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.06496 2019-03-18 cs.LG cs.CV cs.NE 79%

MFAS: Multimodal Fusion Architecture Search

Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux, Moez Baccouche, Frédéric Jurie

专题命中 融合架构与评测 :multimodal fusion(title,abstract);分类 cs.CV

Comments CVPR 2019, Jun 2019, Long Beach, United States http://cvpr2019.thecvf.com/

详情

展开后加载摘要…

URL PDF HTML 收藏
1807.06233 2018-11-05 cs.CV 79%

Robust Deep Multi-modal Learning Based on Gated Information Fusion Network

Jaekyum Kim, Junho Koh, Yecheol Kim, Jaehyung Choi, Youngbae Hwang, Jun Won Choi

专题命中 融合架构与评测 :information fusion(title,abstract);分类 cs.CV

Comments 2018 Asian Conference on Computer Vision (ACCV)

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.07075 2018-10-17 cs.CV 79%

A Multi-stage Framework with Context Information Fusion Structure for Skin Lesion Segmentation

Yujiao Tang, Feng Yang, Shaofeng Yuan, Chang'an Zhan

专题命中 融合架构与评测 :information fusion(title,abstract);分类 cs.CV

Comments 4 pages, 3 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.23230 2025-10-28 cs.IT math.IT 79%

On the use of information fusion techniques to improve information quality: Taxonomy, opportunities and challenges

Raúl Gutiérrez, Víctor Rampérez, Horacio Paggi, Juan A. Lara, Javier Soriano

专题命中 融合架构与评测 :information fusion(title,abstract)

Journal ref Information Fusion, 78, 102-137; 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.00153 2023-06-02 cs.LG cs.AI cs.SC 79%

Information Fusion via Symbolic Regression: A Tutorial in the Context of Human Health

Jennifer J. Schnur, Nitesh V. Chawla

专题命中 融合架构与评测 :information fusion(title,abstract)

Journal ref Information Fusion (2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
cs/0408064 2016-08-31 cs.AI 79%

Proportional Conflict Redistribution Rules for Information Fusion

Florentin Smarandache, Jean Dezert

专题命中 融合架构与评测 :information fusion(title,abstract)

Comments 41 pages

Journal ref Proceedings of the 8th International Conference on Information Fusion, Philadelphia, 25-29 July, 2005; IEEE Catalog Number: 05EX1120C, ISBN: 0-7803-9287-6.

详情

展开后加载摘要…

URL PDF HTML 收藏
1401.6891 2014-01-28 cs.IR 79%

Unsupervised Visual and Textual Information Fusion in Multimedia Retrieval - A Graph-based Point of View

Gabriela Csurka, Julien Ah-Pine, Stéphane Clinchant

专题命中 融合架构与评测 :information fusion(title,abstract)

Comments An extended version of the paper: Visual and Textual Information Fusion in Multimedia Retrieval using Semantic Filtering and Graph based Methods, by J. Ah-Pine, G. Csurka and S. Clinchant, submitted to ACM Transactions on Information Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
adap-org/9906002 2009-11-30 adap-org nlin.AO 79%

Minimum Energy Information Fusion in Sensor Networks

George Chapline

专题命中 融合架构与评测 :information fusion(title,abstract)

Comments postscript, 8 pages. Paper 65 in Proceedings of The 2nd International Conference on Information Fusion

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.20742 2026-07-24 cs.LG 新提交 78%

Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion

用于可信多组学多模态融合的自适应置信加权扩展

Mohammad Raahemi, Ali Sekhavati, Alireza Maleki, Hamid Nasiri

机构 * Faculty of Engineering, University of Ottawa(渥太华大学工程学院) RIV Lab, Department of Computer Engineering, Bu-Ali Sina University(布阿里·西纳大学计算机工程系RIV实验室) School of Computing and Communications, Lancaster University(兰卡斯特大学计算与通信学院)

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 针对多模态学习模型在噪声或无信息数据流下性能不佳及缺乏数据质量评估机制的问题,提出自适应置信加权扩展(ACE)框架,通过生成互补模态和双层置信机制提升性能,在多组学数据集评估中显著优于现有算法。

Comments Accepted for publication in the proceedings of the International Conference on Pattern Recognition (ICPR 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.00300 2026-07-13 cs.CL 版本更新 78%

Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion

基于图卷积网络与信息融合的科技专利实体对齐方法

Runze Fang, Yawen Li, Yingxia Shao, Zeli Guan, Zhe Xue

机构 * Beijing Key Laboratory of Intelligent Communication Software and Multimedia(智能通信软件与多媒体北京重点实验室) School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications(计算机学院(国家试点软件工程学院),北京邮电大学) School of Economics and Management, Beijing University of Posts and Telecommunications(经济管理学院,北京邮电大学)

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 研究科技专利实体对齐问题,提出基于图卷积网络与信息融合的方法,利用专利实体图形结构及辅助信息,通过图卷积网络和BERT模型实现多信息融合,提升实体对齐性能,实验表明该方法优于现有方法。

Comments 8 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
1702.08641 2026-06-04 eess.SY cs.SY 78%

Statistical Information Fusion for Multiple-View Sensor Data in Multi-Object Tracking

多视图传感器数据在多目标跟踪中的统计信息融合

Xiaoying Wang, Reza Hoseinnezhad, Amirali K. Gostar, Tharindu Rathnayake, Benlian Xu, Alireza Bab-Hadiashar

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本文提出了一种新的统计信息融合方法,用于整合多视图传感器数据以提高多目标跟踪性能。方法通过自适应权重改进通用协方差交方法,利用Cauchy-Schwarz散度量化信息内容,并采用Labeled Multi-Bernoulli滤波器实现更精确的跟踪。

Comments 28 pages,7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.31193 2026-06-01 cs.LG 78%

Geometry-based Schrödinger Bridges for Trustworthy Multimodal Fusion

基于几何的薛定谔桥用于可信多模态融合

Jiayu Xiong, Jing Wang, Qi Zhang, Wanlong Wang, Jun Xue

机构 * Department of Computer Science(计算机科学系) Techonology, Huaqiao University(技术学系,华侨大学) Xiamen Key Laboratory of Computer Vision(厦门计算机视觉实验室) Pattern Recognition, Huaqiao University(模式识别,华侨大学) Tongji University(同济大学) School of Cyber Science(网络科学学院) Engineering, Wuhan University(工程学院,武汉大学)

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 提出基于几何的多模态融合方法GMF,利用扩散薛定谔桥的初始速度平方作为独立于预测的可靠性信号,以提升对低质量数据的鲁棒性。

Comments ICML 2026 accepted paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17336 2026-05-19 cs.RO cs.CV eess.SP 78%

Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms

基于触觉的多模态融合在具身智能中的应用:视觉、语言和接触驱动范式的综述

Zhixiang Cao, Di Tian, Runwei Guan, Yanzhou Mu, Xiaolou Sun, Shaofeng Liang, Daizong Liu, Tao Huang, Yutao Yue, Henghui Ding, Bin Fang, Alex Zhou, Qing-Long Han, Hui Xiong

机构 * School of Electronic Science and Engineering, Xi’an Jiaotong University, China(西安交通大学电子科学与技术学院) Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), China(香港科技大学(广州)人工智能研究所) State Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室) Purple Mountain Laboratory, China(紫金山实验室) Institute for Math & AI, Wuhan University, China(武汉大学数学与人工智能学院) Centre for AI and Data Science Innovation and the School of Science and Engineering, James Cook University, Australia(詹姆斯库克大学人工智能与数据科学创新中心及科学与工程学院) School of Artificial Intelligence, Beijing University of Posts and Telecommunications, China(北京邮电大学人工智能学院) Institute of Big Data, Fudan University, China(复旦大学大数据研究院) Linkerbot (Beijing) Technology Co., Ltd, China(北京链动科技有限公司) School of Engineering, Swinburne University of Technology, Melbourne(斯威本技术大学工程学院)

专题命中 融合架构与评测 :multimodal fusion(title);分类 cs.CV、eess.SP、cs.RO

AI总结 本文综述了多模态触觉融合在具身智能中的研究,探讨了如何通过整合视觉、语言和触觉信息来提升物理交互与语义推理的结合,提出了一种分层的分类体系,并总结了当前的研究挑战和未来方向。

Comments 20 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17038 2026-05-19 cs.AI 78%

Evidential Information Fusion on Possibilistic Structure

可能性结构上的证据信息融合

Qianli Zhou, Ye Cui, Zhen Li, Witold Pedrycz, Yong Deng

机构 * School of Electronics and Information, Northwestern Polytechnical University(电子信息学院,西北工业大学) Department of Electrical and Computer Engineering, University of Alberta(阿尔伯塔大学电气与计算机工程系) China Mobile Information Technology Center(中国移动信息科技中心) Systems Research Institute, Polish Academy of Sciences(波兰科学院系统研究所) Institute of Fundamental and Frontier Science, University of Electronic Science and Technology of China(中国电子科技大学基础与前沿科学研究院)

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本文提出了一种基于可能性结构的证据信息融合方法,通过引入信任演化网络和三角范数家族,实现了更灵活的信息融合框架,适用于非distinct源融合、冲突管理等复杂场景。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15235 2026-05-18 cs.LG 78%

MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion

MuteBench: 多模态融合不完整性容忍性评估

Wugeng Zheng, Ziwen Kan, Tianlong Chen, Chen Chen, Song Wang

机构 * University of Central Florida(中央佛罗里达大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 MuteBench评估多模态融合在模态缺失和内模态缺失下的鲁棒性,发现架构类型是预测鲁棒性的最强因素,且通道独立模型对模态缺失容忍性高但对内模态缺失敏感。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12852 2026-05-14 cs.LG q-bio.QM 78%

Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response

多任务多模态融合:基于表格基础模型的百日咳加强针反应峰值和持续性预测

Divya Sitani

机构 * Berlin, Germany(柏林,德国)

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 本文提出多任务对比多模态融合架构,用于预测百日咳加强针反应的峰值和持续性,通过结合冻结的TabPFN-v2模态编码器、双标签监督对比损失、模态dropout和缺失性掩码注意力融合,实现了对两个任务的联合预测。

Comments 22 pages, 8 figures, 4 tables. Code available at https://github.com/Divya1205/cmi-pb-multitask

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11066 2026-04-17 cs.IR 78%

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction

解耦多模态融合用于点击通过率预测中的用户兴趣建模

Alin Fan, Hanqing Li, Sihan Lu, Jingsong Yuan, Jiandong Zhang

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 本文提出解耦多模态融合方法,通过构建目标感知特征和优化注意力机制,提升用户兴趣建模效果,实验表明在公开和工业数据集上均取得显著提升。

Comments Accepted by ICDE2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13714 2026-04-16 cs.CE 78%

An End-to-end Building Load Forecasting Framework with Patch-based Information Fusion Network and Error-weighted Adaptive Loss

一种基于碎片信息融合网络和误差加权自适应损失的端到端建筑负载预测框架

Hang Fan, Ying Lu, Weican Liu, Dunnan Liu, Xiaotao Chen, Shengwei Mei

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本文提出端到端建筑负载预测框架,通过碎片信息融合网络和误差加权自适应损失提升预测精度,解决复杂时间依赖性和高波动性问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12145 2026-04-15 eess.AS cs.SD 78%

Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization

为何您的分词器在信息融合中失败:一种面向时间的预量化融合用于视频增强的音频分词

Xiangyu Zhang, Benjamin John Southwell, Siqi Pan, Xinlei Niu, Beena Ahmed, Julien Epps

机构 * School of Electrical Engineering and Telecommunications, University of New South Wales(新南威尔士大学电气工程与电信学院) Dolby Laboratories(杜比实验室)

专题命中 融合架构与评测 :information fusion(title);multimodal fusion(abstract)

AI总结 本文研究了视频增强音频分词中重建质量下降的根本原因,提出了一种面向时间的预量化融合方法,通过在分词器架构中合理定位融合位置,结合时间轴上的特征融合,实现了高保真重建和下游任务的优越性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22369 2026-03-25 q-bio.GN cs.AI cs.LG 78%

SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts

SynLeaF:一种用于跨泛癌和单癌情境的合成致死性预测双阶段多模态融合框架

Zheming Xing, Siyuan Zhou, Ruinan Wang, Rui Han, Shiming Zhang, Shiqu Chen, Yurui Huang, Jiahao Ma, Yifan Chen, Xuan Wang, Yadong Wang, Junyi Li

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 SynLeaF通过双阶段多模态融合框架,有效整合基因表达、突变、甲基化和拷贝数变异等多组学数据,并利用关系图卷积网络捕捉生物医学知识图谱中的结构化基因表示,从而在17/19种场景中实现优于现有方法的性能。

Comments 29 pages, 5 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.15004 2026-03-17 cs.SE 78%

TriFusion-LLM: Prior-Guided Multimodal Fusion with LLM Arbitration for Fine-grained Code Clone Detection

TriFusion-LLM:基于LLM仲裁的先验引导多模态融合用于细粒度代码克隆检测

Mengdi Li, Yuming Liu, He Wang, Zifeng Xu, Yuqing Zhang

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 本文提出TriFusion-LLM框架,结合传统机器学习的启发式相似性先验、AST结构信号和CodeBERT语义嵌入,提升细粒度代码克隆检测的分类性能,实验表明其在BigCloneBench上将Macro-F1提升至0.875。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14956 2026-03-17 cs.LG 78%

SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

SFedHIFI:基于发火率的异构信息融合用于脉冲联邦学习

Ran Tao, Qiugang Zhan, Shantian Yang, Xiurui Xie, Qi Tian, Guisong Liu

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本文提出SFedHIFI框架,通过基于发火率的异构信息融合实现异构联邦学习,提升资源受限客户端的模型部署效率和性能。

Comments 9 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12192 2026-03-17 physics.optics 78%

Multimodal Fusion Network for Micro-displacement Measurement via Michelson Interferometer

用于迈克尔逊干涉仪的多模融合网络微位移测量

Zixing Jia, Jiawei Li, Ziping Chen, Xin Li

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 本文提出一种多模融合网络用于高精度微位移测量,通过引入双头学习机制解决半波位移模糊问题,实现高精度位移和整数干涉阶分类,具备实时性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16585 2026-02-16 cs.LG stat.CO stat.ML 78%

Leveraging Noisy Manual Labels as Useful Information: An Information Fusion Approach for Enhanced Variable Selection in Penalized Logistic Regression

利用噪声人工标签作为有用信息:一种信息融合方法用于增强正则化逻辑回归中的变量选择

Xiaofei Wu, Rongmei Liangse

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本文提出一种信息融合方法,通过利用噪声人工标签提升正则化逻辑回归中的变量选择性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10092 2026-01-16 cs.LG cs.AI 78%

LeMoF: Level-guided Multimodal Fusion for Heterogeneous Clinical Data

LeMoF:面向异构临床数据的层级引导多模态融合

Jongseok Kim, Seongae Kang, Jonghwan Shin, Yuhan Lee, Ohyun Jo

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

AI总结 LeMoF通过层级引导的多模态融合方法,在异构临床数据中提升预测稳定性与判别能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.24246 2026-01-01 cs.IR 78%

Time-Aware Adaptive Side Information Fusion for Sequential Recommendation

时间感知自适应侧信息融合用于序列推荐

Jie Luo, Wenyu Zhang, Xinming Zhang, Yuan Fang

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 TASIF通过时间感知自适应融合框架提升序列推荐性能,解决时间动态、噪声敏感和计算效率问题。

Comments 10 pages. Accepted by WSDM'26

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.23026 2025-12-01 cs.CR cs.GT cs.MA 78%

A Game-Theoretic Approach for Adversarial Information Fusion in Distributed Sensor Networks

对抗信息融合在分布式传感器网络中的博弈论方法

Kassem Kallas

专题命中 融合架构与评测 :information fusion(title,abstract)

AI总结 本研究提出博弈论方法,用于解决分布式传感器网络中对抗信息融合问题,通过软隔离防御、最优决策融合策略、近似最优消息传递算法和数据篡改防御机制,提升系统安全性。

Comments My PhD Thesis in Information Engineering and Sciences defended at University of Siena in Italy in 2017 under the supervision of Professor Mauro Barni

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10644 2025-11-18 cs.LG 78%

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

Yihua Wang, Qi Jia, Cong Xu, Feiyu Chen, Yuhan Liu, Haotian Zhang, Liang Jin, Lu Liu, Zhichun Wang

机构 * IEIT SYSTEMS Co., Ltd.(IEIT SYSTEMS公司)

专题命中 融合架构与评测 :multimodal fusion(title,abstract)

Comments Accepted at AAAI 2026 Conference

详情

展开后加载摘要…

URL PDF HTML 收藏