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 1409 信号源:cs.CV, eess.IV, eess.SP, cs.RO, cs.MM

1. 融合架构与评测 1409 篇

1606.06259 2016-11-18 cs.CL cs.MM 57%

MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

Amir Zadeh, Rowan Zellers, Eli Pincus, Louis-Philippe Morency

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

Comments Accepted as Journal Publication in IEEE Intelligent Systems

Journal ref IEEE Intelligent Systems 31.6 (2016): 82-88

详情

展开后加载摘要…

URL PDF HTML 收藏
1502.01094 2016-01-20 stat.ML cs.CV cs.LG 57%

Multimodal Task-Driven Dictionary Learning for Image Classification

Soheil Bahrampour, Nasser M. Nasrabadi, Asok Ray, W. Kenneth Jenkins

专题命中 融合架构与评测 :feature-level fusion(abstract);分类 cs.CV

Comments To appear at IEEE Transactions on Image Processing

详情

展开后加载摘要…

URL PDF HTML 收藏
1402.5792 2014-10-01 cs.CV 57%

A Novel Scheme for Intelligent Recognition of Pornographic Images

Seyed Mostafa Kia, Hossein Rahmani, Reza Mortezaei, Mohsen Ebrahimi Moghaddam, Amer Namazi

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1207.5064 2012-07-24 cs.CV 57%

A Novel Metric Approach Evaluation For The Spatial Enhancement Of Pan-Sharpened Images

Firouz Abdullah Al-Wassai, Dr. N. V. Kalyankar

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

Comments arXiv admin note: substantial text overlap with arXiv:1110.4970

Journal ref International Conference of Advanced Computer Science & Information Technology (ACSIT-2012),July 15, 2012, Chennai, India

详情

展开后加载摘要…

URL PDF HTML 收藏
0806.2006 2012-01-09 cs.CV cs.AI 57%

Fusion de classifieurs pour la classification d'images sonar

Arnaud Martin

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

Journal ref Revue Nationale des Technologies de l'Information E, 5 (2005) 259-268

详情

展开后加载摘要…

URL PDF HTML 收藏
1109.1145 2011-09-07 cs.MM 57%

A Survey on Web Multimedia Mining

Pravin M. Kamde, Dr. Siddu. P. Algur

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

Comments 13 Pages; The International Journal of Multimedia & Its Applications (IJMA) Vol.3, No.3, August 2011

详情

展开后加载摘要…

URL PDF HTML 收藏
1002.2755 2010-02-26 cs.CV cs.AI 57%

Multibiometrics Belief Fusion

Dakshina Ranjan Kisku, Jamuna Kanta Sing, Phalguni Gupta

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

Comments 4 pages, 3 figures

Journal ref ICMV 2009

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17470 2026-05-20 cs.CV cs.MM eess.IV 56%

EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution

EchoSR: 为轻量图像超分辨率实现高效的上下文利用

Hanli Zhao, Binhao Wang, Shihao Zhao, Tao Wang, Kaihao Zhang, Wanglong Lu

机构 * College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China(温州大学计算机科学与人工智能学院) vivo BlueImage Lab, vivo Mobile Communication Co., Ltd, Shanghai 200100, China(vivo蓝影实验室,vivo移动通信有限公司,上海200100,中国) College of Engineering and Computer Science, Australian National University, Canberra, Australia(工程与计算机科学学院,澳大利亚国立大学,堪培拉,澳大利亚) The AI/Analytics Team, Nasdaq, St. John’s, Canada(AI/分析团队,纳斯达克,圣约翰,加拿大)

专题命中 融合架构与评测 :分类 cs.CV、eess.IV、cs.MM;information fusion(comments)

AI总结 本文提出EchoSR框架,通过统一多尺度感受野建模和层次化上下文融合,提升了轻量图像超分辨率的效率和效果,同时在多个基准上优于现有方法,并实现了约两倍的速度提升。

Comments Accepted by Information Fusion; 20 pages, 17 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.03596 2026-03-11 cs.HC 56%

Exploring EEG and Eye Movement Fusion for Multi-Class Target RSVP-BCI

探索EEG和眼动融合用于多类目标RSVP-BCI

Xujin Li, Wei Wei, Kun Zhao, Jiayu Mao, Yizhuo Lu, Shuang Qiu, Huiguang He

专题命中 融合架构与评测 :multi-modal fusion(abstract);information fusion(journal_ref)

AI总结 本文提出MTREE-Net,通过融合EEG和眼动数据提升多类RSVP-BCI的解码性能。

Comments 17 pages, 9 figures

Journal ref Information Fusion, 2025, 121: 103135

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.00770 2021-08-11 eess.SY cs.SY 56%

Decentralized Multi-target Tracking in Urban Environments: Overview and Challenges

Donald J. Bucci, Pramod K. Varshney

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

Comments 22nd International Conference on Information Fusion

详情

展开后加载摘要…

URL PDF HTML 收藏
2002.09485 2020-02-25 cs.SI cs.CY cs.LG 56%

The Four Dimensions of Social Network Analysis: An Overview of Research Methods, Applications, and Software Tools

David Camacho, Àngel Panizo-LLedot, Gema Bello-Orgaz, Antonio Gonzalez-Pardo, Erik Cambria

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

Comments This paper is currently under evaluation in Information Fusion journal

详情

展开后加载摘要…

URL PDF HTML 收藏
1706.05913 2017-06-20 cs.CR cs.DB 56%

Fusing restricted information

Magnus Jändel, Pontus Svenson, Ronnie Johansson

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

Comments 9 pages, author contacts: xpontus@gmail.com, ronniej@kth.se

Journal ref Proc 17th Int Conf on Information Fusion (2014)

详情

展开后加载摘要…

URL PDF HTML 收藏
1312.5515 2013-12-20 cs.AI 56%

Conservative, Proportional and Optimistic Contextual Discounting in the Belief Functions Theory

Marek Kurdej, Véronique Cherfaoui

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

Comments 7 pages

Journal ref 16th International Conference on Information Fusion, Istanbul : Turkey (2013)

详情

展开后加载摘要…

URL PDF HTML 收藏
0807.1906 2009-12-01 cs.AI 56%

Extension of Inagaki General Weighted Operators and A New Fusion Rule Class of Proportional Redistribution of Intersection Masses

Florentin Smarandache

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

Comments 6 pages; SWIFT 2008 - Skovde Workshop on Information Fusion Topics, Sweden;

Journal ref International Journal of Artificial Intelligence, Vol. 3, No. A09, 79-85, 2009

详情

展开后加载摘要…

URL PDF HTML 收藏
cs/0305027 2009-11-30 cs.AI cs.NE 56%

Managing Inconsistent Intelligence

Johan Schubert

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

Comments 7 pages, 3 figures

Journal ref in Proceedings of the Third International Conference on Information Fusion (FUSION 2000), pp. TuB4/10-16, Paris, France, 10-13 July 2000, International Society of Information Fusion, Sunnyvale, 2000

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.09675 2023-10-16 cs.LG cs.CV cs.MM 54%

Multi-View Class Incremental Learning

Depeng Li, Tianqi Wang, Junwei Chen, Kenji Kawaguchi, Cheng Lian, Zhigang Zeng

专题命中 融合架构与评测 :information fusion(comments,journal_ref);分类 cs.CV、cs.MM

Comments Accepted to Information Fusion

Journal ref Information Fusion, 2023, 102, 102021

详情

展开后加载摘要…

URL PDF HTML 收藏
1908.08815 2019-08-26 eess.SP cs.CV stat.ML 54%

Spooky effect in optimal OSPA estimation and how GOSPA solves it

Ángel F. García-Fernández, Lennart Svensson

专题命中 融合架构与评测 :information fusion(comments,journal_ref);分类 cs.CV、eess.SP

Comments This paper received the third best paper award at the 22nd International Conference on Information Fusion, Ottawa, Canada, 2019. Matlab code of the GOSPA metric can be found in https://github.com/abusajana/GOSPA . Additional information on MTT can be found in the online course https://www.youtube.com/channel/UCa2-fpj6AV8T6JK1uTRuFpw

Journal ref Proceedings of the 22nd International Conference on Information Fusion, 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17124 2026-08-19 cs.AI 新提交 50%

A decodability criterion predicts when hidden-state selection beats majority voting in large language models

可解码性准则预测大型语言模型中隐藏状态选择何时优于多数投票

Zhixiang wang, Ziliang Hong, Ulas Bagci

机构 * Northwestern University(西北大学)

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

AI总结 该研究提出可解码性准则及CASE方法,可预测大型语言模型中隐藏状态选择何时优于多数投票,CASE在通用和医疗LLM的中、高难度问题上均有显著提升,且预测可跨领域迁移。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17916 2026-08-19 cs.IT math.IT 新提交 50%

On the Estimation of Chernoff Information

关于Chernoff信息的估计

Kadircan Aksoy, Peter Jung

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

AI总结 针对Chernoff信息非参数估计的难题,通过导数条件重构优化并结合k近邻法与二分法,证明了导数估计量的L₂一致性,提出了Chernoff信息的非参数估计方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.15999 2026-08-18 cs.AI 新提交 50%

MUPA$^{2}$E: Multimodal Unified Perception with Asymmetric Attention for Emotion Assessment

MUPA²E:用于情绪评估的非对称注意力多模态统一感知框架

Stefanos Gkikas, Eric Nichols, Christian Arzate Cruz, Randy Gomez

机构 * Honda Research Institute Japan(日本本田研究所)

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

AI总结 本文提出MUPA²E多模态统一感知框架,用共享非对称注意力骨干处理面部视频与EEG,在DMER数据集上对比多配置,发现时长线索影响分类,控制时长后准确率下降,证明统一架构处理异质信号的可行性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07183 2026-08-10 cs.LG 新提交 50%

Conformal Fusion Under Missing Modalities

缺失模态下的共形融合

Alireza Moayedikia

机构 * Swinburne University of Technology(斯威本科技大学)

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

AI总结 本文提出MCCF架构,解决缺失模态下的多模态融合问题,该架构兼具模态缺失鲁棒性与校准不确定性,在多基准测试中表现出良好的覆盖率与精度性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.29256 2026-08-03 cs.LG 新提交 50%

UniPolymer: A Unified Framework for Property Prediction, Structure Recommendation, and Evaluation in Polyimide Design

UniPolymer:聚酰亚胺设计中用于属性预测、结构推荐与评估的统一框架

Junquan Hu, Zhihui Wang, Peng Xu, Xinru Guo, Xintong Li, Kun Lu, Ben Fei

机构 * The Chinese University of Hong Kong(香港中文大学)

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

AI总结 UniPolymer是聚酰亚胺设计的统一框架,通过建立结构-属性映射、生成候选并评估排序,提升了属性预测与候选评估性能,减少了高成本实验的候选数量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.04128 2026-07-31 cs.AI 版本更新 50%

Decision-oriented joint optimization of evidence fusion based on event-conditioned credibility

面向决策的、基于事件条件可信度的证据融合联合优化

Chaoxiong Ma, Yan Liang, Huixia Zhang, Hao Sun

专题命中 融合架构与评测 :decision-level fusion(abstract)

AI总结 针对异构源决策级融合中关键证据易被低估问题,本文提出事件条件可信度,构建联合优化模型,经实验验证其可信度排名更贴合真实值、对正确事件支持度更高且不动点达成率高。

Comments 27 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.24232 2026-07-28 cs.IR 新提交 50%

Strategy-Aware Parameter-Efficient Adaptation for LLM-based Auto-Bidding

基于大语言模型的自动出价的策略感知参数高效适配

Songyue Cai, Lianyu Wang, Shan Gu, Ziru Xu, Jian Xu, Xiaofeng Zhu, Bo Zheng

专题命中 融合架构与评测 :multi-modal fusion(abstract)

AI总结 研究广告自动出价问题,提出SAGE框架,通过位置增强、文本对齐和约束门控LoRA三个组件,实现参数高效多模态对齐,在大规模基准实验中性能卓越,调整参数少,消融研究验证各组件贡献。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.23822 2026-07-28 cs.LG 新提交 50%

DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification

DriveDNA:用于驾驶风格识别的大规模多模态自然驾驶数据集及基准测试

Yuhang Wang, Lingyao Li, Hao Zhou

机构 * University of South Florida(南佛罗里达大学) University of Arizona(亚利桑那大学)

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

AI总结 该研究引入DriveDNA数据集及基准测试用于驾驶风格识别,定义驾驶风格为车辆在相似条件下的特定行为模式,通过三个核心任务评估,对比多种基线方法得出学习表示更优,视频模型有路线泄漏问题,强调可靠评估需考虑多方面因素。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22884 2026-07-28 cs.CL 新提交 50%

CHiPS: Character Histograms and Positional Signals for Lightweight Authorship Attribution in Romanian Texts

CHiPS:罗马尼亚语文本中用于轻量级作者归属的字符直方图和位置信号

Sanda-Maria Avram, George C. Ţurcaş

机构 * Faculty of Mathematics and Computer Science, Babeş-Bolyai University(巴比什-波雅依大学数学与计算机科学学院)

专题命中 融合架构与评测 :decision-level fusion(abstract)

AI总结 该研究针对罗马尼亚语文本提出CHiPS轻量级字符级作者归属方法,研究两种互补写作风格指纹,包括字符直方图分类器和位置信号分类器,还介绍了融合变体等,通过实验探讨受限字符证据在严格泄漏控制下的效果。

Comments 17 pages, 12 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22779 2026-07-28 cs.LG cs.AI 新提交 50%

Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control

使用基于查询的变压器进行多模态表面肌电手势识别以用于假肢控制

Federico Del Pup, Elisa Tentori, Manfredo Atzori

机构 * Department of Information Engineering, University of Padua(帕多瓦大学信息工程系) Padova Neuroscience Center, University of Padua(帕多瓦大学帕多瓦神经科学中心) Department of Biomedical Sciences, University of Padua(帕多瓦大学生物医学科学系) Department of Neuroscience, University of Padua(帕多瓦大学神经科学系) Information Systems Institute, University of Applied Sciences Western Switzerland (HES-SO Valais)(瑞士西部应用科学大学(HES-SO瓦莱州)信息系统研究所)

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

AI总结 研究针对表面肌电手势识别用于假肢控制时当前架构的局限,提出EMG-CrossFormer,通过级联交叉注意力融合层组合单模态编码器表示,经实验验证该方法能提升仅sEMG解码及多模态融合下的手势识别性能。

Comments GitHub repository: see https://github.com/deepPNClab/emg-crossformer

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.20517 2026-07-24 cs.LG 新提交 50%

Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs

多模态CoLRAG-TF:复杂PDF的三重过滤检索

Takato Yasuno

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

AI总结 研究针对异构PDF集合检索增强生成的挑战,提出多模态CoLRAG-TF四轴融合架构,集成多种技术。构建多模态索引,经贝叶斯优化确定融合权重。实验显示其检索召回率高,多跳答案相似性提升显著,还适用于视觉输入,提供通用框架。

Comments 18 pages, 8 tables, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.17330 2026-07-23 cs.LG cs.AI 版本更新 50%

SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework

SubQuad:在自适应受体框架中利用分布平衡目标的近二次自由结构推断

Rong Fu, Zijian Zhang, Kun Liu, Jiekai Wu, Xianda Li, Simon Fong

机构 * University of Macau(澳门大学) University of Pennsylvania(宾夕法尼亚大学) University of Southampton(南安普顿大学) Juntendo University(顺天堂大学) University of Bologna(博洛尼亚大学)

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

AI总结 SubQuad通过结合抗原感知的近子二次检索、GPU加速的亲和力核、学习多模态融合和公平性约束聚类,解决大规模群体适应性免疫谱分析中的二次成本和数据不平衡问题,提升效率与公平性。

Comments 27 pages, 9 figures. In the previous version, Juntendo University was erroneously listed as the affiliation; we must clarify that this paper has absolutely no relation to Juntendo University. Therefore, we have replaced this affiliation in the new version

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.16216 2026-07-22 math.OC 版本更新 50%

Conservative fusion of unbiased partial state estimates: CI is optimal

无偏部分状态估计的保守融合:协方差交集是最优的

Jochen Trumpf, Behzad Zamani, Chris Manzie

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

AI总结 研究两个无偏部分状态估计信息融合时,证明协方差交集(CI)在保守无偏线性融合规则中最优,还表明三个优化问题等价,给出可解性条件及相关成本函数最优解方程。

Comments Provisionally accepted for Automatica

详情

展开后加载摘要…

URL PDF HTML 收藏