@article{bb118700,
        AUTHOR = "Zhu, A. and Hu, M. and Wang, X.H. and Ren, F.",
        TITLE = "Beneficial Noise Learning for Robust Multimodal Fusion",
        JOURNAL = MultMed,
        VOLUME = "28",
        YEAR = "2026",
        PAGES = "5900-5911",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115275"}

@article{bb118701,
        AUTHOR = "Gao, C.Z. and Li, W. and Weng, D. and Tao, R. and Xia, X.G. and Du, Q.",
        TITLE = "HIMO: Cross-Arbitrary-Modality Image Invariant Feature Transform with
Hierarchical Intrinsic Major Orientation",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "9001-9018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115276"}

@article{bb118702,
        AUTHOR = "Shi, X. and Zhang, R. and Liu, J.W. and Liu, Y.P. and Liang, Z. and Cheng, Q.K. and Lu, W.",
        TITLE = "Modality Equilibrium Matters: Minor-Modality-Aware Adaptive
Alternating for Cross-Modal Memory Enhancement",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "10176-10183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115277"}

@article{bb118703,
        AUTHOR = "Tian, W. and Du, Z.L. and Zhao, X.L. and Yu, Q.",
        TITLE = "AMTFusion: Boosting 3D Object Detection by Adaptive Multi-Modal
Temporal Fusion and Augmentation",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "11561-11575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115278"}

@article{bb118704,
        AUTHOR = "Yang, B. and Jiang, Z.H. and Pan, D. and Lin, Z.P. and Gui, W.H.",
        TITLE = "MOFM: A Multiple-in-One Flow Mamba for Unregistered Multi-Modal Image
Fusion",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "12296-12310",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115279"}

@article{bb118705,
        AUTHOR = "Zhu, Q.X. and Luo, X.F.",
        TITLE = "Q-PEIFN: A multimodal image fusion method based on quality-aware
progressive enhanced low-rank representation",
        JOURNAL = IVC,
        VOLUME = "174",
        YEAR = "2026",
        PAGES = "106112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115280"}

@article{bb118706,
        AUTHOR = "Liu, Y.M. and Gao, B. and Yang, X. and Li, H. and Yu, W.X. and Xu, H.R.",
        TITLE = "DBCS-T: A Dual-Branch Cross-Attention Synergistic Transformer for
Multimodal Image Fusion and Semantic Segmentation",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "16",
        PAGES = "2700",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115281"}

@article{bb118707,
        AUTHOR = "Hong, Y.M. and Leng, C.C. and Pei, Z.",
        TITLE = "Structure-Based Feature Representation for Robust Multi-Modal Image
Matching",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "16",
        PAGES = "2744",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115282"}

@inproceedings{bb118708,
        AUTHOR = "Kim, S. and Kokilepersaud, K. and Prabhushankar, M. and AlRegib, G.",
        TITLE = "Countering Multi-modal Representation Collapse through Rank-targeted
Fusion",
        BOOKTITLE = WACV26,
        YEAR = "2026",
        PAGES = "4744-4754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115283"}

@article{bb118709,
        AUTHOR = "Xu, H.R. and Peng, P.X. and Xia, C. and Tan, G. and Chang, Y.Q. and Zhang, X. and Li, L. and Tian, Y.H.",
        TITLE = "Decomposed Multi-Modality Fusion: Integrating Frames and Events for
Efficient Visuomotor Policies",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "11934-11951",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115284"}

@article{bb118710,
        AUTHOR = "Chen, J. and Li, Q.Q. and Dong, K. and Liao, J.H. and Zhang, D.",
        TITLE = "Multi-Source Fusion Positioning Revisited by Drawing on Human
Thinking Process",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "12366-12383",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115285"}

@article{bb118711,
        AUTHOR = "Zhu, C.G. and Chen, H.F. and Guo, G.Q. and Yang, D.S. and Zhang, K. and Gao, S.",
        TITLE = "TMamba: Global Channel-Location Token Interaction for Multi-Modality
Image Fusion",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "12917-12929",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115286"}

@article{bb118712,
        AUTHOR = "Gui, Z. and Huang, H. and Yang, G.Y. and Liu, J. and Ma, J. and He, W.",
        TITLE = "FreedomDiVe: Task-free image fusion via marginal distribution-based
diffusion variational estimation",
        JOURNAL = PR,
        VOLUME = "180",
        YEAR = "2026",
        PAGES = "114400",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115287"}

@article{bb118713,
        AUTHOR = "Feng, D.Z. and Qiu, C.X. and Yue, T. and Hu, X.",
        TITLE = "HCDi-Fusion: Hybrid-Conditioned Diffusion Model for Cross-Resolution
Multimodal Image Fusion",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "13738-13752",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115288"}

@article{bb118714,
        AUTHOR = "Peng, T. and Han, Z.Q. and Tang, T.F. and Ma, X.P. and Ye, Y.X.",
        TITLE = "RIPC: A novel FFT-Based multimodal image matching framework with
radiometric, scale and rotation invariance",
        JOURNAL = PandRS,
        VOLUME = "240",
        YEAR = "2026",
        PAGES = "671-689",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115289"}

@article{bb118715,
        AUTHOR = "Jing, R. and Gao, Q.X. and Duan, Y. and Gao, X.B.",
        TITLE = "M3amba: Multi-Modality Mamba for Image Fusion",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "9359-9371",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115290"}

@article{bb118716,
        AUTHOR = "Zhou, T.Y. and Ding, W.P. and Chen, Y.P. and Huang, J.S. and Luo, H.",
        TITLE = "MMDiffuzzy: Fuzzy memory guided diffusion for uncertainty-aware
multimodal fusion in WSI analysis",
        JOURNAL = PR,
        VOLUME = "180",
        YEAR = "2026",
        PAGES = "114394",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115291"}

@article{bb118717,
        AUTHOR = "Huang, W. and Yang, P.F. and Zhang, L. and Cheng, H.Z. and Li, H.J. and Qin, F. and Li, J.P. and Jiang, X. and Li, R. and Chen, H.",
        TITLE = "Dual-domain attention for individualized visual encoding from
multimodal neuroimaging",
        JOURNAL = PR,
        VOLUME = "180",
        YEAR = "2026",
        PAGES = "114539",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115292"}

@inproceedings{bb118718,
        AUTHOR = "Patapati, S. and Srinivasan, T.",
        TITLE = "Multimodal Graph Representation Learning over Arbitrary Sets of
Modalities",
        BOOKTITLE = WACV26,
        YEAR = "2026",
        PAGES = "7104-7115",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115293"}

@inproceedings{bb118719,
        AUTHOR = "Dayal, A. and Divya, P. and Tiwari, N. and Cenkeramaddi, L.R. and Mohan, C.K. and Kumar, A.",
        TITLE = "Bridging the Domain Gap in Small Multimodal Models:
A Dual-level Alignment Perspective",
        BOOKTITLE = WACV26,
        YEAR = "2026",
        PAGES = "8262-8271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115294"}

@inproceedings{bb118720,
        AUTHOR = "Xue, F. and Elflein, S. and Leal Taixe, L. and Zhou, Q.",
        TITLE = "MATCHA: Towards Matching Anything",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "27081-27091",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115295"}

@inproceedings{bb118721,
        AUTHOR = "Zhou, B. and Li, L. and Wang, Y.J. and Liu, H.F. and Yao, Y.Z. and Wang, W.G.",
        TITLE = "UniAlign: Scaling Multimodal Alignment within One Unified Model",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "29644-29655",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115296"}

@inproceedings{bb118722,
        AUTHOR = "Hou, J.M. and Chen, X.Y. and Ran, R. and Cong, X.F. and Liu, X.Y. and You, J.W. and Deng, L.J.",
        TITLE = "Binarized Neural Network for Multi-spectral Image Fusion",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "2236-2245",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115297"}

@inproceedings{bb118723,
        AUTHOR = "Li, Y. and Xing, Y.F. and Lan, X.Y. and Li, X. and Chen, H.F. and Jiang, D.M.",
        TITLE = "AlignMamba: Enhancing Multimodal Mamba with Local and Global
Cross-Modal Alignment",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "24774-24784",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115298"}

@inproceedings{bb118724,
        AUTHOR = "Maniparambil, M. and Akshulakov, R. and Djilali, Y.A.D. and Narayan, S. and Singh, A. and O'Connor, N.E.",
        TITLE = "Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "29847-29857",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115299"}

@inproceedings{bb118725,
        AUTHOR = "Li, H. and Hou, Y.N. and Xing, X.H. and Ma, Y.X. and Sun, X. and Zhang, Y.",
        TITLE = "OccMamba: Semantic Occupancy Prediction with State Space Models",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "11949-11959",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115300"}

@inproceedings{bb118726,
        AUTHOR = "Wu, G.Y. and Liu, H.Y. and Fu, H.M. and Peng, Y.C. and Liu, J.Y. and Fan, X. and Liu, R.S.",
        TITLE = "Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality
Image Fusion and Beyond",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "17882-17891",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115301"}

@inproceedings{bb118727,
        AUTHOR = "Tran, Q.H. and Ahmed, M. and Popattia, M. and Ahmed, M.H. and Konin, A. and Zia, M.Z.",
        TITLE = "Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "L: 141-161",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115302"}

@inproceedings{bb118728,
        AUTHOR = "Li, C.X. and Liu, X.Y. and Wang, C. and Liu, Y.F. and Yu, W.H. and Shao, J. and Yuan, Y.X.",
        TITLE = "GTP-4O: Modality-prompted Heterogeneous Graph Learning for Omni-modal
Biomedical Representation",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "IV: 168-187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115303"}

@inproceedings{bb118729,
        AUTHOR = "Song, Z.Q. and Wang, L.F.",
        TITLE = "Dual Multi-Modal Feature Fusion Network for the Evaluation of
Osteosarcoma",
        BOOKTITLE = ICIP24,
        YEAR = "2024",
        PAGES = "2937-2943",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115304"}

@inproceedings{bb118730,
        AUTHOR = "Gao, Z.X. and Jiang, X. and Xu, X. and Shen, F.M. and Li, Y.J. and Shen, H.T.",
        TITLE = "Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "26866-26875",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115305"}

@inproceedings{bb118731,
        AUTHOR = "Jiang, H. and Karpur, A. and Cao, B. and Huang, Q.X. and Araujo, A.",
        TITLE = "OmniGlue: Generalizable Feature Matching with Foundation Model
Guidance",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "19865-19875",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115306"}

@inproceedings{bb118732,
        AUTHOR = "Yi, X.P. and Xu, H. and Zhang, H. and Tang, L.F. and Ma, J.Y.",
        TITLE = "Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and
Interactive Image Fusion",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "27016-27025",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115307"}

@inproceedings{bb118733,
        AUTHOR = "Vouitsis, N. and Liu, Z.Y. and Gorti, S.K. and Villecroze, V. and Cresswell, J.C. and Yu, G.W. and Loaiza Ganem, G. and Volkovs, M.",
        TITLE = "Data-Efficient Multimodal Fusion on a Single GPU",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "27229-27241",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115308"}

@inproceedings{bb118734,
        AUTHOR = "Zhao, Z.X. and Bai, H.W. and Zhang, J.S. and Zhang, Y. and Zhang, K. and Xu, S. and Chen, D.D. and Timofte, R. and Van Gool, L.J.",
        TITLE = "Equivariant Multi-Modality Image Fusion",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "25912-25921",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115309"}

@inproceedings{bb118735,
        AUTHOR = "Han, K.Y. and Cao, F.Z. and Shi, T.X. and Wang, P.",
        TITLE = "A Dual Attention Network for Multimodal Remote Sensing Image Matching",
        BOOKTITLE = CVIDL23,
        YEAR = "2023",
        PAGES = "128-134",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115310"}

@inproceedings{bb118736,
        AUTHOR = "Liu, B. and Xu, Z.Q. and Bao, X.L. and Zhong, Z.",
        TITLE = "MUNformer: A strong encoder that uses multi-level features extracted
by different feature extractors for fusion",
        BOOKTITLE = CVIDL23,
        YEAR = "2023",
        PAGES = "291-295",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115311"}

@inproceedings{bb118737,
        AUTHOR = "He, C.M. and Li, K. and Xu, G.X. and Zhang, Y. and Hu, R.Z. and Guo, Z.H. and Li, X.",
        TITLE = "Degradation-Resistant Unfolding Network for Heterogeneous Image
Fusion",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "12577-12587",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115312"}

@inproceedings{bb118738,
        AUTHOR = "Liu, J.Y. and Liu, Z. and Wu, G.Y. and Ma, L. and Liu, R.S. and Zhong, W. and Luo, Z.X. and Fan, X.",
        TITLE = "Multi-interactive Feature Learning and a Full-time Multi-modality
Benchmark for Image Fusion and Segmentation",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "8081-8090",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115313"}

@inproceedings{bb118739,
        AUTHOR = "Sippel, F. and Seiler, J. and Kaup, A.",
        TITLE = "Cross Spectral Image Reconstruction Using a Deep Guided Neural
Network",
        BOOKTITLE = ICIP23,
        YEAR = "2023",
        PAGES = "226-230",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115314"}

@inproceedings{bb118740,
        AUTHOR = "Myers, A. and Kvinge, H. and Emerson, T.",
        TITLE = "TopFusion: Using Topological Feature Space for Fusion and Imputation
in Multi-Modal Data",
        BOOKTITLE = TAG-PRA23,
        YEAR = "2023",
        PAGES = "600-609",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115315"}

@inproceedings{bb118741,
        AUTHOR = "Xue, Z. and Marculescu, R.",
        TITLE = "Dynamic Multimodal Fusion",
        BOOKTITLE = MULA23,
        YEAR = "2023",
        PAGES = "2575-2584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115316"}

@inproceedings{bb118742,
        AUTHOR = "Kong, L.K. and Qi, X.S. and Shen, Q.J. and Wang, J.C. and Zhang, J.Y. and Hu, Y. and Zhou, Q.C.",
        TITLE = "Indescribable Multi-Modal Spatial Evaluator",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "9853-9862",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115317"}

@inproceedings{bb118743,
        AUTHOR = "Zhao, Z.X. and Bai, H.W. and Zhang, J.S. and Zhang, Y. and Xu, S. and Lin, Z. and Timofte, R. and Van Gool, L.J.",
        TITLE = "CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for
Multi-Modality Image Fusion",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "5906-5916",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115318"}

@inproceedings{bb118744,
        AUTHOR = "Li, Y.W. and Quan, R.J. and Zhu, L.C. and Yang, Y.",
        TITLE = "Efficient Multimodal Fusion via Interactive Prompting",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "2604-2613",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115319"}

@inproceedings{bb118745,
        AUTHOR = "Wetzer, E. and Lindblad, J. and Sladoje, N.",
        TITLE = "Can Representation Learning for Multimodal Image Registration be
Improved by Supervision of Intermediate Layers?",
        BOOKTITLE = IbPRIA23,
        YEAR = "2023",
        PAGES = "261-275",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115320"}

@inproceedings{bb118746,
        AUTHOR = "Huang, Z.B. and Liu, J.Y. and Fan, X. and Liu, R.S. and Zhong, W. and Luo, Z.X.",
        TITLE = "ReCoNet: Recurrent Correction Network for Fast and Efficient
Multi-modality Image Fusion",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XVIII:539-555",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115321"}

@inproceedings{bb118747,
        AUTHOR = "Duan, J.L. and Chen, L.Q. and Tran, S. and Yang, J.Y. and Xu, Y. and Zeng, B. and Chilimbi, T.",
        TITLE = "Multi-modal Alignment using Representation Codebook",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "15630-15639",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115322"}

@inproceedings{bb118748,
        AUTHOR = "Xue, Z.H. and Ren, S.C. and Gao, Z.Q. and Zhao, H.",
        TITLE = "Multimodal Knowledge Expansion",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "834-843",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115323"}

@inproceedings{bb118749,
        AUTHOR = "Zolfaghari, M. and Zhu, Y. and Gehler, P. and Brox, T.",
        TITLE = "CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video
Representations",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "1430-1439",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115324"}

@inproceedings{bb118750,
        AUTHOR = "Yang, J.H. and Huang, Y. and Ma, Z.Y. and Wang, L.",
        TITLE = "CMF: Cascaded Multi-Model Fusion for Referring Image Segmentation",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "2289-2293",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115325"}

@inproceedings{bb118751,
        AUTHOR = "Panda, R. and Chen, C.F.R. and Fan, Q.F. and Sun, X. and Saenko, K. and Oliva, A. and Feris, R.S.",
        TITLE = "AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "7556-7565",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115326"}

@inproceedings{bb118752,
        AUTHOR = "Shi, Z.S. and Liang, J. and Li, Q.Q. and Zheng, H.Y. and Gu, Z.R. and Dong, J.Y. and Zheng, B.",
        TITLE = "Multi-Modal Multi-Action Video Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "13658-13667",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115327"}

@inproceedings{bb118753,
        AUTHOR = "Huang, S.C. and Shen, L.Y. and Lungren, M.P. and Yeung, S.",
        TITLE = "GLoRIA: A Multimodal Global-Local Representation Learning Framework
for Label-efficient Medical Image Recognition",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "3922-3931",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115328"}

@inproceedings{bb118754,
        AUTHOR = "Chen, B. and Rouditchenko, A. and Duarte, K. and Kuehne, H. and Thomas, S. and Boggust, A. and Panda, R. and Kingsbury, B. and Feris, R.S. and Harwath, D. and Glass, J. and Picheny, M. and Chang, S.F.",
        TITLE = "Multimodal Clustering Networks for Self-supervised Learning from
Unlabeled Videos",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "7992-8001",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115329"}

@inproceedings{bb118755,
        AUTHOR = "Liang, T. and Lin, G.S. and Feng, L. and Zhang, Y. and Lv, F.M.",
        TITLE = "Attention is not Enough: Mitigating the Distribution Discrepancy in
Asynchronous Multimodal Sequence Fusion",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "8128-8136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115330"}

@inproceedings{bb118756,
        AUTHOR = "Liu, Y.Z. and Fan, Q.N. and Zhang, S.H. and Dong, H. and Funkhouser, T. and Yi, L.",
        TITLE = "Contrastive Multimodal Fusion with TupleInfoNCE",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "734-743",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115331"}

@inproceedings{bb118757,
        AUTHOR = "Ouerghi, H. and Mourali, O. and Zagrouba, E.",
        TITLE = "Multi-modal Image Fusion Based on Weight Local Features and Novel
Sum-modified-laplacian in Non-subsampled Shearlet Transform Domain",
        BOOKTITLE = ISVC20,
        YEAR = "2020",
        PAGES = "II:166-179",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115332"}

@inproceedings{bb118758,
        AUTHOR = "Perez Rua, J.M. and Vielzeuf, V. and Pateux, S. and Baccouche, M. and Jurie, F.",
        TITLE = "MFAS: Multimodal Fusion Architecture Search",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6959-6968",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115333"}

@inproceedings{bb118759,
        AUTHOR = "Sun, S.H. and Hu, J. and Yao, M.Q. and Hu, J.R. and Yang, X.D. and Song, Q. and Wu, X.",
        TITLE = "Robust Multimodal Image Registration Using Deep Recurrent Reinforcement
Learning",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "II:511-526",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115334"}

@inproceedings{bb118760,
        AUTHOR = "Vielzeuf, V. and Lechervy, A. and Pateux, S. and Jurie, F.",
        TITLE = "CentralNet: A Multilayer Approach for Multimodal Fusion",
        BOOKTITLE = MultLearnApp18,
        YEAR = "2018",
        PAGES = "VI:575-589",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115335"}

@inproceedings{bb118761,
        AUTHOR = "Son, C.H. and Zhang, X.P.",
        TITLE = "Multimodal fusion via a series of transfers for noise removal",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "530-534",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115336"}

@inproceedings{bb118762,
        AUTHOR = "Shrivastava, A. and Rastegari, M. and Shekhar, S. and Chellappa, R. and Davis, L.S.",
        TITLE = "Class consistent multi-modal fusion with binary features",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2282-2291",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115337"}

@inproceedings{bb118763,
        AUTHOR = "Kasiri, K. and Fieguth, P.W. and Clausi, D.A.",
        TITLE = "Self-similarity measure for multi-modal image registration",
        BOOKTITLE = ICIP16,
        YEAR = "2016",
        PAGES = "4498-4502",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115338"}

@inproceedings{bb118764,
        AUTHOR = "Kasiri, K. and Fieguth, P.W. and Clausi, D.A.",
        TITLE = "Structural Representations for Multi-modal Image Registration Based on
Modified Entropy",
        BOOKTITLE = ICIAR15,
        YEAR = "2015",
        PAGES = "82-89",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115339"}

@inproceedings{bb118765,
        AUTHOR = "Zhang, H. and Chen, L. and Liu, J. and Yuan, J.S.",
        TITLE = "Hierarchical multi-feature fusion for multimodal data analysis",
        BOOKTITLE = ICIP14,
        YEAR = "2014",
        PAGES = "5916-5920",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115340"}

@inproceedings{bb118766,
        AUTHOR = "Shen, X.Y. and Xu, L. and Zhang, Q. and Jia, J.Y.",
        TITLE = "Multi-modal and Multi-spectral Registration for Natural Images",
        BOOKTITLE = ECCV14,
        YEAR = "2014",
        PAGES = "IV: 309-324",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115341"}

@inproceedings{bb118767,
        AUTHOR = "Sahoo, S. and Nanda, P.K. and Samant, S.",
        TITLE = "Tsallis and Renyi's embedded entropy based mutual information for
multimodal image registration",
        BOOKTITLE = NCVPRIPG13,
        YEAR = "2013",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115342"}

@inproceedings{bb118768,
        AUTHOR = "Kim, M.J. and Han, D.K. and Ko, H.S.",
        TITLE = "Multimodal image fusion via sparse representation with local patch
dictionaries",
        BOOKTITLE = ICIP13,
        YEAR = "2013",
        PAGES = "1301-1305",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115343"}

@inproceedings{bb118769,
        AUTHOR = "Glodek, M. and Schels, M. and Palm, G. and Schwenker, F.",
        TITLE = "Multi-modal Fusion based on classifiers using reject options and Markov
Fusion Networks",
        BOOKTITLE = ICPR12,
        YEAR = "2012",
        PAGES = "1084-1087",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115344"}

@inproceedings{bb118770,
        AUTHOR = "Forsberg, D. and Farneback, G. and Knutsson, H. and Westin, C.F.",
        TITLE = "Multi-modal Image Registration Using Polynomial Expansion and Mutual
Information",
        BOOKTITLE = WBIR12,
        YEAR = "2012",
        PAGES = "40-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115345"}

@inproceedings{bb118771,
        AUTHOR = "Bodensteiner, C. and Huebner, W. and Jueng Ling, K. and Mueller, J. and Arens, M.",
        TITLE = "Local multi-modal image matching based on self-similarity",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "937-940",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115346"}

@inproceedings{bb118772,
        AUTHOR = "Vegh, V. and Yang, Z.Y. and Tieng, Q.M. and Reutens, D.C.",
        TITLE = "Multimodal image registration using stochastic differential equation
optimization",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "4385-4388",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115347"}

@inproceedings{bb118773,
        AUTHOR = "Peng, T.Y. and Yigitsoy, M. and Eslami, A. and Bayer, C. and Navab, N.",
        TITLE = "Deformable Registration of Multi-modal Microscopic Images Using a
Pyramidal Interactive Registration-Learning Methodology",
        BOOKTITLE = WBIR14,
        YEAR = "2014",
        PAGES = "144-153",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115348"}

@inproceedings{bb118774,
        AUTHOR = "Wachinger, C. and Navab, N.",
        TITLE = "Manifold Learning for Multi-modal Image Registration",
        BOOKTITLE = BMVC10,
        YEAR = "2010",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115349"}

@inproceedings{bb118775,
        AUTHOR = "Xu, J. and Yuan, J.S. and Wu, Y.",
        TITLE = "Multimodal Partial Estimates Fusion",
        BOOKTITLE = ICCV09,
        YEAR = "2009",
        PAGES = "2177-2184",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115350"}

@inproceedings{bb118776,
        AUTHOR = "Ma, W.Y. and Li, S. and Yao, Y.F. and Lan, C. and Gao, S.Q. and Tang, H. and Jing, X.Y.",
        TITLE = "Multi-Modal Biometrics Pixel Level Fusion and KPCA-RBF Feature
Classification for Single Sample Recognition Problem",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115351"}

@inproceedings{bb118777,
        AUTHOR = "Town, C. and Zhu, Z.G.",
        TITLE = "Sensor Fusion and Environmental Modelling for Multimodal Sentient
Computing",
        BOOKTITLE = MSCSAS07,
        YEAR = "2007",
        PAGES = "1-2",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115352"}

@inproceedings{bb118778,
        AUTHOR = "Datar, M. and Gopalakrishnan, G. and Ranjan, S. and Mullick, R.",
        TITLE = "Anatomically Guided Registration for Multimodal Images",
        BOOKTITLE = AIPR06,
        YEAR = "2006",
        PAGES = "10-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115353"}

@inproceedings{bb118779,
        AUTHOR = "Gopalakrishnan, G. and Kumar, S.V.B. and Narayanan, A. and Mullick, R.",
        TITLE = "A fast piecewise deformable method for multi-modality image
registration",
        BOOKTITLE = AIPR05,
        YEAR = "2005",
        PAGES = "114-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115354"}

@inproceedings{bb118780,
        AUTHOR = "Kelman, A. and Sofka, M. and Stewart, C.V.",
        TITLE = "Keypoint Descriptors for Matching Across Multiple Image Modalities and
Non-linear Intensity Variations",
        BOOKTITLE = Fusion07,
        YEAR = "2007",
        PAGES = "1-7",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115355"}

@inproceedings{bb118781,
        AUTHOR = "Guo, Y.J. and Lu, C.C.",
        TITLE = "Multi-modality Image Registration Using Mutual Information Based on
Gradient Vector Flow",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "III: 697-700",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115356"}

@inproceedings{bb118782,
        AUTHOR = "Andronache, A. and Cattin, P.C. and Szekely, G.",
        TITLE = "Local Intensity Mapping for Hierarchical Non-rigid Registration of
Multi-modal Images Using the Cross-Correlation Coefficient",
        BOOKTITLE = WBIR06,
        YEAR = "2006",
        PAGES = "26-33",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115357"}

@inproceedings{bb118783,
        AUTHOR = "Cremers, D. and Guetter, C. and Xu, C.Y.",
        TITLE = "Nonparametric Priors on the Space of Joint Intensity Distributions for
Non-Rigid Multi-Modal Image Registration",
        BOOKTITLE = CVPR06,
        YEAR = "2006",
        PAGES = "II: 1777-1783",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115358"}

@inproceedings{bb118784,
        AUTHOR = "Zollei, L. and Wells, W.M.",
        TITLE = "Multi-modal Image Registration Using Dirichlet-Encoded Prior
Information",
        BOOKTITLE = WBIR06,
        YEAR = "2006",
        PAGES = "34-42",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115359"}

@inproceedings{bb118785,
        AUTHOR = "Zollei, L. and Fisher, J. and Wells, W.M.",
        TITLE = "A Unified Statistical and Information Theoretic Framework for
Multi-modal Image Registration",
        BOOKTITLE = "MIT AIM",
        YEAR = "2004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115360"}

@inproceedings{bb118786,
        AUTHOR = "Chan, H.M. and Chung, A.C.S. and Yu, S.C.H. and Norbash, A. and Wells, W.M.",
        TITLE = "Multi-modal image registration by minimizing Kullback-Leibler distance
between expected and observed joint class histograms",
        BOOKTITLE = CVPR03,
        YEAR = "2003",
        PAGES = "II: 570-576",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmf1.html#TT115361"}

@article{bb118787,
        AUTHOR = "Kim, I. and Vachtsevanos, G.J.",
        TITLE = "Overlapping Object Recognition: A Paradigm for Multiple Sensor Fusion",
        JOURNAL = RAMag,
        VOLUME = "5",
        YEAR = "1998",
        NUMBER = "3",
        MONTH = "September",
        PAGES = "37-44",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115362"}

@article{bb118788,
        AUTHOR = "Yu, J.G. and Gao, C.X. and Tian, J.W.",
        TITLE = "Collaborative multicue fusion using the cross-diffusion process for
salient object detection",
        JOURNAL = JOSA-A,
        VOLUME = "33",
        YEAR = "2016",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "404-415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115363"}

@article{bb118789,
        AUTHOR = "Liu, W.B. and Wang, H.B. and Gao, Q.X. and Zhu, Z.R.",
        TITLE = "Multi-modal object detection via transformer network",
        JOURNAL = IET-IPR,
        VOLUME = "17",
        YEAR = "2023",
        NUMBER = "12",
        PAGES = "3541-3550",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115364"}

@article{bb118790,
        AUTHOR = "Lee, S. and Park, J. and Park, J.",
        TITLE = "CrossFormer: Cross-guided attention for multi-modal object detection",
        JOURNAL = PRL,
        VOLUME = "179",
        YEAR = "2024",
        PAGES = "144-150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115365"}

@article{bb118791,
        AUTHOR = "Deng, Y.H. and Liu, X.L. and Yang, K. and Li, Z.H.",
        TITLE = "Flexible thin parts multi-target positioning method of multi-level
feature fusion",
        JOURNAL = IET-IPR,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "11",
        PAGES = "2996-3012",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115366"}

@article{bb118792,
        AUTHOR = "Wang, J.P. and Su, N. and Zhao, C.H. and Yan, Y.M. and Feng, S.",
        TITLE = "Multi-Modal Object Detection Method Based on Dual-Branch Asymmetric
Attention Backbone and Feature Fusion Pyramid Network",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "20",
        PAGES = "3904",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115367"}

@article{bb118793,
        AUTHOR = "Dong, A. and Wang, L. and Liu, J. and Xu, J.Y. and Zhao, G.X. and Zhai, Y. and Lv, G.H. and Cheng, J.",
        TITLE = "Co-Enhancement of Multi-Modality Image Fusion and Object Detection
via Feature Adaptation",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "12624-12637",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115368"}

@article{bb118794,
        AUTHOR = "Cao, Z.H. and Liang, Y.J. and Deng, L.J. and Vivone, G.",
        TITLE = "An Efficient Image Fusion Network Exploiting Unifying Language and
Mask Guidance",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "9845-9862",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115369"}

@article{bb118795,
        AUTHOR = "Liu, Z.W. and Cheng, J. and Fan, J. and Lin, S. and Wang, Y. and Zhao, X.M.",
        TITLE = "Multi-Modal Fusion Based on Depth Adaptive Mechanism for 3D Object
Detection",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "707-717",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115370"}

@article{bb118796,
        AUTHOR = "Yang, Z. and Song, N. and Li, W. and Zhu, X.T. and Zhang, L. and Torr, P.H.S.",
        TITLE = "DeepInteraction++: Multi-Modality Interaction for Autonomous Driving",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "6749-6763",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115371"}

@article{bb118797,
        AUTHOR = "Hu, S. and Liu, T.T. and Han, L.Y. and Xing, R.",
        TITLE = "Vision-language tracking with attention-based optimization",
        JOURNAL = JVCIR,
        VOLUME = "114",
        YEAR = "2026",
        PAGES = "104644",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115372"}

@article{bb118798,
        AUTHOR = "Ning, T. and Lu, K. and Jiang, X. and Xue, J.",
        TITLE = "Mambafusion: State-space model-driven object-scene fusion for
multi-modal 3D object detection",
        JOURNAL = PR,
        VOLUME = "173",
        YEAR = "2026",
        PAGES = "112820",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115373"}

@article{bb118799,
        AUTHOR = "Ning, Z.W. and Liu, Z.J. and Gao, X. and Zuo, Y.F. and Yang, J. and Fang, Y.M. and Liu, W.",
        TITLE = "CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection With IoU
Joint Prediction",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "2177-2190",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match-pl502mmfod2.html#TT115374"}