% Key papers for Multi-modality image fusion (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2022_vlmo_65449,
  title = {{VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54254},
}

@inproceedings{cvpr2022_multimodal_19403,
  title = {{Multimodal Token Fusion for Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_equivariant_23384,
  title = {{Equivariant Multi-Modality Image Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31376},
}

@inproceedings{cvpr2022_omnivore_19498,
  title = {{Omnivore: A Single Model for Many Visual Modalities}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_delivering_20761,
  title = {{Delivering Arbitrary-Modal Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22543},
}

@inproceedings{cvpr2021_encoder_16943,
  title = {{Encoder Fusion Network With Co-Attention Embedding for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_unsupervised_16425,
  title = {{Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_selective_14788,
  title = {{Selective Sensor Fusion for Neural Visual-Inertial Odometry}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_cross_16769,
  title = {{Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_everything_18785,
  title = {{Everything at Once - Multi-Modal Fusion Transformer for Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2024_bi_5292,
  title = {{Bi-directional Adapter for Multimodal Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27852},
}

@inproceedings{cvpr2016_discriminative_11503,
  title = {{Discriminative Multi-Modal Feature Fusion for RGBD Indoor Scene Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2024_sdstrack_24698,
  title = {{SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29819},
}

@inproceedings{cvpr2023_efficient_20894,
  title = {{Efficient RGB-T Tracking via Cross-Modality Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22251},
}

@inproceedings{aaai2020_urban2vec_100277,
  title = {{Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5450},
}

@inproceedings{cvpr2024_mrfs_24080,
  title = {{MRFS: Mutually Reinforcing Image Fusion and Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30733},
}

@inproceedings{cvpr2024_task_24962,
  title = {{Task-Customized Mixture of Adapters for General Image Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29826},
}

@inproceedings{aaai2018_robust_104048,
  title = {{Robust Collaborative Discriminative Learning for RGB-Infrared Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12307},
}

@inproceedings{cvpr2025_dcevo_25815,
  title = {{DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33788},
}

@inproceedings{aaai2021_multimodal_1037,
  title = {{Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/03199-multimodal-fusion-via-teacher-student-network-for-indoor-action-recognition/},
}

@inproceedings{cvpr2024_probing_24519,
  title = {{Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30218},
}

@inproceedings{aaai2024_generative_6133,
  title = {{Generative-Based Fusion Mechanism for Multi-Modal Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28325},
}

@inproceedings{aaai2024_tr_7485,
  title = {{TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28304},
}

@inproceedings{cvpr2025_one_27140,
  title = {{One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34402},
}

@inproceedings{aaai2024_unifying_7701,
  title = {{Unifying Visual and Vision-Language Tracking via Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28205},
}

@inproceedings{cvpr2025_every_26173,
  title = {{Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33512},
}

@inproceedings{aaai2024_rethinking_7135,
  title = {{Rethinking Reverse Distillation for Multi-Modal Anomaly Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28687},
}

@inproceedings{aaai2024_end_5834,
  title = {{End-to-End RGB-D Image Compression via Exploiting Channel-Modality Redundancy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28588},
}

@inproceedings{cvpr2024_dispel_23231,
  title = {{Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31650},
}

@inproceedings{iclr2024_languagebind_34407,
  title = {{LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18668},
}

@inproceedings{cvpr2024_madtp_24047,
  title = {{MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29185},
}

@inproceedings{aaai2024_lds2ae_6395,
  title = {{LDS2AE: Local Diffusion Shared-Specific Autoencoder for Multimodal Remote Sensing Image Classification with Arbitrary Missing Modalities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29391},
}

@inproceedings{aaai2025_rgbt_10445,
  title = {{RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32618},
}

@inproceedings{aaai2024_a_5060,
  title = {{A Robust Mutual-Reinforcing Framework for 3D Multi-Modal Medical Image Fusion Based on Visual-Semantic Consistency}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28536},
}