% Key papers for Unimodal-to-multimodal representation transfer (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_cross_11456,
  title = {{Cross Modal Distillation for Supervision Transfer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_learning_12392,
  title = {{Learning Cross-Modal Deep Representations for Robust Pedestrian Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_contextdesc_13970,
  title = {{ContextDesc: Local Descriptor Augmentation With Cross-Modality Context}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_learning_11651,
  title = {{Learning Aligned Cross-Modal Representations From Weakly Aligned Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_multimodal_17457,
  title = {{Multimodal Contrastive Training for Visual Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_bridging_20513,
  title = {{Bridging Search Region Interaction With Template for RGB-T Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22276},
}

@inproceedings{aaai2022_axm_1695,
  title = {{AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/04477-axm-net-implicit-cross-modal-feature-alignment-for-person-re-identification/},
}

@inproceedings{cvpr2023_multimodality_21627,
  title = {{Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22391},
}

@inproceedings{cvpr2024_noisy_24297,
  title = {{Noisy-Correspondence Learning for Text-to-Image Person Re-identification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29265},
}

@inproceedings{cvpr2024_cricavpr_23057,
  title = {{CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30257},
}

@inproceedings{cvpr2021_shared_17890,
  title = {{Shared Cross-Modal Trajectory Prediction for Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_dip_20697,
  title = {{DIP: Dual Incongruity Perceiving Network for Sarcasm Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23004},
}

@inproceedings{neurips2022_multi_65264,
  title = {{Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55023},
}

@inproceedings{aaai2025_mentor_9844,
  title = {{MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33408},
}

@inproceedings{cvpr2023_hidden_21144,
  title = {{Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21306},
}

@inproceedings{cvpr2024_c2kd_22888,
  title = {{C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30032},
}

@inproceedings{cvpr2023_bicro_20467,
  title = {{BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21474},
}

@inproceedings{cvpr2022_interact_19090,
  title = {{Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2022_promoting_2588,
  title = {{Promoting Single-Modal Optical Flow Network for Diverse Cross-Modal Flow Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03562-promoting-single-modal-optical-flow-network-for-diverse-cross-modal-flow-estimation/},
}

@inproceedings{aaai2024_navigating_6744,
  title = {{Navigating Open Set Scenarios for Skeleton-Based Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28247},
}

@inproceedings{cvpr2024_medm2g_24130,
  title = {{MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31821},
}

@inproceedings{cvpr2024_all_22752,
  title = {{All in One Framework for Multimodal Re-identification in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30100},
}

@inproceedings{cvpr2025_alignmamba_25469,
  title = {{AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33680},
}

@inproceedings{cvpr2024_robust_24670,
  title = {{Robust Noisy Correspondence Learning with Equivariant Similarity Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30240},
}

@inproceedings{cvpr2024_accept_22702,
  title = {{Accept the Modality Gap: An Exploration in the Hyperbolic Space}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29303},
}

@inproceedings{cvpr2024_leveraging_23999,
  title = {{Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30099},
}

@inproceedings{aaai2024_distilvpr_5718,
  title = {{DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28905},
}

@inproceedings{cvpr2024_mitigating_24155,
  title = {{Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29805},
}

@inproceedings{aaai2025_seeing_10707,
  title = {{Seeing Beyond Noise: Joint Graph Structure Evaluation and Denoising for Multimodal Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33358},
}

@inproceedings{cvpr2024_data_23110,
  title = {{Data-Efficient Multimodal Fusion on a Single GPU}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31047},
}

@inproceedings{cvpr2025_beyond_25581,
  title = {{Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34488},
}

@inproceedings{aaai2025_measuring_9924,
  title = {{Measuring Cross-Modal Interactions in Multimodal Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35452},
}

@inproceedings{cvpr2025_crossover_25801,
  title = {{CrossOver: 3D Scene Cross-Modal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34960},
}

@inproceedings{neurips2024_cross_72406,
  title = {{Cross-modal Representation Flattening for Multi-modal Domain Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94949},
}

@inproceedings{aaai2024_multi_6695,
  title = {{Multi-Level Cross-Modal Alignment for Image Clustering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29387},
}