% Key papers for Probabilistic embeddings for cross-modal retrieval (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2019_cross_13985,
  title = {{Cross-Modal Self-Attention Network for Referring Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_deep_14043,
  title = {{Deep Supervised Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_multi_15914,
  title = {{Multi-Modality Cross Attention Network for Image and Sentence Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_imram_15668,
  title = {{IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_learning_12393,
  title = {{Learning Cross-Modal Embeddings for Cooking Recipes and Food Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_look_13345,
  title = {{Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gu_Look_Imagine_and_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_fine_15553,
  title = {{Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_cross_20669,
  title = {{Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21136},
}

@inproceedings{cvpr2020_context_15276,
  title = {{Context-Aware Attention Network for Image-Text Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_polysemous_14659,
  title = {{Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_probabilistic_17652,
  title = {{Probabilistic Embeddings for Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_t2vlad_17969,
  title = {{T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_learning_14394,
  title = {{Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2023_learning_21390,
  title = {{Learning Semantic Relationship Among Instances for Image-Text Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23176},
}

@inproceedings{cvpr2021_stylemeup_17957,
  title = {{StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_learning_17267,
  title = {{Learning Cross-Modal Retrieval With Noisy Labels}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_universal_16409,
  title = {{Universal Weighting Metric Learning for Cross-Modal Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_align_20376,
  title = {{Align and Attend: Multimodal Summarization With Dual Contrastive Losses}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22641},
}

@inproceedings{cvpr2022_cross_18542,
  title = {{Cross Modal Retrieval With Querybank Normalisation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2020_adaptive_103808,
  title = {{Adaptive Cross-Modal Embeddings for Image-Text Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6915},
}

@inproceedings{aaai2024_adaptive_5137,
  title = {{Adaptive Uncertainty-Based Learning for Text-Based Person Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28101},
}

@inproceedings{aaai2024_cross_5531,
  title = {{Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29789},
}

@inproceedings{aaai2024_unifying_7700,
  title = {{Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28585},
}

@inproceedings{cvpr2024_learning_23987,
  title = {{Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29621},
}

@inproceedings{aaai2024_data_5593,
  title = {{Data Roaming and Quality Assessment for Composed Image Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28081},
}

@inproceedings{aaai2024_causality_5386,
  title = {{Causality-Inspired Invariant Representation Learning for Text-Based Person Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29314},
}

@inproceedings{aaai2024_improving_6290,
  title = {{Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28178},
}

@inproceedings{aaai2024_cl2cm_5344,
  title = {{CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28376},
}

@inproceedings{cvpr2025_chat_25696,
  title = {{Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34247},
}

@inproceedings{aaai2026_hierarchical_105624,
  title = {{Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38380},
}

@inproceedings{aaai2024_hierarchical_6204,
  title = {{Hierarchical Aligned Multimodal Learning for NER on Tweet Posts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29831},
}

@inproceedings{cvpr2025_fuzzy_26342,
  title = {{Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34643},
}

@inproceedings{aaai2025_cdtr_8339,
  title = {{CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32717},
}

@inproceedings{aaai2025_dica_8718,
  title = {{DiCA: Disambiguated Contrastive Alignment for Cross-Modal Retrieval with Partial Labels}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34271},
}

@inproceedings{cvpr2024_fine_23472,
  title = {{Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31603},
}

@inproceedings{cvpr2024_how_23719,
  title = {{How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30803},
}

@inproceedings{cvpr2025_neighborretr_27058,
  title = {{NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34645},
}

@inproceedings{aaai2025_adaptive_8039,
  title = {{Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33922},
}

@inproceedings{aaai2025_dynamic_8839,
  title = {{Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32186},
}

@inproceedings{aaai2025_noisy_10125,
  title = {{Noisy Correspondence Rectification via Asymmetric Similarity Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35439},
}