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

@inproceedings{iclr2020_bertscore_29670,
  title = {{BERTScore: Evaluating Text Generation with BERT}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SkeHuCVFDr},
}

@inproceedings{cvpr2016_robust_11822,
  title = {{Robust Scene Text Recognition With Automatic Rectification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{aaai2023_trocr_4864,
  title = {{TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26538},
}

@inproceedings{cvpr2018_convolutional_12925,
  title = {{Convolutional Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Aneja_Convolutional_Image_Captioning_CVPR_2018_paper.html},
}

@inproceedings{cvpr2017_a_12011,
  title = {{A Hierarchical Approach for Generating Descriptive Image Paragraphs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_learning_13297,
  title = {{Learning Semantic Concepts and Order for Image and Sentence Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Learning_Semantic_Concepts_CVPR_2018_paper.html},
}

@inproceedings{aaai2020_when_103882,
  title = {{When Radiology Report Generation Meets Knowledge Graph}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6989},
}

@inproceedings{cvpr2019_unsupervised_14977,
  title = {{Unsupervised Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_show_14822,
  title = {{Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2023_interactive_21271,
  title = {{Interactive and Explainable Region-Guided Radiology Report Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21371},
}

@inproceedings{cvpr2018_discriminability_13021,
  title = {{Discriminability Objective for Training Descriptive Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Luo_Discriminability_Objective_for_CVPR_2018_paper.html},
}

@inproceedings{aaai2021_improving_765,
  title = {{Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01655-improving-image-captioning-by-leveraging-intra-and-inter-layer-global-representation-in-transformer-network/},
}

@inproceedings{cvpr2019_engaging_14150,
  title = {{Engaging Image Captioning via Personality}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2017_attend_12070,
  title = {{Attend to You: Personalized Image Captioning With Context Sequence Memory Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2017_contrastive_56214,
  title = {{Contrastive Learning for Image Captioning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8884},
}

@inproceedings{cvpr2019_fast_14200,
  title = {{Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_learning_13320,
  title = {{Learning to Evaluate Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Cui_Learning_to_Evaluate_CVPR_2018_paper.html},
}

@inproceedings{aaai2019_hierarchical_103526,
  title = {{Hierarchical Attention Network for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4924},
}

@inproceedings{cvpr2017_skeleton_12643,
  title = {{Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_regularizing_13520,
  title = {{Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Regularizing_RNNs_for_CVPR_2018_paper.html},
}

@inproceedings{aaai2024_image_6269,
  title = {{Image Captioning with Multi-Context Synthetic Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28203},
}

@inproceedings{aaai2024_diusum_5565,
  title = {{DIUSum: Dynamic Image Utilization for Multimodal Summarization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29899},
}

@inproceedings{icml2025_whitened_46675,
  title = {{Whitened CLIP as a Likelihood Surrogate of Images and Captions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45897},
}

@inproceedings{iclr2026_imagine_84357,
  title = {{Imagine How To Change: Explicit Procedure Modeling for Change Captioning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=1lK8LPFcXp},
}