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

@inproceedings{cvpr2016_image_11601,
  title = {{Image Captioning With Semantic Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_knowing_12378,
  title = {{Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_semantic_12621,
  title = {{Semantic Compositional Networks for Visual Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_rstnet_17692,
  title = {{RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2017_attention_103918,
  title = {{Attention Correctness in Neural Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11197},
}

@inproceedings{cvpr2019_look_14480,
  title = {{Look Back and Predict Forward in Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2022_end_2036,
  title = {{End-to-End Transformer Based Model for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02585-end-to-end-transformer-based-model-for-image-captioning/},
}

@inproceedings{cvpr2019_good_14254,
  title = {{Good News, Everyone! Context Driven Entity-Aware Captioning for News Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_more_15905,
  title = {{More Grounded Image Captioning by Distilling Image-Text Matching Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2018_semstyle_13575,
  title = {{SemStyle: Learning to Generate Stylised Image Captions Using Unaligned Text}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Mathews_SemStyle_Learning_to_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_injecting_19079,
  title = {{Injecting Semantic Concepts Into End-to-End Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_comprehending_18490,
  title = {{Comprehending and Ordering Semantics for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2017_fine_12275,
  title = {{Fine-Grained Image Classification via Combining Vision and Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_context_12124,
  title = {{Context-Aware Captions From Context-Agnostic Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_tap_17970,
  title = {{TAP: Text-Aware Pre-Training for Text-VQA and Text-Caption}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_beyond_18361,
  title = {{Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2017_text_103958,
  title = {{Text-Guided Attention Model for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11237},
}

@inproceedings{cvpr2020_transform_16384,
  title = {{Transform and Tell: Entity-Aware News Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_memcap_103891,
  title = {{MemCap: Memorizing Style Knowledge for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6998},
}

@inproceedings{cvpr2022_difnet_18576,
  title = {{DIFNet: Boosting Visual Information Flow for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2024_secap_7218,
  title = {{SECap: Speech Emotion Captioning with Large Language Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29902},
}

@inproceedings{aaai2024_noise_6782,
  title = {{Noise-Aware Image Captioning with Progressively Exploring Mismatched Words}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29097},
}

@inproceedings{aaai2024_imagecaptioner2_6273,
  title = {{ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30080},
}

@inproceedings{cvpr2025_benchmarking_25572,
  title = {{Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34150},
}

@inproceedings{aaai2024_relational_7101,
  title = {{Relational Distant Supervision for Image Captioning without Image-Text Pairs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28251},
}

@inproceedings{aaai2025_region_10498,
  title = {{Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32517},
}

@inproceedings{cvpr2024_micap_24062,
  title = {{MICap: A Unified Model for Identity-Aware Movie Descriptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31350},
}

@inproceedings{cvpr2025_preserve_27295,
  title = {{Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34063},
}

@inproceedings{aaai2025_revisiting_10552,
  title = {{Revisiting Change Captioning from Self-supervised Global-Part Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32629},
}

@inproceedings{cvpr2025_towards_27909,
  title = {{Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35023},
}

@inproceedings{cvpr2025_bacon_25546,
  title = {{BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33526},
}

@inproceedings{cvpr2025_semantic_27634,
  title = {{Semantic and Expressive Variations in Image Captions Across Languages}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35077},
}

@inproceedings{iclr2024_alt_33770,
  title = {{Alt-Text with Context: Improving Accessibility for Images on Twitter}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19305},
}

@inproceedings{icml2025_lemon_48083,
  title = {{LEMoN: Label Error Detection using Multimodal Neighbors}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44525},
}

@inproceedings{neurips2024_lotlip_73973,
  title = {{LoTLIP: Improving Language-Image Pre-training for Long Text Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93542},
}

@inproceedings{neurips2025_coconut_76606,
  title = {{COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=L7StVf0UXC},
}

@inproceedings{iclr2026_biocap_86645,
  title = {{BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=SCKLkfgevy},
}

@inproceedings{neurips2026_personal_90307,
  title = {{Personal Visual Memory from Explicit and Implicit Evidence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154605},
}

@inproceedings{cvpr2026_rxncaption_98481,
  title = {{RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Song_RxnCaption_Reformulating_Reaction_Diagram_Parsing_as_Visual_Prompt_Guided_Captioning_CVPR_2026_paper.html},
}

@inproceedings{aaai2026_leveraging_104249,
  title = {{Leveraging Textual Compositional Reasoning for Robust Change Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37778},
}