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

@inproceedings{cvpr2016_video_11954,
  title = {{Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_video_12736,
  title = {{Video Captioning With Transferred Semantic Attributes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_reconstruction_13509,
  title = {{Reconstruction Network for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Reconstruction_Network_for_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_object_15966,
  title = {{Object Relational Graph With Teacher-Recommended Learning for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2022_swinbert_19967,
  title = {{SwinBERT: End-to-End Transformers With Sparse Attention for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2018_video_13699,
  title = {{Video Captioning via Hierarchical Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Video_Captioning_via_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_spatio_16272,
  title = {{Spatio-Temporal Graph for Video Captioning With Knowledge Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_memory_14508,
  title = {{Memory-Attended Recurrent Network for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_spatio_14855,
  title = {{Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_syntax_16313,
  title = {{Syntax-Aware Action Targeting for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_object_14592,
  title = {{Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_m3_13351,
  title = {{M3: Multimodal Memory Modelling for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_M3_Multimodal_Memory_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_end_18755,
  title = {{End-to-End Generative Pretraining for Multimodal Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2021_semantic_1365,
  title = {{Semantic Grouping Network for Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02514-semantic-grouping-network-for-video-captioning/},
}

@inproceedings{cvpr2017_top_12700,
  title = {{Top-Down Visual Saliency Guided by Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_hierarchical_12332,
  title = {{Hierarchical Boundary-Aware Neural Encoder for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_open_17545,
  title = {{Open-Book Video Captioning With Retrieve-Copy-Generate Network}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_hierarchical_18994,
  title = {{Hierarchical Modular Network for Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2019_temporal_103430,
  title = {{Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4826},
}

@inproceedings{cvpr2019_adversarial_13835,
  title = {{Adversarial Inference for Multi-Sentence Video Description}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2024_sharegpt4video_71218,
  title = {{ShareGPT4Video: Improving Video Understanding and Generation with Better Captions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97789},
}

@inproceedings{cvpr2024_video_25220,
  title = {{Video ReCap: Recursive Captioning of Hour-Long Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29430},
}

@inproceedings{aaai2024_set_7324,
  title = {{Set Prediction Guided by Semantic Concepts for Diverse Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28183},
}

@inproceedings{neurips2024_learnability_70425,
  title = {{Learnability Matters: Active Learning for Video Captioning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96680},
}

@inproceedings{cvpr2025_progress_27309,
  title = {{Progress-Aware Video Frame Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32812},
}

@inproceedings{aaai2025_hierarchical_9439,
  title = {{Hierarchical Multi-Source Uncertainty Aggregation for Interactive Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33590},
}

@inproceedings{aaai2025_mams_9831,
  title = {{MAMS: Model-Agnostic Module Selection Framework for Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32478},
}

@inproceedings{icml2026_seeing_54581,
  title = {{Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=qOed6VUiqh},
}

@inproceedings{neurips2024_calvin_70659,
  title = {{CALVIN: Improved Contextual Video Captioning via Instruction Tuning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96463},
}

@inproceedings{iclr2026_carebench_86313,
  title = {{CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=OZtGhb9x7C},
}

@inproceedings{cvpr2026_bridging_98169,
  title = {{Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Wei_Bridging_Brain_and_Semantics_A_Hierarchical_Framework_for_Semantically_Enhanced_CVPR_2026_paper.html},
}

@inproceedings{icml2025_fine_47805,
  title = {{Fine-Grained Captioning of Long Videos through Scene Graph Consolidation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44795},
}